Home Docs Claude Code CLI

One capture · claude-code

One read of Claude Code CLIclaude-code-20261022T180701Z

220 pages moved out of 228 read.

Pages moved 220 significant first

Pages read 228 in this capture

Captured 22 Oct 2026 18:07 UTC

Corpus hash 237d0503e095 corpus-hash

What this read moved

51-75 of 220, page 3 of 9

This capture is too large to show at once. Changes 51-75 of 220 are below, significant first; the rest are on the following screens.

claude-apps-gateway-config Changed · +70 / -70 lines

from line 4

55A Claude apps gateway deployment is configured by one YAML file, conventionally `gateway.yaml`. The file defines everything the gateway does: where it listens, how developers sign in, where inference goes, and which policies and telemetry apply. This page is the reference for every option in that file.

7To write your first one, start from the [quickstart](/docs/en/claude-apps-gateway#quickstart), which builds a minimal working config and runs it. Once you have a config you're happy with, the [deployment guide](/docs/en/claude-apps-gateway-deploy) covers containerizing and hosting it on Kubernetes, Cloud Run, or your own platform.

7To write your first one, start from the [quickstart](/docs/en/claude-apps-gateway#quickstart), which builds a minimal working config and runs it. Once you have a config you're happy with, the [deployment guide](/docs/en/claude-apps-gateway-deploy.md) covers containerizing and hosting it on Kubernetes, Cloud Run, or your own platform.

99The gateway reads the file once, at startup, with `claude gateway --config /path/to/gateway.yaml`. Every option is validated against a schema at boot, so a malformed config fails at start with a field-level error rather than at first use.

1010

from line 60

6060

6161The `oidc` block connects the gateway to your identity provider and decides who can sign in. It names the issuer and OAuth client, maps the claims that carry email and groups, and restricts sign-in by email domain or group.

6262

63OpenID Connect (OIDC) is the SSO protocol the gateway uses with your identity provider; see [Identity provider setup](/docs/en/claude-apps-gateway-deploy#identity-provider-setup) for what to register on the IdP side.

63OpenID Connect (OIDC) is the SSO protocol the gateway uses with your identity provider; see [Identity provider setup](/docs/en/claude-apps-gateway-deploy.md#identity-provider-setup) for what to register on the IdP side.

6464

6565| Field | Required | Description |

6666| - | - | - |

67| `issuer` | Yes | OIDC discovery base. Must serve discovery at `/.well-known/openid-configuration`. Use HTTPS in production; the gateway accepts an `http://` issuer. A loopback issuer such as `http://localhost:8081` is rejected by the [SSRF guard](/docs/en/claude-apps-gateway-deploy#threat-model-summary) unless `CLAUDE_GATEWAY_ALLOW_LOOPBACK=1` is set in the gateway's environment. |

67| `issuer` | Yes | OIDC discovery base. Must serve discovery at `/.well-known/openid-configuration`. Use HTTPS in production; the gateway accepts an `http://` issuer. A loopback issuer such as `http://localhost:8081` is rejected by the [SSRF guard](/docs/en/claude-apps-gateway-deploy.md#threat-model-summary) unless `CLAUDE_GATEWAY_ALLOW_LOOPBACK=1` is set in the gateway's environment. |

6868| `client_id` | Yes | From your OAuth client registration |

6969| `client_secret` | Unless `token_endpoint_auth_method` is `private_key_jwt` | From your OAuth client registration. Leave it out when you use [certificate client authentication](#certificate-client-authentication). |

7070| `allowed_email_domains` | No | Reject id\_tokens whose `email` claim isn't in one of these domains, case-insensitive. Defense-in-depth against multi-tenant IdP misconfiguration. Independent of this setting, an id\_token whose `email_verified` claim is explicitly `false` is always rejected. |

from line 72

7272| `groups_claim` | No | Which id\_token claim carries group membership. Default `groups`. Microsoft Entra emits app roles under `roles`. Accepts a flat key or an RFC 6901 JSON Pointer such as `/resource_access/gateway/roles` for nested claims. |

7373| `google_groups` | No | Look up the signed-in user's groups through the Google Workspace Admin SDK Directory API, because Google's id\_token carries no groups claim. Set `service_account_json_path` to a service-account key file with domain-wide delegation on the `https://www.googleapis.com/auth/admin.directory.group.readonly` scope, and `admin_email` to a Workspace administrator the service account impersonates; the Directory API requires a real admin subject. Each user's group email addresses become their groups claim, so `allowed_groups` and `managed.policies.match.groups` match on group emails. |

7474| `email_claim` | No | Which id\_token claim carries the user's email. Default `email`. Some IdPs, such as ADFS and Entra B2C, emit `upn` or `preferred_username` instead. Accepts a flat key, a JSON Pointer, or a list of fallback keys where the first present key is used. |

75| `scopes` | No | Full override of the OIDC scopes the gateway requests. Default `[openid, profile, email, offline_access]`. Set when your IdP rejects scopes it doesn't recognize, or requires a custom scope to emit groups or email. Must include `openid`. Dropping `offline_access` disables refresh tokens, so developers re-run the browser login every `session.ttl_hours`. See [Identity provider setup](/docs/en/claude-apps-gateway-deploy#identity-provider-setup) for per-IdP scope recipes such as Google's refresh-token flow. |

75| `scopes` | No | Full override of the OIDC scopes the gateway requests. Default `[openid, profile, email, offline_access]`. Set when your IdP rejects scopes it doesn't recognize, or requires a custom scope to emit groups or email. Must include `openid`. Dropping `offline_access` disables refresh tokens, so developers re-run the browser login every `session.ttl_hours`. See [Identity provider setup](/docs/en/claude-apps-gateway-deploy.md#identity-provider-setup) for per-IdP scope recipes such as Google's refresh-token flow. |

7676| `scope_on_refresh` | No | Also send `scope`, with the same list as the sign-in request, when the gateway exchanges a refresh token. Default `false`: the refresh request omits `scope`. Most IdPs return an id\_token on every refresh and don't need this. Set `true` when your IdP returns an id\_token on refresh only if asked for `openid` again, which Okta documents for its refresh grant. Without an id\_token, every refresh depends on the IdP's userinfo endpoint accepting the refreshed access token. If you gate sign-in or match policies on groups and your IdP's refresh-time id\_token omits them, also set `userinfo_fallback: true` so the gateway fills them from the userinfo endpoint. An IdP that granted fewer scopes than requested can reject the refresh with `invalid_scope`, including for existing sessions if you add entries to `scopes` while this is on. Unset the key if refreshes start failing at `token_endpoint` after you set it. Requires Claude Code v2.1.260 or later on the gateway server. |

7777| `extra_auth_params` | No | Extra query parameters appended to the IdP authorization request, verbatim. This is the override mechanism for IdP-specific behavior, such as `access_type: offline` for Google refresh tokens, `domain_hint` for some Entra tenants, or `acr_values` for step-up flows. Cannot override the gateway-managed protocol params: `state`, `nonce`, `redirect_uri`, PKCE, `scope`, `response_type`, `response_mode`, and `client_id`. |

7878| `userinfo_fallback` | No | When the id\_token omits email or groups, fetch them from `/userinfo`. Needed for Keycloak lightweight access tokens, the Okta org server, and ADFS minimal tokens. The id\_token stays authoritative; userinfo only fills gaps. Default `false`. |

from line 138

138138The gateway reads the key and certificate once at boot, so a changed file takes effect only after a restart. Rotate in this order so that no token request presents a certificate the IdP doesn't have:

139139

1401401. Upload the new certificate to the IdP alongside the old one.

1412. Replace the key and certificate files that `gateway.yaml` loads, then restart the gateway. If you run several replicas, a [rolling restart](/docs/en/claude-apps-gateway-deploy#upgrades) works, because the IdP has both certificates until you remove the old one.

1412. Replace the key and certificate files that `gateway.yaml` loads, then restart the gateway. If you run several replicas, a [rolling restart](/docs/en/claude-apps-gateway-deploy.md#upgrades) works, because the IdP has both certificates until you remove the old one.

1421423. After every replica has restarted, remove the old certificate from the IdP.

143143

144144#### IdP requests through a forward proxy

from line 145

145145

146146The inference upstreams honor `HTTPS_PROXY` and `HTTP_PROXY` on every version. The gateway's own requests to the IdP, discovery, JWKS, token, and userinfo, go direct unless you set `oidc.use_proxy: true`, which requires v2.1.227 or later. When a proxy variable is set, `use_proxy` is unset, and the issuer isn't covered by `NO_PROXY`, the gateway keeps those requests direct and logs a notice at boot asking you to choose; `use_proxy: false` keeps them direct and silences the notice.

147147

148With `use_proxy: true`, the pod resolves each IdP endpoint's hostname itself and asks the proxy to `CONNECT` to the resolved IP address, so the proxy must accept `CONNECT` to the IP address of every host the discovery document names, not only the issuer. Use an `http://` proxy URL. `ca_cert_pem` and the [SSRF guard](/docs/en/claude-apps-gateway-deploy#threat-model-summary) apply on the proxied path as well.

148With `use_proxy: true`, the pod resolves each IdP endpoint's hostname itself and asks the proxy to `CONNECT` to the resolved IP address, so the proxy must accept `CONNECT` to the IP address of every host the discovery document names, not only the issuer. Use an `http://` proxy URL. `ca_cert_pem` and the [SSRF guard](/docs/en/claude-apps-gateway-deploy.md#threat-model-summary) apply on the proxied path as well.

149149

150150[Proxy-only egress](#proxy-only-egress) changes both of these: while it's active, IdP requests follow the proxy unless you set `use_proxy: false`, and the gateway hands the proxy each IdP hostname without resolving it first.

151151

from line 182

182182

183183> [!WARNING]

184184>

185> Turn this on only when the proxy's allowlist is at least as strict as the gateway's own check. The proxy must refuse cloud metadata endpoints such as `169.254.169.254` and `metadata.google.internal`, link-local addresses, and the proxy host's own loopback, and it must refuse them by the address a name resolves to, not only by name, because the gateway no longer catches a hostname that resolves to one of them. A proxy that connects anywhere it's asked removes the gateway's [SSRF guard](/docs/en/claude-apps-gateway-deploy#threat-model-summary) for these requests.

186186

187187### `session`

188188

from line 199

199199

200200| Field | Required | Description |

201201| - | - | - |

202| `postgres_url` | Yes | `postgres://` or `postgresql://` URL with one host, not a comma-separated list. The gateway runs its own schema migrations at boot and on upgrade, so the role needs rights to create and alter tables on the target schema. See [Upgrades](/docs/en/claude-apps-gateway-deploy#upgrades) and [Postgres](/docs/en/claude-apps-gateway-deploy#postgres). |

202| `postgres_url` | Yes | `postgres://` or `postgresql://` URL with one host, not a comma-separated list. The gateway runs its own schema migrations at boot and on upgrade, so the role needs rights to create and alter tables on the target schema. See [Upgrades](/docs/en/claude-apps-gateway-deploy.md#upgrades) and [Postgres](/docs/en/claude-apps-gateway-deploy.md#postgres). |

203203| `username` | No | Overrides the user in `postgres_url` |

204204| `password` | No | Database credential. Set it here rather than in `postgres_url` so the credential stays out of the URL. Accepts any characters and takes precedence over URL credentials. |

205| `max_connections` | No | Postgres connection-pool size per replica. Default `5`, which is conservative and friendly to shared databases. With [spend limits](#admin) enabled, the gateway makes a few database operations per inference request, so raise it for a dedicated database under load, within what [Size the connection pool](/docs/en/claude-apps-gateway-deploy#size-the-connection-pool) allows. |

206206| `connect_timeout_seconds` | No | Seconds the gateway waits when it opens a Postgres connection. A whole number from `1` to `60`, default `5`. Raise it if connection attempts time out when a new gateway instance starts. Requires Claude Code v2.1.274 or later on the gateway server. Earlier versions refuse to start when the key is set. |

207| `readiness_grace_seconds` | No | How many seconds `/readyz` keeps reporting ready after Postgres stops answering. A whole number from `0` to `3600`, default `0`. See [Outage behavior](/docs/en/claude-apps-gateway-deploy#outage-behavior) for how to pick a value. Requires Claude Code v2.1.282 or later on the gateway server. Earlier versions refuse to start when the key is set. |

207| `readiness_grace_seconds` | No | How many seconds `/readyz` keeps reporting ready after Postgres stops answering. A whole number from `0` to `3600`, default `0`. See [Outage behavior](/docs/en/claude-apps-gateway-deploy.md#outage-behavior) for how to pick a value. Requires Claude Code v2.1.282 or later on the gateway server. Earlier versions refuse to start when the key is set. |

208208

209209For local development, point `postgres_url` at a throwaway Postgres container, for example `docker run --rm -p 5432:5432 -e POSTGRES_HOST_AUTH_METHOD=trust postgres`.

210210

from line 231

231231

232232When the gateway returns an upstream's response, it keeps the upstream's status code. Whether it keeps the upstream's message depends on the provider. An Anthropic API upstream's error body reaches the developer unchanged.

233233

234The Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry upstreams can name your account IDs, role ARNs, and project IDs in their error text. The gateway records that full text in the [operational log](/docs/en/claude-apps-gateway-deploy#logs). What the developer sees from those upstreams depends on the rejection:

234The Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry upstreams can name your account IDs, role ARNs, and project IDs in their error text. The gateway records that full text in the [operational log](/docs/en/claude-apps-gateway-deploy.md#logs). What the developer sees from those upstreams depends on the rejection:

235235

236236* `400` or `413` in Anthropic's standard error envelope: the upstream's own message, such as `prompt is too long`. Claude Platform on AWS, Agent Platform, and Microsoft Foundry return this envelope for model API rejections.

237237* `400` or `413` in the provider's own shape: a `capability_rejected:` token. When the gateway can't classify the rejection, `upstream rejected the request` on a `400` or `request too large for this upstream` on a `413`.

238238* Any other status: generic per-status copy, such as `upstream rate limit exceeded` on a `429`.

239239

240For example, the gateway replaces Amazon Bedrock's `Input is too long for requested model.` with `capability_rejected: prompt_too_long`. Claude Code [compacts automatically](/docs/en/errors#prompt-is-too-long) on that token, as it does on `prompt is too long`.

240For example, the gateway replaces Amazon Bedrock's `Input is too long for requested model.` with `capability_rejected: prompt_too_long`. Claude Code [compacts automatically](/docs/en/errors.md#prompt-is-too-long) on that token, as it does on `prompt is too long`.

241241

242242Keeping a cloud upstream's `400` or `413` message, or replacing it with a `capability_rejected:` token, requires gateway v2.1.233 or later.

243243

from line 306

306306

307307> [!NOTE]

308308>

309> If you set `forward_user_identity` on an Amazon Bedrock upstream, the gateway exits at startup with `Unrecognized key(s) in object: 'forward_user_identity'`. If your proxy sits in front of Bedrock, list it as a `provider: anthropic` upstream instead. The gateway sends that upstream the Anthropic Messages format, so your proxy has to [translate requests for Bedrock](/docs/en/llm-gateway-protocol#format-mismatch-with-the-upstream). To name each developer to AWS instead, see [Per-developer AWS cost attribution](#per-developer-aws-cost-attribution).

309> If you set `forward_user_identity` on an Amazon Bedrock upstream, the gateway exits at startup with `Unrecognized key(s) in object: 'forward_user_identity'`. If your proxy sits in front of Bedrock, list it as a `provider: anthropic` upstream instead. The gateway sends that upstream the Anthropic Messages format, so your proxy has to [translate requests for Bedrock](/docs/en/llm-gateway-protocol.md#format-mismatch-with-the-upstream). To name each developer to AWS instead, see [Per-developer AWS cost attribution](#per-developer-aws-cost-attribution).

310310

311311#### Amazon Bedrock

312312

313For the client-side Amazon Bedrock deployment that the gateway replaces or fronts, see [Claude Code on Amazon Bedrock](/docs/en/amazon-bedrock). The gateway-side upstream:

313For the client-side Amazon Bedrock deployment that the gateway replaces or fronts, see [Claude Code on Amazon Bedrock](/docs/en/amazon-bedrock.md). The gateway-side upstream:

314314

315315```yaml theme={null}

316316upstreams:

from line 336

336336| Setup | How |

337337| - | - |

338338| IAM permissions | Grant the gateway's principal `bedrock:InvokeModel` and `bedrock:InvokeModelWithResponseStream` on both the inference-profile ARNs and the underlying foundation-model ARNs. For the built-in catalog in US regions: `arn:aws:bedrock:<region>:<account>:inference-profile/us.anthropic.*` and `arn:aws:bedrock:*::foundation-model/anthropic.*`. Also grant `bedrock:CountTokens` on the foundation-model ARNs. The gateway uses it, at no charge, to count the input tokens of a request the client abandoned, so [spend limits](#admin) stay accurate. Without it the gateway falls back to a one-token Bedrock request for that count. |

339| Model access | Amazon Bedrock enables model access by default in commercial regions. The remaining account-level gate is Anthropic's one-time use case form: if no one in your AWS account has submitted it, open the Amazon Bedrock console, select an Anthropic model from the Model catalog, and complete the form. See [Submit use case details](/docs/en/amazon-bedrock#1-submit-use-case-details) for the AWS Organizations form and the permissions the submitter needs. |

339| Model access | Amazon Bedrock enables model access by default in commercial regions. The remaining account-level gate is Anthropic's one-time use case form: if no one in your AWS account has submitted it, open the Amazon Bedrock console, select an Anthropic model from the Model catalog, and complete the form. See [Submit use case details](/docs/en/amazon-bedrock.md#1-submit-use-case-details) for the AWS Organizations form and the permissions the submitter needs. |

340340| EKS (IRSA) | Create an IAM role with the policy above and a trust policy for your cluster's OIDC provider scoped to the gateway's service account. Annotate the service account with `eks.amazonaws.com/role-arn: arn:aws:iam::<acct>:role/claude-gateway`. `auth: {}` picks it up. |

341341| ECS / EC2 | Attach the IAM role to the task definition or instance profile. `auth: {}` picks it up. |

342342| Anywhere else | Pass credentials via the `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, and `AWS_SESSION_TOKEN` env vars, or set them explicitly in `auth:` with `${VAR}` expansion |

from line 426

426426

427427By default the gateway signs every Bedrock request with one credential, so AWS sees all developers' requests under a single IAM principal. Add `session_name: email` to [`assume_role`](#bedrock-in-another-aws-account) and the gateway calls `sts:AssumeRole` once per developer per hour, with the session name set to that developer's email, and signs their requests with the returned credentials, so each developer's requests reach AWS under their own assumed-role session. The role can be in the gateway's own account.

428428

429Requires a gateway running Claude Code v2.1.281 or later. [Cost attribution on AWS](/docs/en/claude-apps-gateway-on-aws#cost-attribution) covers the IAM role and where AWS billing shows the sessions.

429Requires a gateway running Claude Code v2.1.281 or later. [Cost attribution on AWS](/docs/en/claude-apps-gateway-on-aws.md#cost-attribution) covers the IAM role and where AWS billing shows the sessions.

430430

431431```yaml theme={null}

432432upstreams:

from line 442

442442

443443An active developer costs one STS call per hour per gateway replica, and concurrent first requests share one call.

444444

445The gateway also makes one call of its own on this role: the token count for a request the client abandoned, so that [spend limits](/docs/en/claude-apps-gateway-spend-limits) stay accurate. That count and its [one-token fallback request](#amazon-bedrock) are signed by the shared `claude-apps-gateway` session, so AWS attributes the fallback to `claude-apps-gateway` rather than to the developer.

445The gateway also makes one call of its own on this role: the token count for a request the client abandoned, so that [spend limits](/docs/en/claude-apps-gateway-spend-limits.md) stay accurate. That count and its [one-token fallback request](#amazon-bedrock) are signed by the shared `claude-apps-gateway` session, so AWS attributes the fallback to `claude-apps-gateway` rather than to the developer.

446446

447447For strict per-developer attribution, set `assume_role` with `session_name` on every Bedrock upstream you list. An upstream without it signs the requests it serves with its own credentials.

448448

449449#### Amazon Bedrock Mantle endpoint

450450

451The `mantle` provider sends inference to Amazon Bedrock's [Mantle endpoint](/docs/en/amazon-bedrock#use-the-mantle-endpoint). It requires Claude Code v2.1.283 or later on the gateway server. Earlier gateway releases reject it at boot, so upgrade every replica before adding it.

451The `mantle` provider sends inference to Amazon Bedrock's [Mantle endpoint](/docs/en/amazon-bedrock.md#use-the-mantle-endpoint). It requires Claude Code v2.1.283 or later on the gateway server. Earlier gateway releases reject it at boot, so upgrade every replica before adding it.

452452

453453The example below puts Mantle first, with an Amazon Bedrock upstream behind it to serve every model the `models` field leaves out:

454454

from line 472

472472| `auth` | No | Takes the same keys as the [Amazon Bedrock](#amazon-bedrock) upstream's `auth` block, under the same rules. |

473473| `base_url` | No | Override the derived endpoint. Keep the `/anthropic` path at the end. |

474474

475Grant the upstream's AWS identity Mantle's own IAM actions for inference and token counting, which [Use the Mantle endpoint](/docs/en/amazon-bedrock#use-the-mantle-endpoint) lists.

475Grant the upstream's AWS identity Mantle's own IAM actions for inference and token counting, which [Use the Mantle endpoint](/docs/en/amazon-bedrock.md#use-the-mantle-endpoint) lists.

476476

477477For a Mantle model ID that the gateway doesn't know, add an entry to the top-level [`models:`](#models) block whose `upstream_model` maps this upstream's name to that ID. Then put that entry's `id` in this upstream's `models` field too.

478478

from line 481

481481* **`guardrail`**: the gateway applies no [Bedrock guardrail](#apply-an-amazon-bedrock-guardrail) to requests it sends to Mantle, so it refuses to start when a `mantle` upstream is listed while any `bedrock` upstream sets `guardrail`.

482482* **`assume_role`**: a `mantle` upstream takes no [`assume_role`](#bedrock-in-another-aws-account). Requests that Mantle serves are sent with the `mantle` upstream's own `auth` credentials, and aren't [attributed per developer](#per-developer-aws-cost-attribution).

483483

484For what Mantle's own error responses mean, see [Mantle endpoint errors](/docs/en/amazon-bedrock#mantle-endpoint-errors).

484For what Mantle's own error responses mean, see [Mantle endpoint errors](/docs/en/amazon-bedrock.md#mantle-endpoint-errors).

485485

486486#### Claude Platform on AWS

487487

488488Claude Platform on AWS serves the first-party Anthropic API on AWS infrastructure at `aws-external-anthropic.<region>.api.aws`. It uses first-party model IDs, honors `anthropic-beta` headers as sent, and serves `count_tokens`, so none of the Bedrock-specific translation applies. The `anthropicAws` provider requires Claude Code v2.1.198 or later; earlier gateway releases reject it at boot.

489489

490For the client-side deployment of the same platform, see [Claude Code on Claude Platform on AWS](/docs/en/claude-platform-on-aws). The gateway-side upstream:

490For the client-side deployment of the same platform, see [Claude Code on Claude Platform on AWS](/docs/en/claude-platform-on-aws.md). The gateway-side upstream:

491491

492492```yaml theme={null}

493493upstreams:

from line 520

520520

521521#### Google Cloud Agent Platform

522522

523For the equivalent client-side setup, see [Claude Code on Google Cloud](/docs/en/google-vertex-ai). The gateway-side upstream:

523For the equivalent client-side setup, see [Claude Code on Google Cloud](/docs/en/google-vertex-ai.md). The gateway-side upstream:

524524

525525```yaml theme={null}

526526upstreams:

from line 548

548548

549549#### Microsoft Foundry

550550

551For the client-side Microsoft Foundry deployment, see [Claude Code on Microsoft Foundry](/docs/en/microsoft-foundry). The gateway-side upstream:

551For the client-side Microsoft Foundry deployment, see [Claude Code on Microsoft Foundry](/docs/en/microsoft-foundry.md). The gateway-side upstream:

552552

553553```yaml theme={null}

554554upstreams:

from line 685

685685

686686### `admin`

687687

688Optional. Enables `/v1/organizations/spend_limits`, which mirrors Anthropic's public Admin API, and per-developer spend enforcement on `/v1/messages`. See [Spend limits](/docs/en/claude-apps-gateway-spend-limits) for how caps are set and enforced; this section covers the `gateway.yaml` keys that turn the feature on and tune it.

688Optional. Enables `/v1/organizations/spend_limits`, which mirrors Anthropic's public Admin API, and per-developer spend enforcement on `/v1/messages`. See [Spend limits](/docs/en/claude-apps-gateway-spend-limits.md) for how caps are set and enforced; this section covers the `gateway.yaml` keys that turn the feature on and tune it.

689689

690690```yaml theme={null}

691691admin:

from line 708

708708| `write_keys` | No | Array of `{id, key}`. An `x-api-key` matching one of these can list, set, and delete spend limits. Key values must be at least 32 characters; `id`s must be unique across `read_keys` and `write_keys`. |

709709| `read_keys` | No | Array of `{id, key}`. Read-only: every `GET` endpoint, including listing caps, fetching one by ID, and reading [`/effective`](/docs/en/claude-apps-gateway-spend-limits#%2Feffective) and [`/audit`](/docs/en/claude-apps-gateway-spend-limits#%2Faudit). |

710710| `admin_groups` | No | IdP group names. A gateway JWT whose `groups` claim includes one of these has full admin access, read and write, and audits as `oidc:<sub>`. Use this for human admins; use API keys for machines. An empty entry in this list stops the gateway at boot. See [Matcher values that stop the gateway at boot](#matcher-values-that-stop-the-gateway-at-boot). |

711| `blocked_message` | No | Appended verbatim to the `429 billing_error` a blocked developer sees. Write the whole instruction, such as a URL or a Slack channel. When unset, the gateway sends only the default message. See [How enforcement works](/docs/en/claude-apps-gateway-spend-limits#how-enforcement-works). |

712712| `audit_retention_days` | No | Default `365`. Older `admin_audit` rows are swept. |

713713| `spend_retention_months` | No | Default `13`. `spend` counter rows older than this are swept. The default keeps a full year plus the current partial month for year-over-year reporting. |

714714| `identity_retention_days` | No | Default `90`. Last-seen TTL for `principal_emails` rows, which hold each developer's email, display name, and groups (PII). Deliberately shorter than spend retention so a deprovisioned identity ages out while its anonymous spend counters remain. |

from line 748

748748

749749How the meter matches an override row:

750750

751* A row replaces list price for requests that `upstream`, an [`upstreams[].name`](#upstreams), serves for `model`. That includes the higher [fast mode](/docs/en/fast-mode#understand-the-cost-tradeoff) rate, so fast and standard requests meter at the same four rates.

751* A row replaces list price for requests that `upstream`, an [`upstreams[].name`](#upstreams), serves for `model`. That includes the higher [fast mode](/docs/en/fast-mode.md#understand-the-cost-tradeoff) rate, so fast and standard requests meter at the same four rates.

752752* A built-in ID such as `claude-sonnet-4-6`, matched like [`models[].id`](#models), covers every dated form, regional Amazon Bedrock form, or Google Cloud's Agent Platform form the meter prices as that model. Any other string, such as an alias or an inference-profile ARN, matches the ID the client sent or the string sent upstream, case-insensitively.

753753* Where rows overlap, the meter picks the most specific row rather than the first row: a row whose `model` is the exact model string sent upstream, then a row matching the exact ID the client sent, then a row naming the built-in model.

754754* An unknown upstream name fails boot, and so do two rows for one upstream that name the same model, including two spellings of one built-in model. The gateway warns at boot about a row no requestable model can use.

from line 846

846846>

847847> The gateway keeps no user directory of its own. It authorizes each request from the user's IdP token, reading group membership from the token's `groups` claim and evaluating policies against it. There is no roster to enumerate and no accounts to pre-create, and therefore no SCIM endpoint, because there is nothing for SCIM to sync into.

848848>

849> Run user and group lifecycle management at the source of truth, which is your IdP's native SCIM provisioning or a dedicated identity-governance platform. Membership and deprovisioning governed there flow into the gateway automatically through the token. If you want SCIM provisioning of Claude accounts themselves, that is a [Claude for Enterprise](/docs/en/admin-setup) capability.

850850>

851851> Two propagation clocks apply:

852852>

853> * **Policy contents**: editing a policy and redeploying reaches connected Claude Code clients on their next managed-settings poll, within an hour, apart from the [changes that apply only at the next launch](/docs/en/server-managed-settings#fetch-and-caching-behavior)

854854> * **Group membership**: changing a user's group membership changes which policy matches them. This takes effect on the next session re-mint, meaning the next silent refresh, bounded by `session.ttl_hours`.

855855>

856856> Claude Desktop follows [its own schedule](#when-a-policy-change-reaches-claude-desktop).

from line 925

925925

926926#### What goes in `cli`

927927

928Each `code` or `cli` value is a complete Claude Code `managed-settings.json` document, the same schema you would deploy via MDM or `/etc/claude-code/managed-settings.json`, expressed here as YAML. The CLI applies the delivered document at the managed tier, above user and project settings, in place of server-managed settings. It therefore ignores the settings [restricted to OS-level policy sources](/docs/en/server-managed-settings#current-limitations), such as `policyHelper` and `wslInheritsWindowsSettings`.

928Each `code` or `cli` value is a complete Claude Code `managed-settings.json` document, the same schema you would deploy via MDM or `/etc/claude-code/managed-settings.json`, expressed here as YAML. The CLI applies the delivered document at the managed tier, above user and project settings, in place of server-managed settings. It therefore ignores the settings [restricted to OS-level policy sources](/docs/en/server-managed-settings.md#current-limitations), such as `policyHelper` and `wslInheritsWindowsSettings`.

929929

930930The gateway validates each document against the CLI's settings schema at boot, so an unrecognized top-level key fails boot with an error naming every offending key. Deliberately open parts of the schema still accept arbitrary values, because newer clients may recognize entries the gateway's schema doesn't. These open keys include `env`, `pluginConfigs`, and keys nested under `permissions`.

931931

932932Because validation uses the schema bundled with the gateway's installed version, putting a top-level settings key introduced by a newer Claude Code release into managed config requires upgrading the gateway first. Smoke-test a new policy on one client before rolling it out.

933933

934The full key reference is in [Claude Code settings](/docs/en/settings-reference#all-settings). The keys most operators reach for first:

934The full key reference is in [Claude Code settings](/docs/en/settings-reference.md#all-settings). The keys most operators reach for first:

935935

936936```yaml theme={null}

937937managed:

from line 969

969969| Key | Enforced by | Effect |

970970| - | - | - |

971971| `availableModels` | Gateway + CLI | Model allowlist. Also checked at `/v1/messages`, so a patched client can't bypass it. |

972| [`deniedModels`](/docs/en/settings-reference#deniedmodels), [`availableModelsMatch`](/docs/en/settings-reference#availablemodelsmatch) | Gateway + CLI | [Block specific models or versions](/docs/en/model-config#block-specific-models-or-versions) that `availableModels` would otherwise permit. A blocked model is rejected with a `400` at `/v1/messages` and is left out of `/v1/models`. The gateway's own check requires Claude Code v2.1.299 or later on the gateway server. The CLI's check requires v2.1.283 or later on clients, and earlier clients ignore both keys. |

973| `permissions.allow` / `.deny` | CLI | Tool and command rules. See [Permissions](/docs/en/permissions). |

972| [`deniedModels`](/docs/en/settings-reference#deniedmodels), [`availableModelsMatch`](/docs/en/settings-reference#availablemodelsmatch) | Gateway + CLI | [Block specific models or versions](/docs/en/model-config.md#block-specific-models-or-versions) that `availableModels` would otherwise permit. A blocked model is rejected with a `400` at `/v1/messages` and is left out of `/v1/models`. The gateway's own check requires Claude Code v2.1.299 or later on the gateway server. The CLI's check requires v2.1.283 or later on clients, and earlier clients ignore both keys. |

973| `permissions.allow` / `.deny` | CLI | Tool and command rules. See [Permissions](/docs/en/permissions.md). |

974974| `permissions.disableBypassPermissionsMode` | CLI | Set to `disable` to block [`bypassPermissions`](/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode), the mode that skips permission prompts, and the `--dangerously-skip-permissions` flag |

975975| `allowManagedPermissionRulesOnly` | CLI | When `true`, managed settings become the only settings source of permission rules. The [`allowManagedPermissionRulesOnly`](/docs/en/settings-reference#allowmanagedpermissionrulesonly) entry lists every source Claude Code then ignores. |

976976| `env` | CLI | Environment variables merged into the CLI process. Use for telemetry, auto-update, and model-name overrides. |

977| `hooks` | CLI | Org-wide [hooks](/docs/en/hooks) |

978| `managedMcpServers` | CLI | Remote MCP servers [provided to every matching developer](/docs/en/managed-mcp#provide-servers-through-managed-settings) alongside the servers they add themselves, `http` and `sse` only. See [MCP servers in a policy](#mcp-servers-in-a-policy). Requires Claude Code v2.1.259 or later on the gateway server and on clients. Earlier clients ignore the key. |

977| `hooks` | CLI | Org-wide [hooks](/docs/en/hooks.md) |

978| `managedMcpServers` | CLI | Remote MCP servers [provided to every matching developer](/docs/en/managed-mcp.md#provide-servers-through-managed-settings) alongside the servers they add themselves, `http` and `sse` only. See [MCP servers in a policy](#mcp-servers-in-a-policy). Requires Claude Code v2.1.259 or later on the gateway server and on clients. Earlier clients ignore the key. |

979979

980980Because these settings arrive over the network, the CLI shows each developer a security approval dialog before applying the settings listed below:

981981

from line 983

983983* `env` variables that require the developer's approval, such as proxy and base-URL variables

984984* shell-execution settings such as `apiKeyHelper` and `statusLine`

985985* the sandbox binary settings `sandbox.bwrapPath`, `sandbox.socatPath`, and `sandbox.ripgrep`

986* Sandbox settings that intercept traffic, inject credentials, or weaken isolation, such as `sandbox.network.tlsTerminate` and the proxy port settings. [Security approval dialogs](/docs/en/server-managed-settings#security-approval-dialogs) lists them all.

987987

988[Approval memory](/docs/en/server-managed-settings#approval-memory) covers how long an approval lasts and when the dialog appears again.

988[Approval memory](/docs/en/server-managed-settings.md#approval-memory) covers how long an approval lasts and when the dialog appears again.

989989

990990Claude Code applies some delivered `env` variables without showing the developer the approval dialog, such as model selection settings and numeric limits. Other delivered variables can require the developer's approval before they take effect; a non-empty proxy, base-URL, or `OTEL_EXPORTER_OTLP_ENDPOINT` value always does. When a delivered variable needs approval, the dialog names it.

991991

992[Environment variables and the approval dialog](/docs/en/server-managed-settings#environment-variables-and-the-approval-dialog) has the details, including four privacy toggles whose delivered value decides whether they need approval. Before v2.1.218, Claude Code applied fewer variables without asking the developer, so more delivered variables triggered the dialog.

992[Environment variables and the approval dialog](/docs/en/server-managed-settings.md#environment-variables-and-the-approval-dialog) has the details, including four privacy toggles whose delivered value decides whether they need approval. Before v2.1.218, Claude Code applied fewer variables without asking the developer, so more delivered variables triggered the dialog.

993993

994994The gateway's [telemetry](#telemetry) configuration pushes `OTEL_EXPORTER_OTLP_ENDPOINT`, so setting `telemetry.forward_to` triggers the dialog on each interactive client. The dialog protects the developer's machine from a compromised or hostile gateway, not the organization from the developer.

995995

996A [non-interactive run](/docs/en/server-managed-settings#security-approval-dialogs), such as `claude -p`, an Agent SDK session, or a session in Claude Desktop's Code tab, can't show the dialog. It applies the pushed settings for that run only and doesn't record them as approved, so the developer's next interactive session still shows the dialog.

996A [non-interactive run](/docs/en/server-managed-settings.md#security-approval-dialogs), such as `claude -p`, an Agent SDK session, or a session in Claude Desktop's Code tab, can't show the dialog. It applies the pushed settings for that run only and doesn't record them as approved, so the developer's next interactive session still shows the dialog.

997997

998998If a developer declines, Claude Code exits that session rather than applying the policy. When you push a new hook, or any env var that triggers the dialog, to a broad policy, every matching developer therefore sees the dialog in their interactive sessions. A running interactive session shows it on the next hourly poll, and otherwise it appears at the developer's next interactive startup.

999999

from line 1003

10031003

10041004Terminal sessions signed in through `/login` use the 1M context window for Opus 4.7 and later, Sonnet 5 and later, and the Fable models. The model ID needs no `[1m]` suffix, and sessions compact at about 967K tokens. Before Claude Code v2.1.287 on the developer's machine, Claude Code treated the Opus and Fable models as having a 200K window unless the model ID ended in `[1m]`.

10051005

1006To have terminal sessions compact at the 200K boundary instead, set the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) in the policy's `env`:

1006To have terminal sessions compact at the 200K boundary instead, set the [auto-compact window](/docs/en/model-config.md#set-the-auto-compact-window) in the policy's `env`:

10071007

10081008```yaml theme={null}

10091009managed:

from line 1020

10201020

10211021#### One-hour prompt cache

10221022

1023To request the one-hour [prompt cache TTL](/docs/en/prompt-caching#cache-lifetime) instead of the default five minutes, add these keys to a policy's existing [`code`, `cli`, or `settings` block](#choose-cli-or-code) and restart the gateway. The keys need Claude Code v2.1.242 or later on the gateway server and on clients.

1023To request the one-hour [prompt cache TTL](/docs/en/prompt-caching.md#cache-lifetime) instead of the default five minutes, add these keys to a policy's existing [`code`, `cli`, or `settings` block](#choose-cli-or-code) and restart the gateway. The keys need Claude Code v2.1.242 or later on the gateway server and on clients.

10241024

10251025`promptCacheTtl` covers the main conversation. `subagentPromptCacheTtl` is optional and covers subagents, workflows, and background requests. This example adds both to a `match: {}` policy keyed `cli`:

10261026

from line 1037

10371037>

10381038> Set the keys only if your upstreams offer the one-hour TTL for every model the gateway serves. If an upstream rejects the TTL, the request fails, and neither the gateway nor Claude Code retries it with the five-minute TTL. For Amazon Bedrock, check [supported models, regions, and limits](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html#prompt-caching-models).

10391039

1040To confirm `promptCacheTtl`, sign in to the gateway as a user the policy matches and [check which TTL your cache writes used](/docs/en/prompt-caching#choose-the-ttl-yourself). Pass `--model` to repeat the check for each model the gateway serves.

1040To confirm `promptCacheTtl`, sign in to the gateway as a user the policy matches and [check which TTL your cache writes used](/docs/en/prompt-caching.md#choose-the-ttl-yourself). Pass `--model` to repeat the check for each model the gateway serves.

10411041

1042One-hour cache writes [cost more](/docs/en/prompt-caching#cache-lifetime) than five-minute writes. For [spend limits](/docs/en/claude-apps-gateway-spend-limits#how-requests-are-priced) to count that higher rate, you need v2.1.286 or later on the gateway server.

1042One-hour cache writes [cost more](/docs/en/prompt-caching.md#cache-lifetime) than five-minute writes. For [spend limits](/docs/en/claude-apps-gateway-spend-limits.md#how-requests-are-priced) to count that higher rate, you need v2.1.286 or later on the gateway server.

10431043

10441044#### MCP servers in a policy

10451045

10461046To provide MCP servers to the Claude Code clients a policy matches, set [`managedMcpServers`](/docs/en/managed-mcp#provide-servers-through-managed-settings) in that policy's `cli` block. You need Claude Code v2.1.259 or later on the gateway server and on clients.

10471047

1048The gateway checks each entry at boot with [the same rules Claude Code applies on the client](/docs/en/managed-mcp#what-an-entry-can-contain), and if an entry fails a check, the gateway refuses to start and names the entry.

1048The gateway checks each entry at boot with [the same rules Claude Code applies on the client](/docs/en/managed-mcp.md#what-an-entry-can-contain), and if an entry fails a check, the gateway refuses to start and names the entry.

10491049

1050If you write a `${VAR}` reference in `gateway.yaml`, the gateway resolves it from its environment at boot through [secret expansion](#secret-expansion) before it runs the entry checks, so every matching client receives the literal value and can read it. The [header guidance for provided servers](/docs/en/managed-mcp#provide-servers-through-managed-settings) applies to the expanded value.

1050If you write a `${VAR}` reference in `gateway.yaml`, the gateway resolves it from its environment at boot through [secret expansion](#secret-expansion) before it runs the entry checks, so every matching client receives the literal value and can read it. The [header guidance for provided servers](/docs/en/managed-mcp.md#provide-servers-through-managed-settings) applies to the expanded value.

10511051

10521052The gateway rejects the `.mcp.json` spelling `mcpServers` in a `cli` block, and its boot error names `managedMcpServers` as the key to use. Before v2.1.259, the gateway rejected any MCP server definition in a `cli` block.

10531053

10541054#### Claude Desktop overlay

10551055

1056If your organization also deploys [Claude Desktop](/docs/en/desktop), the same gateway serves both clients. Point `bootstrapUrl`, in Claude Desktop's [managed configuration](https://claude.com/docs/third-party/claude-desktop/configuration), at `<listen.public_url>/user/bootstrap`. Claude Desktop derives the OAuth issuer from that URL, runs the same device-code sign-in against this gateway, and fetches its configuration from the response.

1056If your organization also deploys [Claude Desktop](/docs/en/desktop.md), the same gateway serves both clients. Point `bootstrapUrl`, in Claude Desktop's [managed configuration](https://claude.com/docs/third-party/claude-desktop/configuration), at `<listen.public_url>/user/bootstrap`. Claude Desktop derives the OAuth issuer from that URL, runs the same device-code sign-in against this gateway, and fetches its configuration from the response.

10571057

10581058> [!NOTE]

10591059>

from line 1067

10671067

10681068* The model list, from `availableModels`. The list leaves out models that the policy blocks with [`deniedModels` or `availableModelsMatch: exact`](#what-goes-in-cli). This filter requires Claude Code v2.1.299 or later on the gateway server. [Extended context in Claude Desktop](#extended-context-in-claude-desktop) covers each model's 1M context option

10691069* Disabled tools, from bare tool-name `permissions.deny` entries. If you set `disabledBuiltinTools` in the policy's `desktop` block, the gateway serves the union of your value and the derived list, so you can disable more tools this way but can't re-enable one you disabled through `permissions.deny`

1070* The egress allowlist, from `sandbox.network.allowedDomains`. If you set `coworkEgressAllowedHosts` in the policy's `desktop` block, the gateway uses that value instead of the derived list. If the allowlist the gateway serves includes `*` and the gateway doesn't also serve Claude Desktop's [`allowedWorkspaceFolders`](https://claude.com/docs/third-party/claude-desktop/code#applied-as-managed-policy), Claude Desktop doesn't turn on the [Bash sandbox](/docs/en/sandboxing) in the Code tab

10711071* An OTLP endpoint that points at the gateway itself, and the signed-in user's identity attributes. The gateway relays the exports it receives at that endpoint to your `forward_to` destinations. It includes the endpoint and the attributes when you set both [`telemetry.forward_to`](#telemetry) and `listen.public_url`.

10721072

10731073 Claude Desktop exports every signal with one encoding: `http/protobuf`, or `http/json` when you set `OTEL_EXPORTER_OTLP_PROTOCOL` or one of its per-signal variants to `http/json` in the policy's `env`. Before Claude Code v2.1.261 on the gateway server, the response set `http/json` regardless, so a collector that accepts only protobuf rejected Claude Desktop's exports

from line 1159

11591159

11601160#### Extended context in Claude Desktop

11611161

1162If you serve [Claude Desktop](#claude-desktop-overlay) from the gateway, its model picker offers a 1M context option for each listed model that can run with a 1M context window. These include Claude Opus 4.6 and later, Claude Sonnet 4.6 and later, and the Fable models. The option is the model's `[1m]` variant, which [Extended context](/docs/en/model-config#extended-context) describes. You need Claude Code v2.1.284 or later on the gateway server.

1162If you serve [Claude Desktop](#claude-desktop-overlay) from the gateway, its model picker offers a 1M context option for each listed model that can run with a 1M context window. These include Claude Opus 4.6 and later, Claude Sonnet 4.6 and later, and the Fable models. The option is the model's `[1m]` variant, which [Extended context](/docs/en/model-config.md#extended-context) describes. You need Claude Code v2.1.284 or later on the gateway server.

11631163

11641164A [`models`](#models) entry gets no 1M option when:

11651165

from line 1193

11931193

11941194To remove the option from the picker, set `CLAUDE_CODE_DISABLE_1M_CONTEXT: "1"` in the `env` block under the policy's `cli` key. If you also listed an entry whose `id` ends in `[1m]`, the gateway still serves it, so delete that entry too.

11951195

1196The variable also reaches the terminal sessions of developers the policy matches. For what it changes there, see [Extended context](/docs/en/model-config#extended-context).

1196The variable also reaches the terminal sessions of developers the policy matches. For what it changes there, see [Extended context](/docs/en/model-config.md#extended-context).

11971197

11981198#### Precedence with other managed sources

11991199

1200If a device also has an MDM-delivered policy or a local `managed-settings.json`, gateway-delivered settings rank first. [Precedence within the managed tier](/docs/en/managed-settings#precedence-within-the-managed-tier) on the managed settings page says when the local sources apply, and has the [keys Claude Code reads from every admin source](/docs/en/managed-settings#keys-read-from-every-admin-source) regardless of which source it selected, such as the sandbox lock keys, `forceRemoteSettingsRefresh`, and the per-variable `env` merge. A [`policyHelper`](/docs/en/settings-reference#policyhelper) configured in an MDM profile or the managed settings file runs only when the gateway delivers no settings; the entry says what its output replaces.

1200If a device also has an MDM-delivered policy or a local `managed-settings.json`, gateway-delivered settings rank first. [Precedence within the managed tier](/docs/en/managed-settings.md#precedence-within-the-managed-tier) on the managed settings page says when the local sources apply, and has the [keys Claude Code reads from every admin source](/docs/en/managed-settings.md#keys-read-from-every-admin-source) regardless of which source it selected, such as the sandbox lock keys, `forceRemoteSettingsRefresh`, and the per-variable `env` merge. A [`policyHelper`](/docs/en/settings-reference#policyhelper) configured in an MDM profile or the managed settings file runs only when the gateway delivers no settings; the entry says what its output replaces.

12011201

1202Embedding hosts such as [Claude Desktop](/docs/en/desktop) can supply policy through the SDK `managedSettings` option. [Parent settings from embedding hosts](/docs/en/managed-settings#parent-settings-from-embedding-hosts) says when Claude Code applies it, and [Restrict parent settings](/docs/en/claude-apps-gateway#restrict-parent-settings) lists which allow-direction settings still apply without the `allowManaged*Only` locks.

1202Embedding hosts such as [Claude Desktop](/docs/en/desktop.md) can supply policy through the SDK `managedSettings` option. [Parent settings from embedding hosts](/docs/en/managed-settings.md#parent-settings-from-embedding-hosts) says when Claude Code applies it, and [Restrict parent settings](/docs/en/claude-apps-gateway#restrict-parent-settings) lists which allow-direction settings still apply without the `allowManaged*Only` locks.

12031203

12041204Gateway policies apply to every Claude Code invocation on the machine, including non-interactive `claude -p` runs and sessions spawned by the Agent SDK. If the gateway is unreachable at startup, signed-in sessions exit with an error rather than running without their policy.

12051205

12061206### `telemetry`

12071207

1208The CLI sends metrics, logs, and, when enabled, traces to the gateway, which relays them verbatim to each configured destination. The exports use OpenTelemetry Protocol (OTLP) over HTTP. To skip the relay and have sessions export straight to your collector, [name the collector in a policy](#export-directly-to-your-collector). See [Monitoring usage](/docs/en/monitoring-usage) for the metrics and events the CLI emits.

12091209

1210In sessions signed in through `/login`, the CLI stamps each export with the authenticated user's identity, read from the gateway-issued JWT: the `user.id`, `user.email`, and `user.groups` attributes. Per-developer cost and usage attribution therefore works with no developer-side configuration. Events that Claude Code logs before the developer signs in [don't carry this identity](/docs/en/monitoring-usage#standard-attributes). To see which attribute follows a change in a developer's groups, see [Group changes during an open session](#group-changes-during-an-open-session).

1210In sessions signed in through `/login`, the CLI stamps each export with the authenticated user's identity, read from the gateway-issued JWT: the `user.id`, `user.email`, and `user.groups` attributes. Per-developer cost and usage attribution therefore works with no developer-side configuration. Events that Claude Code logs before the developer signs in [don't carry this identity](/docs/en/monitoring-usage.md#standard-attributes). To see which attribute follows a change in a developer's groups, see [Group changes during an open session](#group-changes-during-an-open-session).

12111211

12121212[Claude Desktop](#claude-desktop-overlay) and Cowork sessions signed in through the gateway stamp their telemetry with `user.email` and `user.groups` alongside `enduser.id`, so you can cover terminal, Desktop, and Cowork usage with one query on `user.email` or `user.groups`. `user.groups` is the comma-separated IdP group list.

12131213

from line 1249

12491249

12501250Each `forward_to` URL must use `https://`, with one exception for a collector on the gateway's own loopback interface:

12511251

1252* `http://localhost:<port>` passes config validation, but the [SSRF guard](/docs/en/claude-apps-gateway-deploy#threat-model-summary) blocks every export with `ECONNREFUSED_SSRF` unless you set `CLAUDE_GATEWAY_ALLOW_LOOPBACK=1` in the gateway's environment

1252* `http://localhost:<port>` passes config validation, but the [SSRF guard](/docs/en/claude-apps-gateway-deploy.md#threat-model-summary) blocks every export with `ECONNREFUSED_SSRF` unless you set `CLAUDE_GATEWAY_ALLOW_LOOPBACK=1` in the gateway's environment

12531253* `http://127.0.0.1:<port>` or `http://[::1]:<port>` fails boot unless that variable is set

12541254

12551255For an in-cluster collector, expose it over HTTPS at its own internal address, or run it as a sidecar with the variable set.

from line 1280

12801280

12811281Without a `forward_to` destination for a signal, the gateway accepts and discards it. If developers already export Claude Code telemetry to one of your collectors, add it as a `forward_to` destination, with logs or traces enabled if they export those, so it keeps receiving their data after they sign in. To skip the relay instead, [name the collector in a policy](#export-directly-to-your-collector).

12821282

1283[Traces](/docs/en/monitoring-usage#traces-beta) also require `CLAUDE_CODE_ENHANCED_TELEMETRY_BETA=1` on each client. Set it in a managed policy's `env` block, since the gateway doesn't push it. Developers approve it in the same [security approval dialog](#managed) that the pushed endpoint already triggers.

1283[Traces](/docs/en/monitoring-usage.md#traces-beta) also require `CLAUDE_CODE_ENHANCED_TELEMETRY_BETA=1` on each client. Set it in a managed policy's `env` block, since the gateway doesn't push it. Developers approve it in the same [security approval dialog](#managed) that the pushed endpoint already triggers.

12841284

12851285Set it to `1` only in the policies whose groups you want traced. A policy that doesn't set it inherits the value from your `match: {}` catch-all policy if that policy sets one, per the [merge rules](#managed). To keep a group's clients from sending traces even when a developer sets the variable locally, set it to `0` in that group's policy.

12861286

from line 1291

12911291If your collector accepts only cumulative metrics, set [`OTEL_EXPORTER_OTLP_METRICS_TEMPORALITY_PREFERENCE`](/docs/en/monitoring-usage#common-configuration-variables) to `cumulative`. Claude Code sends delta metrics by default, and the gateway relays them without converting them. Set the variable where each kind of session reads it:

12921292

12931293* **Terminal sessions**: in the `env` block under a policy's [`cli` or `code` key](#choose-cli-or-code)

1294* **Cowork sessions that [run on the user's machine](/docs/en/managed-settings#where-and-when-a-policy-applies)**: in the `env` block of the [client-side managed settings](#client-side-managed-settings) on that machine

1294* **Cowork sessions that [run on the user's machine](/docs/en/managed-settings.md#where-and-when-a-policy-applies)**: in the `env` block of the [client-side managed settings](#client-side-managed-settings) on that machine

12951295* **Code tab sessions under a `code` policy**: in the policy's `env` block, once you meet the [conditions for `code` settings to apply](#apply-code-settings-in-the-code-tab)

12961296* **Code tab sessions under a `cli` policy**: in the `env` block of the client-side managed settings on the machine that runs the session. Over SSH, that's the remote host.

12971297

from line 1324

13241324

13251325Terminal sessions signed in through `/login` receive the labels as `OTEL_RESOURCE_ATTRIBUTES`, pushed with the other [telemetry variables](#telemetry). If you set `OTEL_RESOURCE_ATTRIBUTES` in a policy's `env` block, terminal sessions that policy matches get that value instead of the labels. Claude Desktop receives the labels from the gateway alongside `user.email` and the other identity attributes.

13261326

1327Claude Code also copies each label onto every metric data point, so you can filter metrics by it in a backend that doesn't index resource attributes. To turn that copy off, see [Metrics cardinality control](/docs/en/monitoring-usage#metrics-cardinality-control).

13281328

13291329#### Group changes during an open session

13301330

from line 1385

13851385| - | - | - | - |

13861386| `access_control` | `allow_cidrs` / `deny_cidrs` | empty | Inbound IP allow/deny by client address, after `trusted_proxies` resolution. `deny_cidrs` is checked first; a client it matches is rejected even if `allow_cidrs` also matches. If `allow_cidrs` is non-empty the gateway is default-deny. `/healthz` and `/readyz` are exempt from `allow_cidrs`. When a trusted proxy sends an `X-Forwarded-For` entry that isn't an IP address, the real client is unknown and the gateway logs a warning once naming what to check. Where either list applies to the request, it refuses it with `403` and audit reason `xff_unparseable`. Where neither does, it serves the request and uses the proxy's own address as the client IP for per-IP rate limits and audit. |

1388| `limits` | `max_request_header_bytes` | unset | Lowers the gateway's 256 KiB limit on a request's total headers. A request over the limit returns `431`, and a value above 256 KiB has no effect. If developers get `431` after signing in, see [Request headers too large after sign-in](/docs/en/claude-apps-gateway-deploy#request-headers-too-large-after-sign-in). |

13901390| `timeouts` | `upstream_ttfb_ms` | 120000 | Max wait for the upstream's response headers (time to first byte). The response body then streams with no wall-clock cap. Applies to the direct Anthropic upstream path; on every other provider the gateway waits up to one hour for the response to start. |

1391| `rate_limits` | `device_authorization.max` / `.window_seconds` | 30 / 600 | Per-IP rate limit on the unauthenticated device-authorization endpoint. Raise for a large org behind a shared egress IP or NAT. [Large rollouts](/docs/en/claude-apps-gateway-deploy#large-rollouts) shows how to size it. These limits apply only to the device-grant sign-in flow, not to `/v1/messages` inference. See [User-code brute-force resistance](/docs/en/claude-apps-gateway-deploy#user-code-brute-force-resistance). |

1392| `rate_limits` | `device_verify.max` / `.window_seconds` | 10 / 600 | Per-IP rate limit on `user_code` submissions at `/device`. It is what stops someone from guessing another developer's code. [Large rollouts](/docs/en/claude-apps-gateway-deploy#large-rollouts) shows how far to raise it. |

1391| `rate_limits` | `device_authorization.max` / `.window_seconds` | 30 / 600 | Per-IP rate limit on the unauthenticated device-authorization endpoint. Raise for a large org behind a shared egress IP or NAT. [Large rollouts](/docs/en/claude-apps-gateway-deploy.md#large-rollouts) shows how to size it. These limits apply only to the device-grant sign-in flow, not to `/v1/messages` inference. See [User-code brute-force resistance](/docs/en/claude-apps-gateway-deploy.md#user-code-brute-force-resistance). |

13931393

13941394If you leave both `access_control` lists empty, which is the default, the gateway serves any client address, so only your network restricts who can reach it. That matters because a gateway can push [managed settings](#managed) that run commands on developer machines.

13951395

from line 1433

14331433

14341434> [!WARNING]

14351435>

1436> Never turn this on for a gateway that developers use. Every request gets the canned reply and no model is called. The gateway logs a `load_test_mode is on` warning at boot and marks each `inference` [audit event](/docs/en/claude-apps-gateway-deploy#logs) with `load_test: true` while the mode is on.

1436> Never turn this on for a gateway that developers use. Every request gets the canned reply and no model is called. The gateway logs a `load_test_mode is on` warning at boot and marks each `inference` [audit event](/docs/en/claude-apps-gateway-deploy.md#logs) with `load_test: true` while the mode is on.

14371437

14381438## Complete example

14391439

from line 1598

15981598

15991599## Client-side managed settings

16001600

1601Everything above configures the gateway server. You point developer machines at the gateway separately, on each device, through Claude Code's [managed settings](/docs/en/managed-settings). The gateway can't push the login keys itself, because they're what tell the client where the gateway is.

1601Everything above configures the gateway server. You point developer machines at the gateway separately, on each device, through Claude Code's [managed settings](/docs/en/managed-settings.md). The gateway can't push the login keys itself, because they're what tell the client where the gateway is.

16021602

16031603For the CLI, set these keys in the per-OS `managed-settings.json`. The two login keys route each developer's `/login` to your gateway:

16041604

from line 1614

16141614

16151615To stop developers from bypassing the gateway with a cloud provider variable or an `ANTHROPIC_BASE_URL` of their own, add `"allowedProviders": ["gateway"]` to the same file. Claude Code then refuses every session on the machine that isn't set up for a Cloud gateway, and admits a gateway only when it is the one `forceLoginGatewayUrl` names or one whose URL the file's `env` block sets as `ANTHROPIC_BASE_URL`. `claude gateway` refuses to run on a machine that sets the list, so keep the key off the gateway host. See the [`allowedProviders`](/docs/en/settings-reference#allowedproviders) entry in the settings reference. Requires Claude Code v2.1.285 or later.

16161616

1617Deploy the `managed-settings.json` file to each device, typically via your MDM platform. The file path differs by platform. See [where each mechanism stores the policy](/docs/en/managed-settings#where-each-mechanism-stores-the-policy).

16181618

16191619By default, a registry policy on Windows or a managed-preferences plist on macOS replaces the `managed-settings.json` file rather than merging with it, apart from the [exception keys and cross-source checks above](#precedence-with-other-managed-sources). All three keys in this snippet follow the highest-priority-source rule, so fleets that deliver policy through Group Policy or configuration profiles must put all three in that mechanism instead.

16201620

from line 1622

16221622

16231623Claude Code honors [`forceLoginGatewayUrl`](/docs/en/settings-reference#forcelogingatewayurl), [`gatewayInternalNetworks`](/docs/en/settings-reference#gatewayinternalnetworks), and the `"gateway"` value of [`forceLoginMethod`](/docs/en/settings-reference#forceloginmethod) from a managed source on the machine: `managed-settings.json`, the macOS plist or Windows HKLM registry, or a policy helper. Setting them in the gateway payload doesn't configure the gateway sign-in. For a developer's own `~/.claude/settings.json`, see [Set the gateway URL in user settings](/docs/en/claude-apps-gateway#set-the-gateway-url-in-user-settings).

16241624

1625Leave `forceLoginMethod` and `forceLoginOrgUUID` out of the payload. Claude Code still reads both keys from the payload for its startup credential check, so a developer who keeps an Anthropic-issued credential on the machine gets the startup exit described under [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors#administrator-policy-requires-a-cloud-gateway-sign-in) even after they sign in.

1625Leave `forceLoginMethod` and `forceLoginOrgUUID` out of the payload. Claude Code still reads both keys from the payload for its startup credential check, so a developer who keeps an Anthropic-issued credential on the machine gets the startup exit described under [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors.md#administrator-policy-requires-a-cloud-gateway-sign-in) even after they sign in.

16261626

16271627## Related

16281628

16291629* [Claude apps gateway overview](/docs/en/claude-apps-gateway): quickstart and developer connection

1630* [Deployment guide](/docs/en/claude-apps-gateway-deploy): IdP setup, container image, Kubernetes and Cloud Run, and operations

1631* [Spend limits](/docs/en/claude-apps-gateway-spend-limits): per-developer caps and the Admin API

1630* [Deployment guide](/docs/en/claude-apps-gateway-deploy.md): IdP setup, container image, Kubernetes and Cloud Run, and operations

1631* [Spend limits](/docs/en/claude-apps-gateway-spend-limits.md): per-developer caps and the Admin API

16321632

claude-apps-gateway-deploy Changed · +38 / -38 lines

from line 10

1010>

1111> Choose the gateway's address before you choose where it runs. Usually that's a private address that users reach on your internal network or over a VPN. If your internal network uses public IPv4 ranges, you can list one range that holds both the gateway and your users' machines. Claude Code takes that match as a sign that the gateway is on your internal network. See [Choose an address for the gateway](#choose-an-address-for-the-gateway). If neither fits your network, contact your Anthropic account team.

1212

13This page covers the operational side of running [Claude apps gateway](/docs/en/claude-apps-gateway): registering an OAuth client in your identity provider (IdP), deploying the gateway as a container, and running it day-to-day. For every option in the `gateway.yaml` file the gateway reads at boot, see the [Configuration reference](/docs/en/claude-apps-gateway-config).

1414

1515A production deployment follows four steps in order, and the sections below match them. The first two are where you make choices; the second two are reference material to consult once it's running.

1616

from line 23

2323

2424## Identity provider setup

2525

26Register a confidential OAuth/OpenID Connect (OIDC) web application with a single redirect URI, `https://<gateway>/oauth/callback`, and assign it to the users or groups who should have gateway access. The gateway authenticates to the IdP with the registration's client secret, or with a certificate you upload to the registration if your IdP uses [certificate credentials](/docs/en/claude-apps-gateway-config#certificate-client-authentication) instead.

2727

2828Any OIDC-compliant IdP works: Okta, Microsoft Entra ID, Google Workspace, Keycloak, Dex, PingFederate, and others. The IdP must meet three requirements:

2929

from line 52

5252A few decisions shape the deployment beyond where it runs:

5353

5454* **Cost**: no separate license or per-seat fee. The gateway is part of the `claude` binary, so you pay for inference through your existing commitment, plus the compute it runs on.

55* **Bypass**: the gateway doesn't enforce that the only route to a model goes through it. A developer with their own credential can still call the provider directly, so closing that path is a network policy decision, for example blocking egress to `api.anthropic.com` except from the gateway. Blocking that egress also breaks the [WebFetch domain safety check](/docs/en/data-usage#webfetch-domain-safety-check), which calls `api.anthropic.com` from each developer's machine. Set `skipWebFetchPreflight: true` in the managed policy to disable it.

55* **Bypass**: the gateway doesn't enforce that the only route to a model goes through it. A developer with their own credential can still call the provider directly, so closing that path is a network policy decision, for example blocking egress to `api.anthropic.com` except from the gateway. Blocking that egress also breaks the [WebFetch domain safety check](/docs/en/data-usage.md#webfetch-domain-safety-check), which calls `api.anthropic.com` from each developer's machine. Set `skipWebFetchPreflight: true` in the managed policy to disable it.

5656* **Multiple gateways**: each is a separate deployment with its own config, and the CLI stores trust and credentials per gateway hostname, so teams can use different gateways without conflict. To serve multiple OIDC issuers, run separate instances.

5757* **Serverless**: Cloud Run works if you set `min-instances: 1` to avoid cold OIDC discovery. Lambda and Cloud Functions don't work, because the gateway is a long-running HTTP server.

5858

59Every production topology here puts an L7 proxy, such as an Ingress, Cloud Run's front end, or an ALB, in front of plain-HTTP replicas. Set [`listen.trusted_proxies`](/docs/en/claude-apps-gateway-config#listen) to the proxy's source ranges so the gateway reads client IPs from `X-Forwarded-For`. The gateway honors the header only when the TCP peer is trusted. The [Google Cloud](/docs/en/claude-apps-gateway-on-gcp) and [AWS](/docs/en/claude-apps-gateway-on-aws) worked examples have concrete values per topology. Without trusted proxies, every request appears to come from the proxy's IP, which collapses per-IP rate limits into one shared bucket and records the proxy's IP in audit events.

59Every production topology here puts an L7 proxy, such as an Ingress, Cloud Run's front end, or an ALB, in front of plain-HTTP replicas. Set [`listen.trusted_proxies`](/docs/en/claude-apps-gateway-config#listen) to the proxy's source ranges so the gateway reads client IPs from `X-Forwarded-For`. The gateway honors the header only when the TCP peer is trusted. The [Google Cloud](/docs/en/claude-apps-gateway-on-gcp.md) and [AWS](/docs/en/claude-apps-gateway-on-aws.md) worked examples have concrete values per topology. Without trusted proxies, every request appears to come from the proxy's IP, which collapses per-IP rate limits into one shared bucket and records the proxy's IP in audit events.

6060

6161Don't redirect requests to the gateway's device-authorization and token endpoints, for example with an HTTP-to-HTTPS or host-canonicalization rewrite at the ingress. Claude Code doesn't follow redirects on those requests, so an ingress rule that redirects them breaks sign-in and token refresh.

6262

from line 65

6565* On every upstream except `provider: anthropic`, the gateway writes an SSE `ping` once a stream has been silent for about 15 seconds.

6666* On `provider: anthropic`, the gateway passes the response through unchanged, including the Anthropic API's own pings.

6767

68A default such as the ALB's 60 seconds is enough to keep a quiet stream open. The [AWS worked example](/docs/en/claude-apps-gateway-on-aws#troubleshooting) raises it to an hour anyway, and its troubleshooting row covers gateways older than v2.1.229, which sent nothing during quiet periods on the upstreams that now get pings.

68A default such as the ALB's 60 seconds is enough to keep a quiet stream open. The [AWS worked example](/docs/en/claude-apps-gateway-on-aws.md#troubleshooting) raises it to an hour anyway, and its troubleshooting row covers gateways older than v2.1.229, which sent nothing during quiet periods on the upstreams that now get pings.

6969

7070### Choose an address for the gateway

7171

from line 80

8080

8181Build your own image around the native `claude` binary from the standard Claude Code release:

8282

831. Download the Linux build for your image architecture from a pinned release; see [Install a specific version](/docs/en/setup#install-a-specific-version) for the download URL.

842. Verify it against the release's GPG-signed `manifest.json` as described in [Binary integrity and code signing](/docs/en/setup#binary-integrity-and-code-signing).

831. Download the Linux build for your image architecture from a pinned release; see [Install a specific version](/docs/en/setup.md#install-a-specific-version) for the download URL.

842. Verify it against the release's GPG-signed `manifest.json` as described in [Binary integrity and code signing](/docs/en/setup.md#binary-integrity-and-code-signing).

85853. Copy it into the build context.

8686

8787Mirror the release into your internal registry if your builds can't reach the release host, and pin the version your fleet runs.

from line 88

8888

8989Beyond the binary, the image needs:

9090

91* **A glibc-based image**: the glibc build's only dynamic dependencies are glibc libraries. Musl-based images need the `linux-x64-musl` or `linux-arm64-musl` build plus additional packages; see [Alpine Linux setup](/docs/en/setup#alpine-linux-and-musl-based-distributions).

9292* **A writable state directory**: the gateway runs as any user, but minimal images have no writable home. Set `CLAUDE_CONFIG_DIR` to a writable path such as `/tmp/.claude`.

9393* **The container command**: `claude gateway --config /etc/claude/gateway.yaml`, with the config file mounted read-only and secrets supplied as environment variables; the gateway listens on `listen.port`, default `8080`.

9494

from line 100

100100* Terminate TLS at the Ingress and set `listen.public_url` to the Ingress hostname

101101* Point the readiness probe at `GET /readyz` and the liveness probe at `GET /healthz`

102102

103For a complete worked example on AWS, covering ECS Fargate or EKS, Amazon RDS, and AWS Secrets Manager, see [Deploy on AWS](/docs/en/claude-apps-gateway-on-aws).

103For a complete worked example on AWS, covering ECS Fargate or EKS, Amazon RDS, and AWS Secrets Manager, see [Deploy on AWS](/docs/en/claude-apps-gateway-on-aws.md).

104104

105105Prefer the platform's workload identity over static keys; the [`upstreams` reference](/docs/en/claude-apps-gateway-config#upstreams) has per-platform setup details. For a cross-cloud pairing, such as an Amazon Bedrock upstream on GKE, set explicit credentials in the upstream's `auth` block instead.

106106

from line 109

109109Configure the service as follows:

110110

111111* Leave `listen.port` at its default of `8080`, which matches Cloud Run's default `PORT`, or set `port: ${PORT}`

112* Set `public_url` to the externally reachable origin. For production this is normally an internal load balancer's hostname, because `/login` [rejects public addresses](/docs/en/claude-apps-gateway#prerequisites) and the `*.run.app` URL resolves to one, so the Cloud Run URL alone works only for a `curl` or browser smoke test. The exception is a network where `*.run.app` resolves privately through Private Service Connect and a Cloud DNS private zone; in that topology the Cloud Run URL is a valid `public_url`. The [Google Cloud worked example](/docs/en/claude-apps-gateway-on-gcp#deploy-the-gateway) covers both.

113113* Mount the config as a secret volume

114114* Set `min-instances: 1` to avoid a cold OIDC discovery on first request

115115

116For a complete worked example on Google Cloud, covering Cloud Run or GKE, Cloud SQL, and Secret Manager, see [Deploy on Google Cloud](/docs/en/claude-apps-gateway-on-gcp).

116For a complete worked example on Google Cloud, covering Cloud Run or GKE, Cloud SQL, and Secret Manager, see [Deploy on Google Cloud](/docs/en/claude-apps-gateway-on-gcp.md).

117117

118118### Push the gateway URL to developer machines

119119

120120Once the gateway is serving, push `forceLoginMethod`, `forceLoginGatewayUrl`, and `parentSettingsBehavior: "merge"` to each developer's machine through managed settings, via MDM or by writing the per-OS `managed-settings.json` directly.

121121

122Once you deploy the keys, Claude Code stops using a leftover API key or claude.ai login on the machine, so plan the push together with your sign-in instructions. [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors#administrator-policy-requires-a-cloud-gateway-sign-in) describes the messages developers see.

122Once you deploy the keys, Claude Code stops using a leftover API key or claude.ai login on the machine, so plan the push together with your sign-in instructions. [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors.md#administrator-policy-requires-a-cloud-gateway-sign-in) describes the messages developers see.

123123

124See [where each mechanism stores the policy](/docs/en/managed-settings#where-each-mechanism-stores-the-policy) for the file paths, and [Client-side managed settings](/docs/en/claude-apps-gateway-config#client-side-managed-settings) for the Claude Desktop `bootstrapUrl` equivalent.

124See [where each mechanism stores the policy](/docs/en/managed-settings.md#where-each-mechanism-stores-the-policy) for the file paths, and [Client-side managed settings](/docs/en/claude-apps-gateway-config.md#client-side-managed-settings) for the Claude Desktop `bootstrapUrl` equivalent.

125125

126126### Large rollouts

127127

from line 204

204204* **`provider: anthropic`**: set `API_TIMEOUT_MS` above the longest time your upstream takes to send its first event.

205205* **Every other upstream**: set it more than 20 seconds above the longest time your upstream takes to return response headers. The gateway sends its first [keepalive `ping`](#deployment) about 15 seconds after those headers, unless the upstream's first event comes sooner. A gateway older than v2.1.229 sends no pings, so use the `provider: anthropic` rule there.

206206

207On top of that time, allow for any [wait for a free slot](#concurrent-upstream-requests) and for the wait on a down upstream before [failover](/docs/en/claude-apps-gateway-config#multiple-upstreams). Keep the value above the longest [non-streaming request](/docs/en/network-config#streaming-idle-watchdogs) too.

207On top of that time, allow for any [wait for a free slot](#concurrent-upstream-requests) and for the wait on a down upstream before [failover](/docs/en/claude-apps-gateway-config.md#multiple-upstreams). Keep the value above the longest [non-streaming request](/docs/en/network-config.md#streaming-idle-watchdogs) too.

208208

209209### Outage behavior

210210

from line 212

212212

213213* **Existing sessions**: bearer tokens validate locally with the JWT secret, session refreshes don't touch the store, and the gateway process can still serve inference

214214* **New sign-ins**: fail until Postgres recovers, because the device flow and its rate-limit counters live in Postgres

215* **[Spend-limit enforcement](/docs/en/claude-apps-gateway-spend-limits#postgres-availability)**: fails open by default during the outage, so inference still flows; flip it to fail closed if you'd rather block than run unmetered

215* **[Spend-limit enforcement](/docs/en/claude-apps-gateway-spend-limits.md#postgres-availability)**: fails open by default during the outage, so inference still flows; flip it to fail closed if you'd rather block than run unmetered

216216* **Readiness**: by default `/readyz` reports not-ready as soon as Postgres is unreachable, so every replica fails its readiness check at once. Where traffic only reaches replicas that pass the check, all traffic, including inference the gateway could still serve, fails until Postgres recovers. The liveness probe on `/healthz` keeps passing throughout.

217217

218218If your IdP goes down, existing sessions work until `ttl_hours` and new logins fail. A session refresh gets a try-again answer and succeeds once the IdP is back. Set a longer `ttl_hours` if your IdP has frequent maintenance windows.

from line 252

252252| `admin_audit` | Admin API mutation trail | `admin.audit_retention_days`, default 365 |

253253| `principal_emails` | Each principal's last-seen email, display name, and IdP groups. Contains PII. | `admin.identity_retention_days` since last activity, default 90 |

254254

255A 30-second loop expires `kv` rows past their TTL, and an hourly sweep enforces the retention windows on the spend tables, so nothing grows without bound. Without [spend limits](/docs/en/claude-apps-gateway-spend-limits) configured, only `kv` is written. The gateway applies its own schema migrations at boot and on every upgrade, so its database role needs rights to create and alter tables. Point it at a database or schema dedicated to the gateway to keep that grant narrow.

255A 30-second loop expires `kv` rows past their TTL, and an hourly sweep enforces the retention windows on the spend tables, so nothing grows without bound. Without [spend limits](/docs/en/claude-apps-gateway-spend-limits.md) configured, only `kv` is written. The gateway applies its own schema migrations at boot and on every upgrade, so its database role needs rights to create and alter tables. Point it at a database or schema dedicated to the gateway to keep that grant narrow.

256256

257257With spend limits in use, a lost database means lost spend tracking and caps, not only developer re-logins, so run regular backups. To erase one departed developer immediately rather than waiting on retention, run `DELETE FROM principal_emails WHERE principal = '<sub>'` directly; that removes the only table holding their email, name, and groups. `spend` and `admin_audit` rows reference the pseudonymous OIDC `sub` only.

258258

from line 269

269269

270270* **The database**: raise its `max_connections`

271271* **The replicas**: run fewer, or have your orchestrator start fewer extra replicas in a rolling update

272* **The pool**: lower `store.max_connections`, but with [spend limits](/docs/en/claude-apps-gateway-spend-limits) on, keep it large enough for each replica's load. Otherwise spend checks can [time out](/docs/en/claude-apps-gateway-spend-limits#postgres-availability) waiting for a connection, and the gateway logs `spend check failed: spend precheck timed out`.

272* **The pool**: lower `store.max_connections`, but with [spend limits](/docs/en/claude-apps-gateway-spend-limits.md) on, keep it large enough for each replica's load. Otherwise spend checks can [time out](/docs/en/claude-apps-gateway-spend-limits.md#postgres-availability) waiting for a connection, and the gateway logs `spend check failed: spend precheck timed out`.

273273

274274### Upgrades

275275

from line 304

304304| Data | Path | Sent to Anthropic by the gateway |

305305| - | - | - |

306306| Inference (prompts, completions) | CLI → gateway → your upstream | Only if the Anthropic API is a configured upstream |

307| Telemetry (OTLP metrics, plus [opt-in logs and traces](/docs/en/claude-apps-gateway-config#telemetry)) | CLI → gateway → your collector | Never |

307| Telemetry (OTLP metrics, plus [opt-in logs and traces](/docs/en/claude-apps-gateway-config.md#telemetry)) | CLI → gateway → your collector | Never |

308308| Identity (email, groups, sub) | IdP → gateway → CLI; the CLI stamps it on OTLP exports. If you turn on [`forward_user_identity`](/docs/en/claude-apps-gateway-config#per-user-identity-headers-for-a-proxy-you-run), the gateway also sends the developer's email and IdP subject as headers to your proxy | Never |

309309| Managed settings | Your gateway YAML → CLI | Never |

310310| Audit log | Gateway stderr → your aggregator | Never |

from line 317

317317* The device-verification page enforces same-origin POST and a per-IP rate limit per RFC 8628 §5.1. See [User-code brute-force resistance](#user-code-brute-force-resistance).

318318* The gateway's requests to your IdP, your OTLP collectors, and `provider: anthropic` upstreams go through a server-side request forgery (SSRF) guard that resolves DNS, blocks link-local and cloud-metadata addresses plus loopback by default, and pins the connection to the resolved IP, so those operator-influenced URLs can't be redirected to cloud metadata endpoints. RFC 1918 private ranges are deliberately allowed, because IdPs and OTLP collectors commonly live on private IPs. For the other providers, the gateway refuses a `base_url` that names one of those addresses or a metadata hostname when it loads the config, and the provider's SDK then connects without the DNS check.

319319

320 If you turn on [proxy-only egress](/docs/en/claude-apps-gateway-config#proxy-only-egress), that address check moves to your forward proxy: the gateway hands it hostnames and the proxy's allowlist must refuse those destinations.

320 If you turn on [proxy-only egress](/docs/en/claude-apps-gateway-config.md#proxy-only-egress), that address check moves to your forward proxy: the gateway hands it hostnames and the proxy's allowlist must refuse those destinations.

321321

322322 Set `CLAUDE_GATEWAY_ALLOW_LOOPBACK=1` in the gateway's environment only when something the gateway must reach legitimately lives on loopback, such as a local-development IdP or a sidecar OTLP collector on `localhost`. The variable relaxes the loopback block for every operator-configured URL and also skips the boot-time warning that checks whether the pod can reach the cloud metadata endpoint, so prefer giving the collector its own internal address.

323323

from line 325

325325

326326Two threats are out of scope because they are your infrastructure to secure:

327327

328* **A compromised gateway host**: the host both holds the upstream credential and distributes [managed settings](/docs/en/claude-apps-gateway-config#managed) to every connected developer, so control over the gateway's configuration is comparable to control over your MDM. The CLI's [approval dialog](/docs/en/server-managed-settings#approval-memory) for shell-capable settings limits silent changes but doesn't replace host security.

328* **A compromised gateway host**: the host both holds the upstream credential and distributes [managed settings](/docs/en/claude-apps-gateway-config.md#managed) to every connected developer, so control over the gateway's configuration is comparable to control over your MDM. The CLI's [approval dialog](/docs/en/server-managed-settings.md#approval-memory) for shell-capable settings limits silent changes but doesn't replace host security.

329329* **A malicious OIDC provider**: the provider signs the id\_tokens the gateway trusts, so it can assert any identity. Vetting and securing your IdP is your responsibility.

330330

331331### User-code brute-force resistance

from line 338

338338

339339* **Data residency**: the gateway's own data plane sends nothing to Anthropic unless the Anthropic API is a configured upstream; when it is, your existing data-handling agreement applies to the inference path. Telemetry, audit, identity, and settings go only to the destinations you configure.

340340* **Host-process traffic**: the host process is the Claude Code CLI. `claude gateway` runs under the same third-party rules as Amazon Bedrock and Google Cloud's Agent Platform deployments and sends nothing to Anthropic. Before v2.1.227, the host process sent startup telemetry such as product version and platform, which setting `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` in the container environment turned off. Those releases also sent one `HEAD` request at boot, with no body or credentials, to `/api/hello` on `https://api.anthropic.com`, or on `ANTHROPIC_BASE_URL` when the environment set it, unless the environment also set a proxy variable such as `HTTPS_PROXY` or an mTLS client certificate. They ignored the response, so blocking that request at the egress firewall didn't affect the gateway.

341* **Client analytics**: the CLI disables its own usage analytics and error reporting while signed in to a gateway. Before the first sign-in, the CLI still sends startup events to Anthropic, including on machines whose managed settings force gateway sign-in. To keep those off too, deliver [`DISABLE_TELEMETRY`](/docs/en/managed-settings#turn-telemetry-off-for-your-organization) in the same [client-side managed settings](/docs/en/claude-apps-gateway-config#client-side-managed-settings) that force gateway sign-in.

341* **Client analytics**: the CLI disables its own usage analytics and error reporting while signed in to a gateway. Before the first sign-in, the CLI still sends startup events to Anthropic, including on machines whose managed settings force gateway sign-in. To keep those off too, deliver [`DISABLE_TELEMETRY`](/docs/en/managed-settings#turn-telemetry-off-for-your-organization) in the same [client-side managed settings](/docs/en/claude-apps-gateway-config.md#client-side-managed-settings) that force gateway sign-in.

342342* **Error reporting**: the CLI turns error reporting off whenever its model requests go to any endpoint other than Anthropic's first-party API, such as Amazon Bedrock or a custom `ANTHROPIC_BASE_URL`.

343* **Client machines**: developers' CLIs still send WebFetch hostname checks and version checks to Anthropic unless `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` and `skipWebFetchPreflight: true` are set. [Plugin marketplace requests](#plugin-marketplace-requests) have their own off switches. See [data usage](/docs/en/data-usage).

344344* **Survey ratings**: while signed in to a gateway, the CLI disables the Anthropic-bound rating upload together with the analytics streams, so it doesn't send ratings to Anthropic.

345345* **Transcript sharing**: choosing Yes on a survey's transcript-share prompt writes a local file under `~/.claude/feedback-bundles/` instead of uploading to Anthropic.

346346* **Client updates**: update checks are separate from gateway traffic. Pin versions through your own distribution and set `DISABLE_UPDATES` if laptops must not fetch releases. `DISABLE_AUTOUPDATER` stops only background updates while `claude update` still works.

347347* **TLS**: serve `public_url` over HTTPS in production, either from the gateway's own listener via `listen.tls` or from a TLS-terminating ingress in front of plain-HTTP replicas, with `listen.public_url` set in both cases. The gateway doesn't refuse plain HTTP. The IdP must serve HTTPS in production, and Postgres supports `?sslmode=require`. Set `Strict-Transport-Security` at your ingress.

348* **Vulnerability disclosure**: follow [Reporting security issues](/docs/en/security#reporting-security-issues)

348* **Vulnerability disclosure**: follow [Reporting security issues](/docs/en/security.md#reporting-security-issues)

349349

350350### Plugin marketplace requests

351351

352Claude Code fetches plugin marketplaces directly from each developer's machine, not through the gateway. [Network access requirements](/docs/en/network-config#network-access-requirements) lists the hosts.

352Claude Code fetches plugin marketplaces directly from each developer's machine, not through the gateway. [Network access requirements](/docs/en/network-config.md#network-access-requirements) lists the hosts.

353353

354The first time a developer starts an interactive terminal session, Claude Code registers the official marketplace, `claude-plugins-official`. It downloads the catalog from `downloads.claude.ai` and, if that fails, clones it from `github.com`. [Which marketplaces and plugins auto-update](/docs/en/plugins/loading#which-marketplaces-and-plugins-auto-update) covers later refreshes.

354The first time a developer starts an interactive terminal session, Claude Code registers the official marketplace, `claude-plugins-official`. It downloads the catalog from `downloads.claude.ai` and, if that fails, clones it from `github.com`. [Which marketplaces and plugins auto-update](/docs/en/plugins/loading.md#which-marketplaces-and-plugins-auto-update) covers later refreshes.

355355

356356`CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` doesn't stop the first registration. Either of these managed settings does:

357357

from line 358

358358* **A marketplace list**: a [`strictKnownMarketplaces`](/docs/en/plugins/org#allowlist-with-strictknownmarketplaces) allowlist that leaves the marketplace out, or a [`blockedMarketplaces`](/docs/en/plugins/org#blocklist-with-blockedmarketplaces) entry that names it

359359* **An environment variable**: `CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL` set to `"1"` in the managed [`env` block](/docs/en/plugins/org#turn-updates-off-for-the-whole-fleet)

360360

361The first registration can run before the developer signs in to the gateway, when no gateway policy has arrived. To cover that first start, deliver your choice in [client-side managed settings](/docs/en/claude-apps-gateway-config#client-side-managed-settings) as well as in the gateway policy's [`cli` or `code` block](/docs/en/claude-apps-gateway-config#what-goes-in-cli).

361The first registration can run before the developer signs in to the gateway, when no gateway policy has arrived. To cover that first start, deliver your choice in [client-side managed settings](/docs/en/claude-apps-gateway-config.md#client-side-managed-settings) as well as in the gateway policy's [`cli` or `code` block](/docs/en/claude-apps-gateway-config#what-goes-in-cli).

362362

363363## Troubleshooting

364364

from line 373

373373| Symptom | Cause | Fix |

374374| - | - | - |

375375| A developer's `/login` shows the standard account picker instead of the **Cloud gateway** screen | `forceLoginMethod` or `forceLoginGatewayUrl` isn't set in managed settings on that machine | Deploy the [managed settings file](/docs/en/claude-apps-gateway#set-the-gateway-url) to the device; `/login` reads the gateway URL from there |

376| A developer's requests fail with `Not signed in to the Cloud gateway — run /login.` | The machine's managed settings set `forceLoginMethod: "gateway"` or `forceLoginGatewayUrl`, and the session has no gateway sign-in. A leftover claude.ai login doesn't satisfy the requirement. | Have the developer run `/login` and complete the gateway sign-in. See also [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors#administrator-policy-requires-a-cloud-gateway-sign-in). |

377| Claude Desktop reports that its bootstrap configuration couldn't be fetched | `/user/bootstrap` returned 404: the policy matching the user doesn't carry a `desktop` key, or no policy matched. The gateway's audit log records each rejection as `desktop_bootstrap.denied` with the reason. | Add a `desktop` block to the policy that matches the user, or to the `match: {}` base layer; an empty `desktop: {}` suffices. See [Claude Desktop overlay](/docs/en/claude-apps-gateway-config#claude-desktop-overlay). |

376| A developer's requests fail with `Not signed in to the Cloud gateway — run /login.` | The machine's managed settings set `forceLoginMethod: "gateway"` or `forceLoginGatewayUrl`, and the session has no gateway sign-in. A leftover claude.ai login doesn't satisfy the requirement. | Have the developer run `/login` and complete the gateway sign-in. See also [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors.md#administrator-policy-requires-a-cloud-gateway-sign-in). |

378378| Startup shows `Gateway login is configured in managed settings, but this Claude Code build does not include Cloud gateway support.` | The installed Claude Code build predates gateway support | Have the developer update Claude Code to a release that includes Cloud gateway support |

379| Startup exits with `Administrator policy requires a Cloud gateway sign-in on this machine` | The developer's environment sets `ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN`, their settings configure an [`apiKeyHelper`](/docs/en/settings-reference#apikeyhelper), or an API key from an earlier Claude Console login is still saved | Have the developer clear each that applies: unset the variable, remove the `apiKeyHelper` entry, or run `claude auth logout` to remove the saved key. A session that selects a cloud provider with `CLAUDE_CODE_USE_*` then starts with no sign-in; for every other session, have them start `claude` and sign in with `/login`. See also [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors#administrator-policy-requires-a-cloud-gateway-sign-in). |

379| Startup exits with `Administrator policy requires a Cloud gateway sign-in on this machine` | The developer's environment sets `ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN`, their settings configure an [`apiKeyHelper`](/docs/en/settings-reference#apikeyhelper), or an API key from an earlier Claude Console login is still saved | Have the developer clear each that applies: unset the variable, remove the `apiKeyHelper` entry, or run `claude auth logout` to remove the saved key. A session that selects a cloud provider with `CLAUDE_CODE_USE_*` then starts with no sign-in; for every other session, have them start `claude` and sign in with `/login`. See also [Administrator policy requires a Cloud gateway sign-in](/docs/en/errors.md#administrator-policy-requires-a-cloud-gateway-sign-in). |

380380| Startup or `/login` reports `Claude Code may not be enabled for your organization` after a 403 on the managed settings load | The gateway, or something in front of it, answered the `/managed/settings` request with 403. The gateway's own settings route never answers 403. The status comes from the [`access_control`](/docs/en/claude-apps-gateway-config#http-tuning) IP checks or from a proxy or WAF in front of the gateway. The audit log records an IP-check denial as `access.denied` with the reason. The developer stays signed in. | Check the audit log for `access.denied` at the time of the failure and fix the `access_control` lists or the front end, then have the developer start `claude` again |

381381| CLI `/login`: `The gateway is limiting sign-in attempts right now`, or `Request failed with status code 429` on older versions. The `/device` page may show `Too many attempts` to developers who haven't tried before | The per-IP sign-in rate limit was reached. Either `listen.trusted_proxies` doesn't cover the load balancer, so every developer shares its address, or many developers share a NAT or VPN egress address. Audit events with `result: rate_limited` show the same one or few `client_ip` values. | Set `listen.trusted_proxies` to the load balancer's source ranges first, then raise `rate_limits` if developers still share addresses. See [Large rollouts](#large-rollouts). |

382382| CLI `/login`: `Gateway hosts must be on your organization's private network; <host> resolves to the public (or unrecognized) address <ip>` | The gateway hostname resolves to at least one public IP address. Claude Code checks each resolved address and requires every one to be private. A common cause is a dual-stack name where one family resolves to a public address, including AWS internal dual-stack load balancers, which return public-range AAAA addresses. | Have the gateway name resolve only to private addresses on developer machines. For a dual-stack name, drop the public-range record or serve a separate internal-only DNS name. See the [private-network prerequisite](/docs/en/claude-apps-gateway#prerequisites). If the address is public space your organization owns and uses internally, [declare that block](/docs/en/claude-apps-gateway#allow-a-gateway-on-public-address-space-you-own) instead. |

from line 389

389389| CLI `/login`: `Could not resolve gateway host <host>` | The machine can't resolve the gateway's internal DNS name, typically because it isn't on the corporate network | Have the developer connect to your network or VPN, then retry `/login` |

390390| Boot exits with a config validation error naming `store.postgres_url` | No Postgres configured; the gateway requires Postgres | Set `store.postgres_url`. For local development, use a throwaway container: `docker run --rm -p 5432:5432 -e POSTGRES_HOST_AUTH_METHOD=trust postgres`. |

391391| Boot exits: `store.postgres_url in <path> is not a URL the gateway can read`, or before v2.1.290 a bare `Invalid URL` or `URI error` | The URL can't be parsed, for example because it lists more than one host or its password has an unencoded `/`, `?`, `#`, or `%` | Name [one host](#postgres), and move the password into [`store.password`](/docs/en/claude-apps-gateway-config#store) |

392| Boot exits: `requires the native binary` | Running under Node instead of the native binary | Install Claude Code with one of the [standalone install methods](/docs/en/setup) |

393| Boot exits with an OIDC discovery error after `config.load` | `oidc.issuer` unreachable, or TLS chain not trusted | Check the issuer is reachable from the pod and serves `/.well-known/openid-configuration`. Set `ca_cert_pem` for private PKI. If the pod reaches the IdP only through a forward proxy, set [`oidc.use_proxy: true`](/docs/en/claude-apps-gateway-config#idp-requests-through-a-forward-proxy); on versions before v2.1.227, give the pod a direct route to each of the IdP's endpoints instead. If the pod also can't resolve the IdP's hostname, or the proxy refuses `CONNECT` to an IP address, see [Proxy-only egress](/docs/en/claude-apps-gateway-config#proxy-only-egress), which requires v2.1.277 or later. |

392| Boot exits: `requires the native binary` | Running under Node instead of the native binary | Install Claude Code with one of the [standalone install methods](/docs/en/setup.md) |

393| Boot exits with an OIDC discovery error after `config.load` | `oidc.issuer` unreachable, or TLS chain not trusted | Check the issuer is reachable from the pod and serves `/.well-known/openid-configuration`. Set `ca_cert_pem` for private PKI. If the pod reaches the IdP only through a forward proxy, set [`oidc.use_proxy: true`](/docs/en/claude-apps-gateway-config#idp-requests-through-a-forward-proxy); on versions before v2.1.227, give the pod a direct route to each of the IdP's endpoints instead. If the pod also can't resolve the IdP's hostname, or the proxy refuses `CONNECT` to an IP address, see [Proxy-only egress](/docs/en/claude-apps-gateway-config.md#proxy-only-egress), which requires v2.1.277 or later. |

394394| Boot exits with a Postgres permission error | The database role lacks DDL rights on its schema | Grant the role `CREATE` on the gateway's schema so it can create and alter its tables at boot |

395395| Log: `remaining connection slots are reserved` or `sorry, too many clients already`, from PostgreSQL. It shows in running replicas' `postgres connection closed` warnings, or in a new replica's boot log. There, `remaining connection slots are reserved` can follow `attempt 1 of 3`, and the replica may still start. | The replicas ask for more connections than the database has left for the gateway, and PostgreSQL refuses the extra ones | Make the total fit, as [Size the connection pool](#size-the-connection-pool) describes: run fewer replicas, lower `store.max_connections`, or raise the database's `max_connections`. If the total fits except during a rolling update, you can instead have your orchestrator stop an old replica before it starts a new one, if it supports that. |

396396| Log: `could not connect to Postgres at boot, attempt 1 of 3`, with a reason other than `remaining connection slots are reserved` | The database wasn't reachable yet when the gateway started, for example on a cold instance whose network is still coming up | If the gateway then finishes booting, no action is needed. When the database isn't reachable, the gateway tries the connection three times, two seconds apart, before it exits. If it exits with `could not connect to Postgres`, check `store.postgres_url`, including that it names one host, and the network path to the database. If the attempts time out rather than being refused, raise [`store.connect_timeout_seconds`](/docs/en/claude-apps-gateway-config#store) to give each one longer. |

from line 435

435435* **[`oidc.allowed_groups`](/docs/en/claude-apps-gateway-config#oidc)**: decides who can sign in

436436* **[`admin.admin_groups`](/docs/en/claude-apps-gateway-config#admin)**: decides who can call the admin API with their gateway session

437437* **`match.groups` in [`managed.policies`](/docs/en/claude-apps-gateway-config#managed)**: decides which policy applies to a developer

438* **`rbac_group` [spend caps](/docs/en/claude-apps-gateway-spend-limits)**: decide which group caps apply to a developer

438* **`rbac_group` [spend caps](/docs/en/claude-apps-gateway-spend-limits.md)**: decide which group caps apply to a developer

439439

440440### Long thinking ends in proxy timeouts

441441

from line 444

444444If turns fail after long thinking and your proxy logs one request open for about 12.5 minutes, then a run of `504` errors, raise [`CLAUDE_STREAM_IDLE_TIMEOUT_MS`](/docs/en/env-vars) in a gateway policy. For example, with a 240-second idle timeout on the proxy, the run is 10 requests, each cut at 240 seconds.

445445

446446* **The first request**: a stream that delivers its first response event, `message_start`, and then only pings while Claude thinks. With default settings, Claude Code ends that stream after about 12.5 minutes.

447* **The other 10**: the same request, sent [without streaming](/docs/en/errors#streaming-response-ended-before-any-complete-data-was-received) and then retried, 10 sends in all by default. They get no pings, so a slow reply hits the proxy's timeout.

447* **The other 10**: the same request, sent [without streaming](/docs/en/errors.md#streaming-response-ended-before-any-complete-data-was-received) and then retried, 10 sends in all by default. They get no pings, so a slow reply hits the proxy's timeout.

448448

449449You don't need a longer proxy timeout for this fix. If you raise only the proxy's timeout, requests without streaming still fail once a reply takes longer than Claude Code's own wait, 300 seconds by default.

450450

from line 468

468468| `900000` | About 22.5 minutes |

469469| `1800000` | About 37.5 minutes |

470470

471If an upstream hangs while the gateway keeps sending pings, your developers also wait that long before Claude Code gives up on the stream. A connection that goes fully silent still ends after 5 to 6 minutes, because the [body idle timeout](/docs/en/network-config#streaming-idle-watchdogs) doesn't follow this variable.

471If an upstream hangs while the gateway keeps sending pings, your developers also wait that long before Claude Code gives up on the stream. A connection that goes fully silent still ends after 5 to 6 minutes, because the [body idle timeout](/docs/en/network-config.md#streaming-idle-watchdogs) doesn't follow this variable.

472472

473473#### Deliver the value in a policy

474474

from line 492

492492If `provider: anthropic` is the model's only upstream and your proxy logs one request open for about 20 minutes, then `502` or `504` errors, raise [`CLAUDE_STREAM_IDLE_TIMEOUT_MS`](/docs/en/env-vars) in a gateway policy.

493493

494494* **The long request**: a stream that delivers `message_start` and then only pings while Claude thinks. Claude Code ends it after about 20 minutes with default settings, and later once you raise the variable.

495* **The errors**: requests that Claude Code then sends [without streaming](/docs/en/errors#streaming-response-ended-before-any-complete-data-was-received). Each one fails with a `502` from the gateway, or with your proxy's `504` if the proxy's timeout is shorter than the gateway's wait. That wait is [`timeouts.upstream_ttfb_ms`](/docs/en/claude-apps-gateway-config#http-tuning), which you don't need to raise for this fix.

495* **The errors**: requests that Claude Code then sends [without streaming](/docs/en/errors.md#streaming-response-ended-before-any-complete-data-was-received). Each one fails with a `502` from the gateway, or with your proxy's `504` if the proxy's timeout is shorter than the gateway's wait. That wait is [`timeouts.upstream_ttfb_ms`](/docs/en/claude-apps-gateway-config#http-tuning), which you don't need to raise for this fix.

496496

497497To confirm the cause, see [Confirm the cause](#confirm-the-cause).

498498

from line 501

501501## Related

502502

503503* [Claude apps gateway overview](/docs/en/claude-apps-gateway): quickstart and developer connection

504* [Configuration reference](/docs/en/claude-apps-gateway-config): every `gateway.yaml` option

504* [Configuration reference](/docs/en/claude-apps-gateway-config.md): every `gateway.yaml` option

505505

claude-apps-gateway-on-aws Changed · +30 / -28 lines

from line 4

55> [!NOTE]

66>

7> This page walks through one way to run Claude apps gateway on AWS. The configuration is a working example for customer-managed infrastructure rather than a supported production deployment; use it to see how the pieces fit together before adapting it to your own environment. For the platform-agnostic requirements, see the [deployment guide](/docs/en/claude-apps-gateway-deploy).

9This example provisions Claude apps gateway on AWS with Amazon Bedrock as the model upstream, using either [Amazon ECS](https://aws.amazon.com/ecs/) on [AWS Fargate](https://aws.amazon.com/fargate/) or [Amazon EKS](https://aws.amazon.com/eks/) for compute. [Okta](https://www.okta.com/) is the example identity provider (IdP), but any OpenID Connect (OIDC) compliant IdP works; see [Identity provider setup](/docs/en/claude-apps-gateway-deploy#identity-provider-setup) for per-IdP details.

1010

1111> [!NOTE]

1212>

13> Bedrock isn't the only Claude upstream on AWS. The gateway also supports Claude Platform on AWS, the Anthropic-operated Claude API with AWS authentication and AWS Marketplace billing, in place of Bedrock or alongside it. Its upstream entry, credentials, and IAM permissions differ from this page's Bedrock-scoped ones; the [Claude Platform on AWS upstream reference](/docs/en/claude-apps-gateway-config#claude-platform-on-aws) covers what changes, and the rest of this page applies unchanged.

13> Bedrock isn't the only Claude upstream on AWS. The gateway also supports Claude Platform on AWS, the Anthropic-operated Claude API with AWS authentication and AWS Marketplace billing, in place of Bedrock or alongside it. Its upstream entry, credentials, and IAM permissions differ from this page's Bedrock-scoped ones; the [Claude Platform on AWS upstream reference](/docs/en/claude-apps-gateway-config.md#claude-platform-on-aws) covers what changes, and the rest of this page applies unchanged.

1414

1515## Architecture

1616

1717![Diagram of Claude apps gateway on AWS: Claude Code clients connect over HTTPS to an internal Application Load Balancer fronting the gateway (ECS Fargate or EKS), which runs in private subnets alongside an Amazon RDS for PostgreSQL instance for session state. The gateway signs users in via OIDC against the corporate IdP, reads secrets from AWS Secrets Manager, forwards model requests to Amazon Bedrock using its IAM role, and pulls its image from Amazon ECR at deploy.](https://mintcdn.com/claude-code/PHweeRmDUYEKff49/images/claude-gateway-aws-architecture.svg?fit=max\&auto=format\&n=PHweeRmDUYEKff49\&q=85\&s=8599cc34aa28522cde208ee831439bb4)

1818

19The example architecture, with Amazon Bedrock as the model upstream. A Claude Platform on AWS upstream occupies the same position.

1921The gateway runs as a private HTTPS endpoint on your network that developers sign in to through your IdP. Their Claude Code sessions reach Claude models on Amazon Bedrock through the gateway's IAM role, so no model credentials land on developer machines. The reference configuration provisions:

2022

2123* **Amazon ECS on AWS Fargate** service or **Amazon EKS** Deployment running the gateway container

2224* **Amazon ECR** repository for the gateway image

23* **Amazon RDS for PostgreSQL** instance in private subnets, not publicly accessible, for the gateway's [store](/docs/en/claude-apps-gateway-config#store)

25* **Amazon RDS for PostgreSQL** instance in private subnets, not publicly accessible, for the gateway's [store](/docs/en/claude-apps-gateway-config.md#store)

2426* **AWS Secrets Manager** secrets for the JWT signing key, the OIDC client secret, and the Postgres URL

2527* **IAM role** with `bedrock:InvokeModel`, `bedrock:InvokeModelWithResponseStream`, and `bedrock:CountTokens`, attached as the ECS task role or bound via IAM Roles for Service Accounts (IRSA) on EKS

2628* **Internal Application Load Balancer** for HTTPS

from line 34

3234* An AWS account with permission to create the [resources above](#architecture)

3335* The [AWS CLI v2](https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html) installed and [authenticated](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-authentication.html), and [Docker](https://docs.docker.com/get-started/get-docker/) installed locally

3436* A [VPC](https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html) with at least two [private subnets](https://docs.aws.amazon.com/vpc/latest/userguide/configure-subnets.html) in different Availability Zones, with outbound internet access through a [NAT gateway](https://docs.aws.amazon.com/vpc/latest/userguide/vpc-nat-gateway.html); the internal load balancer needs subnets in two AZs, and the gateway needs egress to Bedrock and your IdP

35* An Okta OIDC web application with redirect URI `https://<gateway-host>/oauth/callback`; see [Identity provider setup](/docs/en/claude-apps-gateway-deploy#identity-provider-setup)

37* An Okta OIDC web application with redirect URI `https://<gateway-host>/oauth/callback`; see [Identity provider setup](/docs/en/claude-apps-gateway-deploy.md#identity-provider-setup)

3638* A TLS hostname for the gateway, typically an internal DNS name in a [Route 53 private hosted zone](https://docs.aws.amazon.com/Route53/latest/DeveloperGuide/hosted-zones-private.html) pointing at the load balancer, with an [ACM certificate](https://docs.aws.amazon.com/acm/latest/userguide/gs.html) for that name, imported or issued by [AWS Private CA](https://docs.aws.amazon.com/privateca/latest/userguide/PcaWelcome.html)

3739

3840### Set your environment variables

from line 91

8991

9092**2. Create the IAM roles and submit the use case form**

9193

92The gateway runs with a dedicated task role whose only permission is invoking Claude models on Bedrock. Per the [Bedrock upstream reference](/docs/en/claude-apps-gateway-config#amazon-bedrock), the policy must cover both the cross-region inference-profile ARNs and the underlying foundation-model ARNs:

94The gateway runs with a dedicated task role whose only permission is invoking Claude models on Bedrock. Per the [Bedrock upstream reference](/docs/en/claude-apps-gateway-config.md#amazon-bedrock), the policy must cover both the cross-region inference-profile ARNs and the underlying foundation-model ARNs:

9395

9496```bash theme={null}

9597cat > bedrock-invoke.json <<EOF

from line 151

149151

150152The policy names one ARN per secret rather than a bare `gateway-*` wildcard, which in a shared account would also match unrelated secrets; the trailing `-??????` matches exactly the random six-character suffix Secrets Manager appends to every secret's ARN. A trailing `-*` would be a plain prefix glob and would also match longer names such as `gateway-postgres-url-prod`.

151153

152The IAM policy grants the gateway permission to call Bedrock, and Bedrock enables model access by default in commercial regions. The remaining account-level gate is Anthropic's one-time use case form: if no one in your account has submitted it, open the [Amazon Bedrock console](https://console.aws.amazon.com/bedrock/), select an Anthropic model from the Model catalog, and complete the form. Access is granted immediately after submission; see [Claude Code on Amazon Bedrock](/docs/en/amazon-bedrock#1-submit-use-case-details) for the AWS Organizations form and the IAM permissions the submitter needs.

154The IAM policy grants the gateway permission to call Bedrock, and Bedrock enables model access by default in commercial regions. The remaining account-level gate is Anthropic's one-time use case form: if no one in your account has submitted it, open the [Amazon Bedrock console](https://console.aws.amazon.com/bedrock/), select an Anthropic model from the Model catalog, and complete the form. Access is granted immediately after submission; see [Claude Code on Amazon Bedrock](/docs/en/amazon-bedrock.md#1-submit-use-case-details) for the AWS Organizations form and the IAM permissions the submitter needs.

153155

154156The EKS track reuses both policy documents on an IRSA role instead of the two ECS roles; see the deploy step.

155157

from line 206

204206

205207**4. Write gateway.yaml**

206208

207The `upstreams` block points at Bedrock with `auth: {}`, so the gateway authenticates via the AWS default credential chain from the task role on ECS or the IRSA role on EKS. See the [configuration reference](/docs/en/claude-apps-gateway-config) for every field.

209The `upstreams` block points at Bedrock with `auth: {}`, so the gateway authenticates via the AWS default credential chain from the task role on ECS or the IRSA role on EKS. See the [configuration reference](/docs/en/claude-apps-gateway-config.md) for every field.

208210

209211Two `listen` fields describe what fronts the gateway:

210212

from line 256

254256

255257> [!NOTE]

256258>

257> Only the `oidc` block is Okta-specific. To use Microsoft Entra ID instead, set `issuer` to `https://login.microsoftonline.com/<tenant-id>/v2.0`, drop `userinfo_fallback` and the `groups` scope, and note that Entra emits group Object IDs rather than names, so [`managed.policies`](/docs/en/claude-apps-gateway-config#managed) must match on the GUIDs, or on App Roles with `oidc.groups_claim: roles`. See [Identity provider setup](/docs/en/claude-apps-gateway-deploy#identity-provider-setup).

259> Only the `oidc` block is Okta-specific. To use Microsoft Entra ID instead, set `issuer` to `https://login.microsoftonline.com/<tenant-id>/v2.0`, drop `userinfo_fallback` and the `groups` scope, and note that Entra emits group Object IDs rather than names, so [`managed.policies`](/docs/en/claude-apps-gateway-config#managed) must match on the GUIDs, or on App Roles with `oidc.groups_claim: roles`. See [Identity provider setup](/docs/en/claude-apps-gateway-deploy.md#identity-provider-setup).

258260

259261**5. Store secrets in AWS Secrets Manager**

260262

from line 284

282284

283285**6. Build and push the image to Amazon ECR**

284286

285Build the image per the [container image requirements](/docs/en/claude-apps-gateway-deploy#container-image), placing the `linux-x64` glibc binary at `./claude` in the build context. Write your own Dockerfile per those requirements or start from the bundle's [`Dockerfile`](https://github.com/anthropics/claude-code/blob/main/examples/gateway/aws/Dockerfile), which copies the filled-in `gateway.yaml` from the previous steps into the image at `/etc/claude/gateway.yaml`. On ECS that embedded copy is how the configuration reaches the container, which is why the build comes after the file is written. The EKS track instead mounts `gateway.yaml` from a ConfigMap at deploy, so the embedded copy is unused there.

287Build the image per the [container image requirements](/docs/en/claude-apps-gateway-deploy.md#container-image), placing the `linux-x64` glibc binary at `./claude` in the build context. Write your own Dockerfile per those requirements or start from the bundle's [`Dockerfile`](https://github.com/anthropics/claude-code/blob/main/examples/gateway/aws/Dockerfile), which copies the filled-in `gateway.yaml` from the previous steps into the image at `/etc/claude/gateway.yaml`. On ECS that embedded copy is how the configuration reaches the container, which is why the build comes after the file is written. The EKS track instead mounts `gateway.yaml` from a ConfigMap at deploy, so the embedded copy is unused there.

286288

287289The image also carries the AWS RDS certificate bundle as the trust anchor for the connection string's `sslmode=verify-full`, so download it into the build context first. AWS rotates the bundle (new regional CAs get appended), so download it per build rather than pinning a checksum or committing it:

288290

from line 415

413415

414416The 60-second grace period gives a cold task time to pull the image, connect to the store, and answer its first health check before ECS starts counting failures against the deployment.

415417

416The target group's health check on `GET /readyz` verifies the store is reachable, so a task that can't reach Postgres never enters rotation. To keep tasks passing the check through a short database outage such as an RDS failover, set `store.readiness_grace_seconds` as described in [Outage behavior](/docs/en/claude-apps-gateway-deploy#outage-behavior), which also covers the `/healthz` alternative.

418The target group's health check on `GET /readyz` verifies the store is reachable, so a task that can't reach Postgres never enters rotation. To keep tasks passing the check through a short database outage such as an RDS failover, set `store.readiness_grace_seconds` as described in [Outage behavior](/docs/en/claude-apps-gateway-deploy.md#outage-behavior), which also covers the `/healthz` alternative.

417419

418The tasks run in private subnets with no public IP, so all egress (to Bedrock, your IdP, Secrets Manager, ECR, and CloudWatch Logs) goes through the NAT gateway. To keep Bedrock traffic off the public path, create a `bedrock-runtime` interface VPC endpoint and point the upstream's `base_url` at it, as shown in the [Bedrock upstream reference](/docs/en/claude-apps-gateway-config#amazon-bedrock); the IdP still needs internet egress.

420The tasks run in private subnets with no public IP, so all egress (to Bedrock, your IdP, Secrets Manager, ECR, and CloudWatch Logs) goes through the NAT gateway. To keep Bedrock traffic off the public path, create a `bedrock-runtime` interface VPC endpoint and point the upstream's `base_url` at it, as shown in the [Bedrock upstream reference](/docs/en/claude-apps-gateway-config.md#amazon-bedrock); the IdP still needs internet egress.

419421

420422Finish by giving developers a privately resolvable hostname: in a Route 53 private hosted zone, alias the gateway's internal DNS name to the ALB, and set `listen.public_url` to that hostname. The ALB's own `*.elb.amazonaws.com` name resolves to private addresses on an internal ALB, but it can't carry your ACM certificate, so use your own name.

421423

from line 445

443445

444446The secrets policy is needed only when the pods read Secrets Manager themselves, as the Secrets Store CSI driver's AWS provider does using the mounting pod's service account; drop it if you create the Kubernetes Secrets another way. The provider needs both of the policy's actions: it calls `DescribeSecret` when it reconciles rotated secrets, so a `GetSecretValue`-only grant mounts on the first deploy but stops picking up rotations.

445447

446Deploy the gateway as a standard Deployment plus a Service and an Ingress, as described in [Kubernetes deployment](/docs/en/claude-apps-gateway-deploy#kubernetes), with:

448Deploy the gateway as a standard Deployment plus a Service and an Ingress, as described in [Kubernetes deployment](/docs/en/claude-apps-gateway-deploy.md#kubernetes), with:

447449

448450* `serviceAccountName: gateway`

449451* `gateway.yaml` mounted from a ConfigMap and the secrets mounted at `/secrets`

from line 479

477479

478480## Troubleshooting

479481

480For gateway boot and login errors, see the platform-agnostic [troubleshooting table](/docs/en/claude-apps-gateway-deploy#troubleshooting). The entries below are specific to AWS.

482For gateway boot and login errors, see the platform-agnostic [troubleshooting table](/docs/en/claude-apps-gateway-deploy.md#troubleshooting). The entries below are specific to AWS.

481483

482484| Symptom | Cause | Fix |

483485| - | - | - |

484486| CLI `/login`: `Gateway hosts must be on your organization's private network; <host> resolves to the public (or unrecognized) address <ip>` | The gateway name resolves to at least one public address. A dual-stack internal ALB publishes public-range AAAA records, and the [private-network check](/docs/en/claude-apps-gateway#prerequisites) requires every resolved address to be private | Create the ALB with `--ip-address-type ipv4`, or serve a separate internal-only DNS name with no public AAAA record |

485| Every Bedrock request returns 502; log shows `Could not load credentials from any providers` | The task runs on the ECS EC2 launch type without a task role, or the pod runs on an EKS node without IRSA, so credentials come from instance metadata, which IMDSv2's default hop limit of 1 stops inside a container. Neither track on this page is affected: Fargate task roles and IRSA don't use instance metadata | Prefer task roles and IRSA. Where instance credentials are unavoidable, raise the hop limit with `aws ec2 modify-instance-metadata-options --instance-id <id> --http-put-response-hop-limit 2`; the [platform-agnostic table](/docs/en/claude-apps-gateway-deploy#troubleshooting) covers the tradeoffs |

487| Every Bedrock request returns 502; log shows `Could not load credentials from any providers` | The task runs on the ECS EC2 launch type without a task role, or the pod runs on an EKS node without IRSA, so credentials come from instance metadata, which IMDSv2's default hop limit of 1 stops inside a container. Neither track on this page is affected: Fargate task roles and IRSA don't use instance metadata | Prefer task roles and IRSA. Where instance credentials are unavoidable, raise the hop limit with `aws ec2 modify-instance-metadata-options --instance-id <id> --http-put-response-hop-limit 2`; the [platform-agnostic table](/docs/en/claude-apps-gateway-deploy.md#troubleshooting) covers the tradeoffs |

486488| Bedrock requests return `403 AccessDeniedException` | The account hasn't submitted Anthropic's one-time use case form, the automatic AWS Marketplace subscription that starts on the account's first invoke hasn't finished yet, or the task role's policy is missing the inference-profile or foundation-model ARNs | Submit the use case form from the Bedrock console's Model catalog; if it was just submitted or this is the account's first invoke, retry after a few minutes. Grant `bedrock:InvokeModel` and `bedrock:InvokeModelWithResponseStream` on both ARN families. |

487489| Bedrock returns a `ValidationException` saying on-demand throughput isn't supported | A custom `models:` entry maps to a bare foundation-model ID that the region serves only through inference profiles | Map the model to its cross-region inference profile ID (`us.anthropic.*`) instead; the built-in catalog already does this |

488490| ECS task stops with `ResourceInitializationError` before the gateway logs anything | The execution role can't read the Secrets Manager secrets, or the private subnets have no path to Secrets Manager or ECR | Grant `secretsmanager:GetSecretValue` on the three `gateway-` secrets' ARNs to the execution role, and provide egress via the NAT gateway, or, without one, interface endpoints for Secrets Manager, ECR, and CloudWatch Logs, which the `awslogs` driver needs at the same stage, plus an S3 gateway endpoint |

from line 494

492494

493495## Telemetry

494496

495The gateway gives you per-developer usage metrics without any per-machine OTEL configuration. Claude Code emits OpenTelemetry (OTLP) metrics, logs, and opt-in traces; [Monitoring usage](/docs/en/monitoring-usage) covers everything the CLI reports. In sessions signed in through `/login`, the CLI [stamps each export](/docs/en/monitoring-usage#standard-attributes) with the authenticated IdP identity attributes `user.id`, `user.email`, and `user.groups`, so usage rolls up per developer.

497The gateway gives you per-developer usage metrics without any per-machine OTEL configuration. Claude Code emits OpenTelemetry (OTLP) metrics, logs, and opt-in traces; [Monitoring usage](/docs/en/monitoring-usage.md) covers everything the CLI reports. In sessions signed in through `/login`, the CLI [stamps each export](/docs/en/monitoring-usage.md#standard-attributes) with the authenticated IdP identity attributes `user.id`, `user.email`, and `user.groups`, so usage rolls up per developer.

496498

497499The gateway itself is an authenticated OTLP relay. Set [`telemetry.forward_to`](/docs/en/claude-apps-gateway-config#telemetry) together with `listen.public_url`, and it pushes the OTEL exporter settings to every connected client and forwards their OTLP traffic verbatim to each destination you list. Each destination opts into metrics, logs, and traces independently, and the default is metrics only; see the [`telemetry` reference](/docs/en/claude-apps-gateway-config#telemetry) for the per-signal fields and their sensitivity tradeoffs. The gateway doesn't buffer, aggregate, or store telemetry, so where the data lands is entirely the collector's exporter configuration.

498500

499Client telemetry is off by default; configuring `telemetry.forward_to` is what turns it on for connected developers, and each interactive client shows a security approval dialog for the pushed settings, as described in the [configuration reference](/docs/en/claude-apps-gateway-config#telemetry). On AWS, each signal maps to a destination as follows.

501Client telemetry is off by default; configuring `telemetry.forward_to` is what turns it on for connected developers, and each interactive client shows a security approval dialog for the pushed settings, as described in the [configuration reference](/docs/en/claude-apps-gateway-config.md#telemetry). On AWS, each signal maps to a destination as follows.

500502

501503### Client metrics, logs, and traces

502504

from line 516

514516

515517### Spend

516518

517Telemetry shows usage after the fact; [spend limits](/docs/en/claude-apps-gateway-spend-limits) are the gateway's live per-developer view and enforcement.

519Telemetry shows usage after the fact; [spend limits](/docs/en/claude-apps-gateway-spend-limits.md) are the gateway's live per-developer view and enforcement.

518520

519521## Cost attribution

520522

from line 524

522524

523525### Per developer with `assume_role`

524526

525Create a second IAM role that holds the Bedrock permissions and trusts the gateway's principal, grant that principal `sts:AssumeRole` on it, and set [`assume_role`](/docs/en/claude-apps-gateway-config#per-developer-aws-cost-attribution) with `session_name: email` on the Bedrock upstream. The gateway then assumes that role once per developer per hour with the session name set to their email and signs their requests with the result. Requires a gateway running Claude Code v2.1.281 or later. The role can also be in another AWS account: see [Bedrock in another AWS account](/docs/en/claude-apps-gateway-config#bedrock-in-another-aws-account). In Terraform, next to the task role in the [Terraform bundle](#terraform-reference):

527Create a second IAM role that holds the Bedrock permissions and trusts the gateway's principal, grant that principal `sts:AssumeRole` on it, and set [`assume_role`](/docs/en/claude-apps-gateway-config#per-developer-aws-cost-attribution) with `session_name: email` on the Bedrock upstream. The gateway then assumes that role once per developer per hour with the session name set to their email and signs their requests with the result. Requires a gateway running Claude Code v2.1.281 or later. The role can also be in another AWS account: see [Bedrock in another AWS account](/docs/en/claude-apps-gateway-config.md#bedrock-in-another-aws-account). In Terraform, next to the task role in the [Terraform bundle](#terraform-reference):

526528

527529```hcl theme={null}

528530resource "aws_iam_role" "bedrock_user" {

from line 585

583585* The config grows with teams times models

584586* The role that signs this upstream's Bedrock requests must also be allowed to invoke the `application-inference-profile/*` ARNs. That role is the gateway's principal, or with `assume_role` the role it assumes.

585587

586See [How requests are priced](/docs/en/claude-apps-gateway-spend-limits#how-requests-are-priced) for how the gateway's own spend meter prices these ids.

588See [How requests are priced](/docs/en/claude-apps-gateway-spend-limits.md#how-requests-are-priced) for how the gateway's own spend meter prices these ids.

587589

588590#### Let a developer choose which team to bill

589591

from line 593

591593

592594**1. Add a group for the pair**

593595

594In your IdP, add the developer to a new group, such as `team-platform-and-data`. If they're already signed in, have them run `/login` again, or wait for the next [silent refresh](/docs/en/claude-apps-gateway-config#managed), so the gateway sees the new group.

596In your IdP, add the developer to a new group, such as `team-platform-and-data`. If they're already signed in, have them run `/login` again, or wait for the next [silent refresh](/docs/en/claude-apps-gateway-config.md#managed), so the gateway sees the new group.

595597

596598**2. List its policy first**

597599

from line 616

614616

615617Have the developer pass the id of the team the work is for, such as `claude --model data-claude-opus-4-8`.

616618

617The gateway applies the [first policy that matches](/docs/en/claude-apps-gateway-config#managed), so a developer in only the two team groups gets the `team-platform` policy. Their sessions on the data team's id fail with `is not in your role's availableModels allowlist`, naming Claude Code's default model and not the id they typed. If you list both team groups in one policy's `groups` instead, everyone in either team can bill either team's profile.

619The gateway applies the [first policy that matches](/docs/en/claude-apps-gateway-config.md#managed), so a developer in only the two team groups gets the `team-platform` policy. Their sessions on the data team's id fail with `is not in your role's availableModels allowlist`, naming Claude Code's default model and not the id they typed. If you list both team groups in one policy's `groups` instead, everyone in either team can bill either team's profile.

618620

619In the gateway's own [spend limits](/docs/en/claude-apps-gateway-spend-limits#set-a-cap), the developer has one total and one cap per period, by default the lowest of their groups' caps, whichever id a session uses. To keep one team's lower cap from stopping work for the other, set a per-user cap for the developer.

621In the gateway's own [spend limits](/docs/en/claude-apps-gateway-spend-limits.md#set-a-cap), the developer has one total and one cap per period, by default the lowest of their groups' caps, whichever id a session uses. To keep one team's lower cap from stopping work for the other, set a per-user cap for the developer.

620622

621623## Next steps

622624

623* [Configuration reference](/docs/en/claude-apps-gateway-config): every `gateway.yaml` option, including `managed.policies` and `telemetry`

624* [Deployment and operations](/docs/en/claude-apps-gateway-deploy): IdP setup, health checks, JWT secret rotation, upgrades, and the security model

625* [Configuration reference](/docs/en/claude-apps-gateway-config.md): every `gateway.yaml` option, including `managed.policies` and `telemetry`

626* [Deployment and operations](/docs/en/claude-apps-gateway-deploy.md): IdP setup, health checks, JWT secret rotation, upgrades, and the security model

625627* [Claude apps gateway overview](/docs/en/claude-apps-gateway): quickstart and connecting developers

626628* [AWS samples for Claude apps gateway](https://github.com/aws-samples/anthropic-on-aws/tree/main/claude-apps-gateway): AWS-maintained deployment samples covering a range of customer environments

627629

claude-apps-gateway-on-gcp Changed · +13 / -13 lines

from line 4

55> [!NOTE]

66>

7> This page walks through one way to run Claude apps gateway on Google Cloud. The configuration is a working example for customer-managed infrastructure rather than a supported production deployment; use it to see how the pieces fit together before adapting it to your own environment. For the platform-agnostic requirements, see the [deployment guide](/docs/en/claude-apps-gateway-deploy).

9This example provisions Claude apps gateway on Google Cloud with Google Cloud's Agent Platform as the model upstream, using either Cloud Run or GKE for compute. Google Workspace is the example identity provider (IdP), but any OpenID Connect (OIDC) compliant IdP works; only the `oidc` block changes. See [Identity provider setup](/docs/en/claude-apps-gateway-deploy#identity-provider-setup) for per-IdP details.

1010

1111## What you'll build

1212

from line 16

1616

1717* **Cloud Run** service or **GKE** Deployment running the gateway container

1818* **Artifact Registry** repository for the gateway image

19* **Cloud SQL for PostgreSQL** instance, private IP only, for the gateway's [store](/docs/en/claude-apps-gateway-config#store)

19* **Cloud SQL for PostgreSQL** instance, private IP only, for the gateway's [store](/docs/en/claude-apps-gateway-config.md#store)

2020* **Secret Manager** secrets for `gateway.yaml`, the JWT signing key, the OIDC client secret, and the Postgres URL

2121* **Service account** with `roles/aiplatform.user`, attached directly on Cloud Run or bound via Workload Identity on GKE

2222* **HTTPS front end** that you provide: an internal Application Load Balancer in front of Cloud Run, which this walkthrough configures the gateway for but doesn't create, or an internal **GKE Ingress** of class `gce-internal` on GKE

from line 27

2727* The `gcloud` CLI, authenticated with `gcloud auth login`, and Docker installed locally

2828* For the GKE track: `kubectl`, and a GKE cluster on the VPC created in the walkthrough below

2929* Access to the Claude models you need in Model Garden, in a region that publishes them

30* A Google Workspace OAuth 2.0 web-application client with redirect URI `https://<gateway-host>/oauth/callback`; see [Identity provider setup](/docs/en/claude-apps-gateway-deploy#identity-provider-setup)

3131* A TLS hostname for the gateway, typically an internal DNS name pointing at the load balancer

3232

3333Set the project and region once:

from line 82

8282

8383**3. Build and push the image to Artifact Registry**

8484

85Build the image per the [container image requirements](/docs/en/claude-apps-gateway-deploy#container-image), using the `linux-x64` glibc binary, and push it:

85Build the image per the [container image requirements](/docs/en/claude-apps-gateway-deploy.md#container-image), using the `linux-x64` glibc binary, and push it:

8686

8787```bash theme={null}

8888gcloud artifacts repositories create claude-gateway \

from line 129

129129

130130**5. Write gateway.yaml**

131131

132The `upstreams` block points at Google Cloud's Agent Platform with `auth: {}`, so the gateway authenticates via Application Default Credentials from the runtime service account. See the [configuration reference](/docs/en/claude-apps-gateway-config) for every field.

133133

134134Two `listen` fields describe what fronts the gateway:

135135

from line 221

221221

222222> [!NOTE]

223223>

224> Each instance holds up to [`store.max_connections`](/docs/en/claude-apps-gateway-config#store) Postgres connections, five by default. Use [Size the connection pool](/docs/en/claude-apps-gateway-deploy#size-the-connection-pool) to check `--max-instances=8` against the connections your database has left for the gateway, and include the extra instances a rolling update starts.

224> Each instance holds up to [`store.max_connections`](/docs/en/claude-apps-gateway-config#store) Postgres connections, five by default. Use [Size the connection pool](/docs/en/claude-apps-gateway-deploy.md#size-the-connection-pool) to check `--max-instances=8` against the connections your database has left for the gateway, and include the extra instances a rolling update starts.

225225

226226The invoker IAM check must be open or disabled. The gateway runs its own OIDC and its clients carry no GCP token, so Cloud Run's invoker check has to admit unauthenticated requests. The gateway's OIDC sign-in authenticates the request once it reaches the container, with `allowed_email_domains` gating which domains may sign in.

227227

from line 267

267267 iam.gke.io/gcp-service-account="claude-gateway@${PROJECT_ID}.iam.gserviceaccount.com"

268268```

269269

270Deploy the gateway as a standard Deployment plus a Service and an internal Ingress, class `gce-internal`, as described in [Kubernetes deployment](/docs/en/claude-apps-gateway-deploy#kubernetes), with:

271271

272272* `serviceAccountName: gateway`

273273* the Secret Manager CSI driver mounting secrets at `/secrets`

from line 275

275275

276276Attach a BackendConfig with a raised `timeoutSec` to the gateway Service: the load balancer backend service behind GKE Ingress defaults to a 30-second timeout, which cuts off long streaming responses.

277277

278Don't apply an egress NetworkPolicy that blocks `169.254.169.254` on a Workload Identity cluster; the pod must reach the metadata server for credentials. The gateway's built-in [SSRF guard](/docs/en/claude-apps-gateway-deploy#threat-model-summary) is the defense there.

279279

280280The gateway logs a boot warning that the metadata endpoint is reachable and suggests applying an egress NetworkPolicy. Under Workload Identity that warning is expected, because the pod needs the endpoint.

281281

from line 297

297297

298298## Troubleshooting

299299

300For gateway boot and login errors, see the platform-agnostic [troubleshooting table](/docs/en/claude-apps-gateway-deploy#troubleshooting). The entries below are specific to Google Cloud.

300For gateway boot and login errors, see the platform-agnostic [troubleshooting table](/docs/en/claude-apps-gateway-deploy.md#troubleshooting). The entries below are specific to Google Cloud.

301301

302302| Symptom | Cause | Fix |

303303| - | - | - |

from line 310

310310

311311## Next steps

312312

313* [Configuration reference](/docs/en/claude-apps-gateway-config): every `gateway.yaml` option, including `managed.policies` and `telemetry`

314* [Deployment and operations](/docs/en/claude-apps-gateway-deploy): IdP setup, health checks, JWT secret rotation, upgrades, and the security model

313* [Configuration reference](/docs/en/claude-apps-gateway-config.md): every `gateway.yaml` option, including `managed.policies` and `telemetry`

314* [Deployment and operations](/docs/en/claude-apps-gateway-deploy.md): IdP setup, health checks, JWT secret rotation, upgrades, and the security model

315315* [Claude apps gateway overview](/docs/en/claude-apps-gateway): quickstart and connecting developers

316316

claude-apps-gateway-spend-limits Changed · +7 / -7 lines

from line 4

55Spend limits cap how much each developer can spend through your [Claude apps gateway](/docs/en/claude-apps-gateway) in a given day, week, or month. When a developer passes their cap, the gateway returns `429` on their next request and blocks them until the period resets or an admin raises the cap. Use spend limits to give each developer, group, or the whole organization a ceiling on a credential everyone shares.

7By default, a Claude apps gateway forwards all inference through one shared upstream credential, so your provider's bill attributes everything to that credential, not to individual developers. On Amazon Bedrock, [per-developer AWS cost attribution](/docs/en/claude-apps-gateway-config#per-developer-aws-cost-attribution) changes this. Without per-developer limits, one runaway agent fleet can spend the organization's entire commitment. Spend limits are the gateway's per-developer view and circuit breaker on top of that shared bill.

7By default, a Claude apps gateway forwards all inference through one shared upstream credential, so your provider's bill attributes everything to that credential, not to individual developers. On Amazon Bedrock, [per-developer AWS cost attribution](/docs/en/claude-apps-gateway-config.md#per-developer-aws-cost-attribution) changes this. Without per-developer limits, one runaway agent fleet can spend the organization's entire commitment. Spend limits are the gateway's per-developer view and circuit breaker on top of that shared bill.

99## Set a cap

1010

from line 30

3030

3131| Field | Values | Description |

3232| - | - | - |

33| `scope.type` | `user`, `rbac_group`, `organization` | `user` targets one developer by their OpenID Connect (OIDC) `sub`, the stable user ID your identity provider assigns; pass it as `scope.user_id`. `rbac_group` targets an [IdP group](/docs/en/claude-apps-gateway-config#managed) by name; pass it as `scope.rbac_group_id`. `organization` is the org-wide default. The gateway accepts all three; Anthropic's public `POST` is user-only today. |

33| `scope.type` | `user`, `rbac_group`, `organization` | `user` targets one developer by their OpenID Connect (OIDC) `sub`, the stable user ID your identity provider assigns; pass it as `scope.user_id`. `rbac_group` targets an [IdP group](/docs/en/claude-apps-gateway-config.md#managed) by name; pass it as `scope.rbac_group_id`. `organization` is the org-wide default. The gateway accepts all three; Anthropic's public `POST` is user-only today. |

3434| `amount` | Whole-number string of USD cents, or `null` | `null` is unlimited. `"0"` is a zero cap, which blocks every request. |

3535| `period` | `daily`, `weekly`, `monthly` | A scope can hold one cap per period, and each enforces independently: a developer is blocked if over any of them. |

3636

from line 70

7070

7171#### Long-prompt rates

7272

73The list price for [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) has a [higher rate for prompts over a token threshold](/docs/en/model-config#haiku-5-5-context-window-and-pricing). When Haiku 5.5 serves a request whose prompt exceeds the threshold, a gateway server running Claude Code v2.1.293 or later prices the whole request at that rate. The meter counts input tokens, cache reads, and cache writes toward that threshold.

73The list price for [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) has a [higher rate for prompts over a token threshold](/docs/en/model-config.md#haiku-5-5-context-window-and-pricing). When Haiku 5.5 serves a request whose prompt exceeds the threshold, a gateway server running Claude Code v2.1.293 or later prices the whole request at that rate. The meter counts input tokens, cache reads, and cache writes toward that threshold.

7474

7575If one of your `pricing.overrides` rows matches the request, that row's rates apply at any prompt length.

7676

from line 78

7878

7979The pre-check queries Postgres with a two-second timeout. If the store is unreachable or times out, enforcement fails open by default: the request proceeds, the gateway logs a warning, and the response carries no `anthropic-ratelimit-unified-*` headers. Set [`enforcement.fail_closed_on_error: true`](/docs/en/claude-apps-gateway-config#enforcement) to fail closed instead, which returns the same `429 billing_error` but with the message `spend limit unavailable` and no period, reset time, or `retry-after` header. Fail-open keeps a store outage from becoming an inference outage; fail-closed guarantees no unmetered spend.

8080

81Fail-open only helps while your load balancer or orchestrator still routes traffic to the gateway. See [Outage behavior](/docs/en/claude-apps-gateway-deploy#outage-behavior) for `store.readiness_grace_seconds`, which keeps replicas passing their readiness check through a short outage.

81Fail-open only helps while your load balancer or orchestrator still routes traffic to the gateway. See [Outage behavior](/docs/en/claude-apps-gateway-deploy.md#outage-behavior) for `store.readiness_grace_seconds`, which keeps replicas passing their readiness check through a short outage.

8282

8383### Usage warnings in Claude Code

8484

85Claude Code warns a developer as they approach their cap: once utilization passes 75%, and again past 95% of their most-consumed cap. When the gateway blocks a request, Claude Code shows the gateway's `429` message as is, including your `admin.blocked_message`. It also shows the cap in `/usage` and passes it to the developer's [status line](/docs/en/statusline#spend-limit-fields) script.

8686

8787Each display needs a minimum Claude Code version on the developer's machine and on the gateway server:

8888

from line 94

9494

9595The warnings and the percentage come from the `anthropic-ratelimit-unified-*` headers, which the gateway adds to each successful `/v1/messages` response for a developer who has a cap. The headers always describe the developer's own cap: the gateway strips the upstream provider's rate-limit headers, which describe your shared quota, and never forwards them.

9696

97The spend a developer sees is the gateway's own [estimate](#how-requests-are-priced), the same figure it enforces the cap with, and not an amount from your provider's bill. Claude Code reads the dollar amounts with a separate request to the gateway. If you set `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` on developers' machines, as [Compliance posture](/docs/en/claude-apps-gateway-deploy#compliance-posture) suggests, Claude Code skips that request. With that variable set, or with a gateway server older than v2.1.284, the bar and the status line stay percentage-only.

97The spend a developer sees is the gateway's own [estimate](#how-requests-are-priced), the same figure it enforces the cap with, and not an amount from your provider's bill. Claude Code reads the dollar amounts with a separate request to the gateway. If you set `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` on developers' machines, as [Compliance posture](/docs/en/claude-apps-gateway-deploy.md#compliance-posture) suggests, Claude Code skips that request. With that variable set, or with a gateway server older than v2.1.284, the bar and the status line stay percentage-only.

9898

9999## Admin API reference

100100

from line 168

168168## Related

169169

170170* [`admin` and `enforcement` configuration](/docs/en/claude-apps-gateway-config#admin): enabling the admin API and tuning retention

171* [Deployment guide](/docs/en/claude-apps-gateway-deploy#postgres): Postgres schema and backup guidance

171* [Deployment guide](/docs/en/claude-apps-gateway-deploy.md#postgres): Postgres schema and backup guidance

172172

claude-code-on-the-web Changed · +71 / -71 lines

from line 13

1313You can start a cloud session from any of these surfaces:

1414

1515* **Browser**: [claude.ai/code](https://claude.ai/code), also called Claude Code on the web

16* **Mobile**: the **Code** tab in the [Claude app](/docs/en/mobile)

17* **Desktop app**: select **Cloud** instead of **Local** when you [start a session](/docs/en/desktop#run-long-running-tasks-in-the-cloud)

16* **Mobile**: the **Code** tab in the [Claude app](/docs/en/mobile.md)

17* **Desktop app**: select **Cloud** instead of **Local** when you [start a session](/docs/en/desktop.md#run-long-running-tasks-in-the-cloud)

1818* **Terminal**: [`claude --cloud`](#from-terminal-to-cloud)

19* **Cloud scheduled tasks**: [scheduled and triggered runs](/docs/en/routines) each run as a cloud session

19* **Cloud scheduled tasks**: [scheduled and triggered runs](/docs/en/routines.md) each run as a cloud session

2020

2121Once you're set up, use this page to move work between your terminal and the cloud, manage and share sessions, turn on auto-fix for pull requests, and troubleshoot.

2222

from line 24

2424>

2525> These cases are covered on other pages:

2626>

27> * **Starting your first cloud session**: [Get started with cloud sessions](/docs/en/web-quickstart) connects GitHub and walks through a task in the browser

28> * **Many cloud sessions for one body of work**: a [project](/docs/en/claude-projects) has Claude start and keep track of them for you

29> * **Steering a local session from another device**: sessions in your terminal, IDE, or the Desktop app with **Local** selected run on your machine, and [Remote Control](/docs/en/remote-control) lets you reach them from your phone or browser

27> * **Starting your first cloud session**: [Get started with cloud sessions](/docs/en/web-quickstart.md) connects GitHub and walks through a task in the browser

28> * **Many cloud sessions for one body of work**: a [project](/docs/en/claude-projects.md) has Claude start and keep track of them for you

3030

3131## Cloud environments

3232

33Every cloud session runs in a [cloud environment](/docs/en/cloud-environments), the saved configuration that controls network access, environment variables, and setup scripts.

33Every cloud session runs in a [cloud environment](/docs/en/cloud-environments.md), the saved configuration that controls network access, environment variables, and setup scripts.

3434

35* **Your first environment**: if you don't have one yet, onboarding sets up a **Default** environment with [**Trusted** network access](/docs/en/cloud-environments#access-levels), either by creating it for you or by asking you to create it. See [The Default environment](/docs/en/cloud-environments#the-default-environment) for which of those happens on your plan

36* **Which environment a session uses**: see [The Default environment](/docs/en/cloud-environments#the-default-environment) for how sessions choose an environment when you have more than one

37* **Change what sessions can reach or run at startup**: see [Configure cloud environments](/docs/en/cloud-environments)

38* **What's installed without any configuration**: see [Installed tools](/docs/en/cloud-environments#installed-tools)

35* **Your first environment**: if you don't have one yet, onboarding sets up a **Default** environment with [**Trusted** network access](/docs/en/cloud-environments.md#access-levels), either by creating it for you or by asking you to create it. See [The Default environment](/docs/en/cloud-environments.md#the-default-environment) for which of those happens on your plan

36* **Which environment a session uses**: see [The Default environment](/docs/en/cloud-environments.md#the-default-environment) for how sessions choose an environment when you have more than one

37* **Change what sessions can reach or run at startup**: see [Configure cloud environments](/docs/en/cloud-environments.md)

38* **What's installed without any configuration**: see [Installed tools](/docs/en/cloud-environments.md#installed-tools)

3939

4040## GitHub authentication options

4141

from line 43

4343

4545| :- | :- | :- | :- |

46| **GitHub App** | Authorize the Claude GitHub App during [web onboarding](/docs/en/web-quickstart) | Any public repository, and private repositories that the Claude GitHub App is installed on | Browser onboarding; teams that want [Auto-fix](#auto-fix-pull-requests) |

46| **GitHub App** | Authorize the Claude GitHub App during [web onboarding](/docs/en/web-quickstart.md) | Any public repository, and private repositories that the Claude GitHub App is installed on | Browser onboarding; teams that want [Auto-fix](#auto-fix-pull-requests) |

4747| **`/web-setup`** | Run `/web-setup` in your terminal to send your local `gh` CLI token to your Claude account | Any repository your `gh` token can access, whether or not the Claude GitHub App is installed | Individual developers who already use `gh` |

4848

4949These features depend on the Claude GitHub App being installed on the repository:

5050

5151* **Auto-fix**: installing the Claude GitHub App on a repository also enables [Auto-fix](#auto-fix-pull-requests) for pull requests in it

52* **Projects**: threads in a [project](/docs/en/claude-projects) need the Claude GitHub App installed on each repository they clone, whichever method you connected with. See [Set up GitHub access](/docs/en/claude-projects#set-up-github-access)

52* **Projects**: threads in a [project](/docs/en/claude-projects.md) need the Claude GitHub App installed on each repository they clone, whichever method you connected with. See [Set up GitHub access](/docs/en/claude-projects.md#set-up-github-access)

5353

54In Anthropic-hosted environments, your GitHub credentials stay encrypted on Anthropic's servers and never enter a session's VM. GitHub operations from the VM go through the [GitHub proxy](/docs/en/cloud-environments#github-proxy), which attaches the credential on the server side.

54In Anthropic-hosted environments, your GitHub credentials stay encrypted on Anthropic's servers and never enter a session's VM. GitHub operations from the VM go through the [GitHub proxy](/docs/en/cloud-environments.md#github-proxy), which attaches the credential on the server side.

5555

56See [Connect from your terminal](/docs/en/web-quickstart#connect-from-your-terminal) for the `/web-setup` walkthrough, including what `/web-setup` stores and how to remove it.

56See [Connect from your terminal](/docs/en/web-quickstart.md#connect-from-your-terminal) for the `/web-setup` walkthrough, including what `/web-setup` stores and how to remove it.

5757

5858> [!NOTE]

5959>

60> Organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled, or with the [HIPAA configuration](/docs/en/hipaa-setup) applied, can't use `/web-setup` or other cloud session features. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) (CMEK) can't start cloud sessions either.

60> Organizations with [Zero Data Retention](/docs/en/zero-data-retention.md) enabled, or with the [HIPAA configuration](/docs/en/hipaa-setup.md) applied, can't use `/web-setup` or other cloud session features. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) (CMEK) can't start cloud sessions either.

6161

6262### Quick setup for Team and Enterprise

6363

from line 67

6767

6868* **`/web-setup`**: members can connect GitHub with `/web-setup`. While the setting is off, the command is hidden

6969* **GitHub App prompt**: browser onboarding skips the Claude GitHub App install prompt

70* **First environment**: browser onboarding creates the [**Default** environment](/docs/en/cloud-environments#the-default-environment) for members instead of showing the environment form

70* **First environment**: browser onboarding creates the [**Default** environment](/docs/en/cloud-environments.md#the-default-environment) for members instead of showing the environment form

7171

72An [Owner](/docs/en/server-managed-settings#access-control) turns it on with the **Quick setup** toggle at [**Organization settings > Claude Code**](https://claude.ai/admin-settings/claude-code).

72An [Owner](/docs/en/server-managed-settings.md#access-control) turns it on with the **Quick setup** toggle at [**Organization settings > Claude Code**](https://claude.ai/admin-settings/claude-code).

7373

7474## Move tasks between terminal and cloud

7575

76These workflows require the [Claude Code CLI](/docs/en/quickstart) signed in to the same claude.ai account. You can start new cloud sessions from your terminal, or pull cloud sessions into your terminal to continue locally. Cloud sessions persist even if you close your laptop, and you can monitor them from anywhere including the Claude mobile app.

76These workflows require the [Claude Code CLI](/docs/en/quickstart.md) signed in to the same claude.ai account. You can start new cloud sessions from your terminal, or pull cloud sessions into your terminal to continue locally. Cloud sessions persist even if you close your laptop, and you can monitor them from anywhere including the Claude mobile app.

7777

7878> [!NOTE]

7979>

80> From the CLI, session handoff is one-way: you can pull cloud sessions into your terminal with `--teleport`, but you can't push an existing terminal session to the cloud. The `--cloud` flag with a task description creates a new cloud session for your current repository; with `-p` and a session ID or claude.ai/code URL it instead [queues a message into that existing session](/docs/en/claude-code-on-the-web#send-follow-ups-from-the-cli). The [Desktop app](/docs/en/desktop#continue-in-another-surface) can send a local session in its Code tab to the cloud from its **Open in** menu.

80> From the CLI, session handoff is one-way: you can pull cloud sessions into your terminal with `--teleport`, but you can't push an existing terminal session to the cloud. The `--cloud` flag with a task description creates a new cloud session for your current repository; with `-p` and a session ID or claude.ai/code URL it instead [queues a message into that existing session](/docs/en/claude-code-on-the-web.md#send-follow-ups-from-the-cli). The [Desktop app](/docs/en/desktop.md#continue-in-another-surface) can send a local session in its Code tab to the cloud from its **Open in** menu.

8181

8282### Start a cloud session from your terminal

8383

from line 91

9191

9292`--cloud` works with a single repository at a time. The task runs in the cloud while you continue working locally. The older `--remote` spelling still works as a deprecated alias for `--cloud`.

9393

94While the cloud container starts, the CLI shows a live checklist of setup steps, such as cloning the repository and running your [setup script](/docs/en/cloud-environments#setup-scripts). It queues messages you type during provisioning and sends them once the session is ready.

94While the cloud container starts, the CLI shows a live checklist of setup steps, such as cloning the repository and running your [setup script](/docs/en/cloud-environments.md#setup-scripts). It queues messages you type during provisioning and sends them once the session is ready.

9595

9696> [!NOTE]

9797>

98> `--cloud` creates cloud sessions. `--remote-control` is unrelated: it lets you monitor and steer a local CLI session from claude.ai or the Claude app. See [Remote Control](/docs/en/remote-control).

9999

100100Open the session on claude.ai or the Claude mobile app to check progress or interact directly. From there you can steer Claude, provide feedback, or answer questions as in any other conversation.

101101

from line 147

147147* The directory must be a git repository with at least one commit

148148* The bundled repository must be under 100 MB. Larger repositories fall back to bundling only the current branch, then to a single squashed snapshot of the working tree, and fail if the snapshot is still too large

149149* Untracked files are not included; run `git add` on files you want the cloud session to see

150* On macOS, Linux, and WSL, Claude Code refuses the upload when it can't follow a git setting that affects which attribute rules apply to your files, such as `core.attributesFile` set in an included config file. The [refusal message](/docs/en/errors#the-repository-upload-cant-follow-a-git-setting) names the setting and the fix

150* On macOS, Linux, and WSL, Claude Code refuses the upload when it can't follow a git setting that affects which attribute rules apply to your files, such as `core.attributesFile` set in an included config file. The [refusal message](/docs/en/errors.md#the-repository-upload-cant-follow-a-git-setting) names the setting and the fix

151151* Sessions created from a bundle can push back to a GitHub remote only when your [GitHub connection](#github-authentication-options) has push access to that repository

152152

153153On macOS, Linux, and WSL, the upload also needs git 2.31 or later and a checkout layout it supports, while on native Windows Claude Code uploads without either check. When a checkout doesn't meet those requirements, Claude Code doesn't start the session. It prints an error that contains `Not uploading this working tree:`, names the cause, and says what to change. These are the common causes:

from line 171

171171claude -p "your message" --cloud <session-id>

172172```

173173

174The CLI queues the message into the session and exits without waiting for a reply. Use it to steer a long-running session, queue the next step while the current one is still finishing, or send follow-ups from a [CI script](/docs/en/self-hosted-environments-testing#run-the-test-loop). You can also pipe the message on stdin instead of passing it as an argument: `echo "your message" | claude -p --cloud <session-id>`.

174The CLI queues the message into the session and exits without waiting for a reply. Use it to steer a long-running session, queue the next step while the current one is still finishing, or send follow-ups from a [CI script](/docs/en/self-hosted-environments-testing.md#run-the-test-loop). You can also pipe the message on stdin instead of passing it as an argument: `echo "your message" | claude -p --cloud <session-id>`.

175175

176176For `<session-id>`, pass the bare ID, such as `session_...` or `cse_...`, or the session's `claude.ai/code/<id>` URL, with or without the scheme or query string. Find the ID in your session list at claude.ai/code.

177177

from line 234

234234

235235### Permission modes in cloud sessions

236236

237You pick a cloud session's [permission mode](/docs/en/permission-modes) from the [mode dropdown](/docs/en/permission-modes#switch-permission-modes), both when you create the task and while the session runs.

237You pick a cloud session's [permission mode](/docs/en/permission-modes.md) from the [mode dropdown](/docs/en/permission-modes.md#switch-permission-modes), both when you create the task and while the session runs.

238238

239239Claude Code resumes a session in the permission mode it was in when you do either of these:

240240

241241* Reopen a session whose Anthropic-hosted [environment expired](#environment-expired)

242* Send a message to a session that a self-hosted runner [released while it was idle](/docs/en/self-hosted-environments-reference#runner-cli-flags)

242* Send a message to a session that a self-hosted runner [released while it was idle](/docs/en/self-hosted-environments-reference.md#runner-cli-flags)

243243

244244### Review changes

245245

from line 251

251251

252252These steps are covered elsewhere:

253253

254* **The full walkthrough, including PR creation**: see [Review and iterate](/docs/en/web-quickstart#review-and-iterate)

254* **The full walkthrough, including PR creation**: see [Review and iterate](/docs/en/web-quickstart.md#review-and-iterate)

255255* **Having Claude monitor the PR for CI failures and review comments automatically**: see [Auto-fix pull requests](#auto-fix-pull-requests)

256256

257257### Manage context

258258

259Cloud sessions support [built-in commands](/docs/en/commands) that produce text output. Commands that only run in the terminal interface, such as `/plugin` or `/resume`, aren't available. Commands that open a picker or panel in the terminal behave differently in cloud sessions:

259Cloud sessions support [built-in commands](/docs/en/commands.md) that produce text output. Commands that only run in the terminal interface, such as `/plugin` or `/resume`, aren't available. Commands that open a picker or panel in the terminal behave differently in cloud sessions:

260260

261* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms follow each command's [availability notes](/docs/en/commands#all-commands).

262* **`/fast`**: toggles [fast mode](/docs/en/fast-mode#use-fast-mode-in-cloud-sessions) for the session when fast mode is [available on your account](/docs/en/fast-mode#requirements). Requires Claude Code v2.1.271 or later in the session's environment.

263* **`/config`**: in your browser at claude.ai/code, opens the Claude Code section of your settings instead of setting a value, and text after the command, including `key=value`, is ignored. To change a setting for a cloud session, set an [environment variable](/docs/en/cloud-environments#set-environment-variables) on the environment. In a session with one repository outside a [project](/docs/en/claude-projects)'s threads, commit the key to that repository's `.claude/settings.json` instead. [Settings in cloud sessions](/docs/en/settings#settings-in-cloud-sessions) lists what each session reads.

262* **`/fast`**: toggles [fast mode](/docs/en/fast-mode.md#use-fast-mode-in-cloud-sessions) for the session when fast mode is [available on your account](/docs/en/fast-mode.md#requirements). Requires Claude Code v2.1.271 or later in the session's environment.

263* **`/config`**: in your browser at claude.ai/code, opens the Claude Code section of your settings instead of setting a value, and text after the command, including `key=value`, is ignored. To change a setting for a cloud session, set an [environment variable](/docs/en/cloud-environments.md#set-environment-variables) on the environment. In a session with one repository outside a [project](/docs/en/claude-projects.md)'s threads, commit the key to that repository's `.claude/settings.json` instead. [Settings in cloud sessions](/docs/en/settings.md#settings-in-cloud-sessions) lists what each session reads.

264264

265265For context management specifically:

266266

from line 270

270270| `/context` | Yes | Shows what's currently in the context window |

271271| `/clear` | No | Start a new session from the sidebar instead |

272272

273Auto-compaction runs automatically when the context window approaches capacity. Cloud sessions set [`CLAUDE_AUTOCOMPACT_PCT_OVERRIDE`](/docs/en/env-vars) themselves, so compaction triggers partway through the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) rather than when the window fills. That value overrides one you add in your [environment variables](/docs/en/cloud-environments#set-environment-variables), so adding the variable there doesn't change when compaction triggers.

273Auto-compaction runs automatically when the context window approaches capacity. Cloud sessions set [`CLAUDE_AUTOCOMPACT_PCT_OVERRIDE`](/docs/en/env-vars) themselves, so compaction triggers partway through the [auto-compact window](/docs/en/model-config.md#set-the-auto-compact-window) rather than when the window fills. That value overrides one you add in your [environment variables](/docs/en/cloud-environments.md#set-environment-variables), so adding the variable there doesn't change when compaction triggers.

274274

275275To change the auto-compact window instead, set [`CLAUDE_CODE_AUTO_COMPACT_WINDOW`](/docs/en/env-vars) in your environment variables, or run [`/autocompact`](/docs/en/commands#all-commands) with a token count in a session where the variable isn't set.

276276

277[Subagents](/docs/en/sub-agents) work the same way they do locally. Claude can spawn them with the Agent tool to offload research or parallel work into a separate context window, keeping the main conversation lighter. Outside a [project](/docs/en/claude-projects#what-threads-pick-up-from-your-repositories)'s threads, subagents defined in your repo's `.claude/agents/` load automatically.

277[Subagents](/docs/en/sub-agents.md) work the same way they do locally. Claude can spawn them with the Agent tool to offload research or parallel work into a separate context window, keeping the main conversation lighter. Outside a [project](/docs/en/claude-projects.md#what-threads-pick-up-from-your-repositories)'s threads, subagents defined in your repo's `.claude/agents/` load automatically.

278278

279[Agent teams](/docs/en/agent-teams) are off by default but can be enabled by adding `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` to your [environment variables](/docs/en/cloud-environments#set-environment-variables).

279[Agent teams](/docs/en/agent-teams.md) are off by default but can be enabled by adding `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` to your [environment variables](/docs/en/cloud-environments.md#set-environment-variables).

280280

281281### Take back a queued message

282282

from line 295

295295* **Visibility options**: **Private** and **Team**. Team visibility makes the session visible to other members of your claude.ai organization

296296* **Repository access**: verification is enabled by default, based on the GitHub account connected to the recipient's account

297297* **Your name**: your account's display name is visible to all recipients with access

298* **Slack sessions**: [Claude in Slack](/docs/en/slack) sessions are automatically shared with Team visibility

298* **Slack sessions**: [Claude in Slack](/docs/en/slack.md) sessions are automatically shared with Team visibility

299299

300300#### Share from a Max or Pro account

301301

from line 360

360360Each cloud session is separated from your machine and from other sessions through several layers:

361361

362362* **Isolated virtual machines**: each session runs in an isolated, Anthropic-managed VM. Sessions your organization routes to a [self-hosted environment](/docs/en/self-hosted-environments) run on your own infrastructure instead, where isolation is your deployment's responsibility

363* **Network access controls**: in Anthropic-hosted environments, network access is limited by default and can be disabled. See [Network access](/docs/en/cloud-environments#network-access) for the access levels, the [default allowed domains](/docs/en/cloud-environments#default-allowed-domains), and the traffic that doesn't go through the allowlist. In a self-hosted environment, you restrict session egress at your own network boundary. When running with network access disabled, Claude Code can still communicate with the Anthropic API, which may allow data to exit the VM.

364* **Credential protection**: in Anthropic-hosted environments, git credentials and signing keys stay outside the sandbox, and a proxy authenticates on the session's behalf with scoped credentials. In a self-hosted environment, your deployment supplies git credentials; see [Configure git](/docs/en/self-hosted-environments-deploy#configure-git)

365* **Network secrets**: in Anthropic-hosted environments, keys you [add to a cloud environment](/docs/en/cloud-environments#add-network-secrets) stay outside the sandbox the same way, attached to matching requests after they leave the session. A self-hosted environment doesn't have network secrets

363* **Network access controls**: in Anthropic-hosted environments, network access is limited by default and can be disabled. See [Network access](/docs/en/cloud-environments.md#network-access) for the access levels, the [default allowed domains](/docs/en/cloud-environments.md#default-allowed-domains), and the traffic that doesn't go through the allowlist. In a self-hosted environment, you restrict session egress at your own network boundary. When running with network access disabled, Claude Code can still communicate with the Anthropic API, which may allow data to exit the VM.

365* **Network secrets**: in Anthropic-hosted environments, keys you [add to a cloud environment](/docs/en/cloud-environments.md#add-network-secrets) stay outside the sandbox the same way, attached to matching requests after they leave the session. A self-hosted environment doesn't have network secrets

366366* **Secure analysis**: code is analyzed and modified within the session's isolated environment before creating PRs

367367

368368## Troubleshooting

369369

370For runtime API errors that appear in the conversation such as `API Error: 500`, `529 Overloaded`, `429`, or `Prompt is too long`, see the [Error reference](/docs/en/errors). Those errors and their fixes are shared with the CLI and Desktop app. The sections below cover issues specific to cloud sessions.

370For runtime API errors that appear in the conversation such as `API Error: 500`, `529 Overloaded`, `429`, or `Prompt is too long`, see the [Error reference](/docs/en/errors.md). Those errors and their fixes are shared with the CLI and Desktop app. The sections below cover issues specific to cloud sessions.

371371

372372### Session creation failed

373373

from line 375

375375

376376* Check [status.claude.com](https://status.claude.com) for cloud session incidents

377377* Retry after a minute, as capacity is provisioned on demand

378* Confirm your GitHub connection can reach the repository by following [No repositories appear after connecting GitHub](/docs/en/web-quickstart#no-repositories-appear-after-connecting-github)

378* Confirm your GitHub connection can reach the repository by following [No repositories appear after connecting GitHub](/docs/en/web-quickstart.md#no-repositories-appear-after-connecting-github)

379379

380380### Unable to get organization UUID

381381

from line 410

410410| Message | What it means |

411411| - | - |

412412| `Cloud sessions aren't available with <provider>. They run on Anthropic's infrastructure and require an Anthropic account.` | Claude Code is configured for a third-party provider. The message names the provider with the label your configuration uses, such as `Amazon Bedrock` or `Google Vertex AI`. Remove that provider's configuration, for example by unsetting `CLAUDE_CODE_USE_BEDROCK`, and sign in with an Anthropic account (`claude auth login`). |

413| `Cloud sessions are disabled by your organization's policy. Contact your organization admin to enable them.` | Your organization's `allow_remote_sessions` policy is off; see [Cloud sessions are disabled by your organization's policy](/docs/en/errors#cloud-sessions-are-disabled-by-your-organizations-policy). If the message instead names a credential this session is using, see [Cloud sessions use your claude.ai login](/docs/en/errors#cloud-sessions-use-your-claude-ai-login). |

413| `Cloud sessions are disabled by your organization's policy. Contact your organization admin to enable them.` | Your organization's `allow_remote_sessions` policy is off; see [Cloud sessions are disabled by your organization's policy](/docs/en/errors.md#cloud-sessions-are-disabled-by-your-organizations-policy). If the message instead names a credential this session is using, see [Cloud sessions use your claude.ai login](/docs/en/errors.md#cloud-sessions-use-your-claude-ai-login). |

414414| `Couldn't verify your organization's policy for cloud sessions. Check your network connection and try again.` | Claude Code hasn't finished loading your organization's policy, so it refuses the send rather than assume cloud sessions are allowed. Check your network connection and retry. |

415| `Cloud sessions aren't available:` followed by a cause | Loading your organization's policy failed, and the rest of the message says how. Act on the cause it names; see [Couldn't verify your organization's policy for cloud sessions](/docs/en/errors#couldnt-verify-your-organizations-policy-for-cloud-sessions). |

415| `Cloud sessions aren't available:` followed by a cause | Loading your organization's policy failed, and the rest of the message says how. Act on the cause it names; see [Couldn't verify your organization's policy for cloud sessions](/docs/en/errors.md#couldnt-verify-your-organizations-policy-for-cloud-sessions). |

416416| `Attaching to an existing cloud session is not enabled for your account.` | You ran `--cloud <session-id>` without `-p`. Send the message with `claude -p "your message" --cloud <session-id>`. |

417417| `Session not found: <id>` | The ID or URL doesn't match a session you can access. Check it against the session's claude.ai/code URL. |

418418| `cloud session <id> is archived and cannot accept new messages` | The session has been archived. Start a new session instead. |

from line 419

419419

420420### Environment expired

421421

422Cloud sessions stop after a period of inactivity and the session's VM is reclaimed. A session counts as inactive while it waits for you to approve an [MCP connector](/docs/en/cloud-environments#network-access) tool call or to sign in to an MCP server, and it can expire during that wait.

422Cloud sessions stop after a period of inactivity and the session's VM is reclaimed. A session counts as inactive while it waits for you to approve an [MCP connector](/docs/en/cloud-environments.md#network-access) tool call or to sign in to an MCP server, and it can expire during that wait.

423423

424424Reopen the session from [claude.ai/code](https://claude.ai/code) to provision a fresh VM:

425425

from line 426

426426* **Restored**: your conversation history

427427* **Not restored**: background work that was still running or pending when the VM was reclaimed, including:

428428 * **Shell commands**: Claude Code tells Claude which commands stopped. Ask Claude to rerun the ones you still need.

429 * **Subagents**: Claude Code tells Claude which subagents stopped, and which of those can be [resumed](/docs/en/sub-agents#resume-subagents) instead of started over. Ask Claude to continue their work.

430 * **Session-scoped scheduled tasks**: tasks you [scheduled in the session](/docs/en/scheduled-tasks) and a `/loop` waiting for its next iteration don't carry over to the reopened session. Ask Claude to schedule the tasks again, or run `/loop` again to restart the loop.

429 * **Subagents**: Claude Code tells Claude which subagents stopped, and which of those can be [resumed](/docs/en/sub-agents.md#resume-subagents) instead of started over. Ask Claude to continue their work.

430 * **Session-scoped scheduled tasks**: tasks you [scheduled in the session](/docs/en/scheduled-tasks.md) and a `/loop` waiting for its next iteration don't carry over to the reopened session. Ask Claude to schedule the tasks again, or run `/loop` again to restart the loop.

431431

432432## Limitations

433433

from line 434

434434Before relying on cloud sessions for a workflow, account for these constraints:

435435

436436* **Rate limits**: cloud sessions share rate limits with all other Claude and Claude Code usage within your account. Running multiple tasks in parallel consumes more rate limits proportionately.

437* **Time limits**: commands Claude runs and SessionStart hooks have default timeouts you can change, and a setup script is cached only when it finishes in roughly five minutes. See [Time limits](/docs/en/cloud-environments#time-limits)

438438* **Repository authentication**: you can only pull a cloud session into your terminal when you are authenticated to the same account

439* **Platform restrictions**: repository cloning and pull request creation require GitHub. Self-hosted [GitHub Enterprise Server](/docs/en/github-enterprise-server) instances are supported for Team and Enterprise plans. You can send a GitLab, Bitbucket, or other non-GitHub repository to a cloud session as a [local bundle](#send-local-repositories-without-github) by setting `CCR_FORCE_BUNDLE=1`, but the session can't push results back to that remote

439* **Platform restrictions**: repository cloning and pull request creation require GitHub. Self-hosted [GitHub Enterprise Server](/docs/en/github-enterprise-server.md) instances are supported for Team and Enterprise plans. You can send a GitLab, Bitbucket, or other non-GitHub repository to a cloud session as a [local bundle](#send-local-repositories-without-github) by setting `CCR_FORCE_BUNDLE=1`, but the session can't push results back to that remote

440440* **Organization IP allowlist**: cloud sessions call the Anthropic API from Anthropic-managed infrastructure, not your network, while sessions in a [self-hosted environment](/docs/en/self-hosted-environments) call it from your own network. If your organization has [IP allowlisting](https://support.claude.com/en/articles/13200993-restrict-access-to-claude-with-ip-allowlisting) enabled, every Anthropic-hosted cloud session fails with an authentication error.

441 * **Code Review and scheduled tasks**: the same applies to [Code Review](/docs/en/code-review) and to [cloud scheduled tasks](/docs/en/routines) that run on Anthropic-hosted environments. A scheduled task routed to a self-hosted environment calls the API from your own network.

441 * **Code Review and scheduled tasks**: the same applies to [Code Review](/docs/en/code-review.md) and to [cloud scheduled tasks](/docs/en/routines.md) that run on Anthropic-hosted environments. A scheduled task routed to a self-hosted environment calls the API from your own network.

442442 * **Getting an exemption**: contact [Anthropic support](https://support.claude.com/) to exempt Anthropic-hosted services from your organization's IP allowlist.

443443

444444## Related resources

445445

446* [Cloud environments](/docs/en/cloud-environments): configure network access, environment variables, and setup scripts for cloud sessions

447* [Projects](/docs/en/claude-projects): one conversation where Claude coordinates parallel cloud sessions on your repositories and reports back

448* [Ultrareview](/docs/en/ultrareview): run a deep multi-agent code review in a cloud sandbox

449* [Cloud scheduled tasks](/docs/en/routines): automate work on a schedule, via API call, or in response to GitHub events

450* [Hooks configuration](/docs/en/hooks): run scripts at session lifecycle events

451* [All settings](/docs/en/settings-reference): all configuration options

452* [Security](/docs/en/security): isolation guarantees and data handling

453* [Data usage](/docs/en/data-usage): what Anthropic retains from cloud sessions

446* [Cloud environments](/docs/en/cloud-environments.md): configure network access, environment variables, and setup scripts for cloud sessions

447* [Projects](/docs/en/claude-projects.md): one conversation where Claude coordinates parallel cloud sessions on your repositories and reports back

448* [Ultrareview](/docs/en/ultrareview.md): run a deep multi-agent code review in a cloud sandbox

449* [Cloud scheduled tasks](/docs/en/routines.md): automate work on a schedule, via API call, or in response to GitHub events

450* [Hooks configuration](/docs/en/hooks.md): run scripts at session lifecycle events

451* [All settings](/docs/en/settings-reference.md): all configuration options

452* [Security](/docs/en/security.md): isolation guarantees and data handling

453* [Data usage](/docs/en/data-usage.md): what Anthropic retains from cloud sessions

454454* [Claude Tag](https://claude.com/docs/claude-tag/overview): an organization-managed @Claude in Slack that runs on the same cloud infrastructure

455455

claude-platform-on-aws Changed · +9 / -9 lines

from line 4

55Claude Platform on AWS is the Anthropic-operated Claude API with AWS authentication, IAM access control, and AWS Marketplace billing. Requests reach Anthropic's API directly, so you get the same models and API features as the [Claude API](https://platform.claude.com/docs) on the same release schedule. You authenticate with AWS credentials or a workspace API key, and you pay through AWS Marketplace.

7Client-side features that Claude Code turns on through Anthropic's feature-flag service are off by default, and the [advisor tool](/docs/en/advisor) isn't available. See the [feature availability matrix](/docs/en/feature-availability#summary-by-provider) for the full list.

7Client-side features that Claude Code turns on through Anthropic's feature-flag service are off by default, and the [advisor tool](/docs/en/advisor.md) isn't available. See the [feature availability matrix](/docs/en/feature-availability.md#summary-by-provider) for the full list.

99Use this guide to point Claude Code at a workspace you've already provisioned through Claude Platform on AWS. For the AWS subscription and workspace setup that comes before this, see the [Claude Platform on AWS documentation](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws).

1010

from line 43

4343

4444For CI and automation, give the runner an IAM role with permission to invoke the Anthropic service and set `AWS_REGION`. The credential chain picks the role up automatically.

4545

46If your SSO credentials expire mid-session, configure [`awsAuthRefresh`](/docs/en/amazon-bedrock#advanced-credential-configuration) so Claude Code re-runs your login command and retries instead of failing. Add the command to your [settings file](/docs/en/settings), such as `~/.claude/settings.json`:

4747

4848```json theme={null}

4949{

from line 65

6565

6666The key is sent as `x-api-key` and takes precedence over SigV4, so any AWS credentials in your environment are ignored. API keys from a separate Claude Console organization won't work here.

6767

68Treat workspace API keys like any other production credential. The [user settings file](/docs/en/settings) `env` block is a convenient way to scope the key to your machine without exporting it globally.

68Treat workspace API keys like any other production credential. The [user settings file](/docs/en/settings.md) `env` block is a convenient way to scope the key to your machine without exporting it globally.

6969

7070> [!NOTE]

7171>

from line 83

8383

8484`ANTHROPIC_AWS_WORKSPACE_ID` is required. Claude Code sends it on every request as the `anthropic-workspace-id` header. Replace the example `wrkspc_01ABCDEFGHIJKLMN` value with your own workspace ID from your Claude Platform on AWS setup.

8585

86Claude Code computes the base URL as `https://aws-external-anthropic.{region}.api.aws` from the AWS region, which it resolves with the [same precedence as Amazon Bedrock](/docs/en/amazon-bedrock#3-configure-claude-code). To override the URL directly, set `ANTHROPIC_AWS_BASE_URL`.

86Claude Code computes the base URL as `https://aws-external-anthropic.{region}.api.aws` from the AWS region, which it resolves with the [same precedence as Amazon Bedrock](/docs/en/amazon-bedrock.md#3-configure-claude-code). To override the URL directly, set `ANTHROPIC_AWS_BASE_URL`.

8787

8888Claude Platform on AWS is opt-in even when AWS credentials are present in your environment. Amazon Bedrock and Microsoft Foundry take precedence in provider routing, so unset `CLAUDE_CODE_USE_BEDROCK` and `CLAUDE_CODE_USE_FOUNDRY` if they're set.

8989

from line 102

102102export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-haiku-4-5

103103```

104104

105For the full list of model IDs and aliases, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). For other model-related variables, see [Model configuration](/docs/en/model-config).

106106

107[Prompt caching](/docs/en/prompt-caching) is enabled automatically. To request a 1-hour cache TTL instead of the 5-minute default, set `ENABLE_PROMPT_CACHING_1H=1`. The API bills 1-hour cache writes at a higher rate. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing) for the rates.

107[Prompt caching](/docs/en/prompt-caching.md) is enabled automatically. To request a 1-hour cache TTL instead of the 5-minute default, set `ENABLE_PROMPT_CACHING_1H=1`. The API bills 1-hour cache writes at a higher rate. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing) for the rates.

108108

109To set different TTLs for your main conversation and for the requests Claude Code makes outside it, [choose the TTL yourself](/docs/en/prompt-caching#choose-the-ttl-yourself).

109To set different TTLs for your main conversation and for the requests Claude Code makes outside it, [choose the TTL yourself](/docs/en/prompt-caching.md#choose-the-ttl-yourself).

110110

111111### 4. Launch and verify

112112

from line 120

120120

121121## Use the Agent SDK

122122

123The [Agent SDK](/docs/en/agent-sdk/overview) reads the same environment variables as the CLI, so any program that spawns the Claude Code subprocess can target Claude Platform on AWS by exporting `CLAUDE_CODE_USE_ANTHROPIC_AWS`, `ANTHROPIC_AWS_WORKSPACE_ID`, and either `ANTHROPIC_AWS_API_KEY` or AWS credentials before the call.

123The [Agent SDK](/docs/en/agent-sdk/overview.md) reads the same environment variables as the CLI, so any program that spawns the Claude Code subprocess can target Claude Platform on AWS by exporting `CLAUDE_CODE_USE_ANTHROPIC_AWS`, `ANTHROPIC_AWS_WORKSPACE_ID`, and either `ANTHROPIC_AWS_API_KEY` or AWS credentials before the call.

124124

125125```typescript theme={null}

126126import { query } from "@anthropic-ai/claude-agent-sdk";

from line 134

134134}

135135```

136136

137This example relies on the ambient AWS credential chain for SigV4. To authenticate with a workspace API key instead, set `ANTHROPIC_AWS_API_KEY` the same way. For the broader Agent SDK surface, see [Agent SDK overview](/docs/en/agent-sdk/overview).

138138

139139## Route through a corporate proxy

140140

claude-projects Changed · +50 / -50 lines

from line 4

55> [!NOTE]

66>

7> Projects are in public beta on Pro and Max plans and rolling out gradually, starting with accounts that have used [cloud sessions](/docs/en/claude-code-on-the-web) and don't have existing projects in claude.ai chat or Cowork. They aren't available on Team or Enterprise plans yet. If **Projects** doesn't appear in the sidebar at [claude.ai/code](https://claude.ai/code) or in the Code tab of the [desktop app](/docs/en/desktop), the rollout hasn't reached your account, and you can [join the waitlist](https://claude.com/form/projects). [Run agents in parallel](/docs/en/agents) lists what you can use in the meantime.

7> Projects are in public beta on Pro and Max plans and rolling out gradually, starting with accounts that have used [cloud sessions](/docs/en/claude-code-on-the-web.md) and don't have existing projects in claude.ai chat or Cowork. They aren't available on Team or Enterprise plans yet. If **Projects** doesn't appear in the sidebar at [claude.ai/code](https://claude.ai/code) or in the Code tab of the [desktop app](/docs/en/desktop.md), the rollout hasn't reached your account, and you can [join the waitlist](https://claude.com/form/projects). [Run agents in parallel](/docs/en/agents.md) lists what you can use in the meantime.

99A project is one ongoing conversation where Claude coordinates a stream of related work for you. You tell it what needs doing and it starts a thread for each task.

1010

11Each thread is usually a [cloud session](/docs/en/claude-code-on-the-web): Claude Code running in the cloud rather than on your machine. When a task needs something only your computer has, you can ask Claude to [run that thread on your computer](#run-a-thread-on-your-own-computer) instead of in the cloud, through [Remote Control](/docs/en/remote-control). Threads run in parallel, and you can check on them and steer them from your phone. Cloud threads keep going after you close your laptop, while a thread on your computer runs only while that computer is awake.

11Each thread is usually a [cloud session](/docs/en/claude-code-on-the-web.md): Claude Code running in the cloud rather than on your machine. When a task needs something only your computer has, you can ask Claude to [run that thread on your computer](#run-a-thread-on-your-own-computer) instead of in the cloud, through [Remote Control](/docs/en/remote-control.md). Threads run in parallel, and you can check on them and steer them from your phone. Cloud threads keep going after you close your laptop, while a thread on your computer runs only while that computer is awake.

1212

1313Without a project, running several sessions means doing the coordinating yourself: you decide what each one works on, repeat the same background at the start of each, and check back to see which finished or needs an answer. With a project, you instead:

1414

from line 27

2727* **A build or migration bigger than a session**: "Build what `docs/spec.md` describes" or "Move the app off the deprecated ORM." The work splits into threads that each take a part, decisions you ask Claude to remember early on reach the later cloud threads, and the spec changes and bugs you find during the build go into the same conversation.

2828* **Work that isn't code**: a folder of contracts or a support-ticket export you keep coming back to with new questions, such as "find the ten most common integration mistakes in these tickets." Upload the documents instead of adding a repository, and threads deliver each write-up as a file on the project's [**Library** tab](#see-what-needs-you-in-overview).

2929

30In any of them you can send a batch of tasks, tell Claude to start without asking you to confirm, and walk away. When you're back, you can find the threads that need you under [**Waiting on you**](#see-what-needs-you-in-overview). You can also ask Claude to put part of the work on a schedule as a [cloud scheduled task](/docs/en/routines). If one of these is your situation, [create a project](#create-a-project).

30In any of them you can send a batch of tasks, tell Claude to start without asking you to confirm, and walk away. When you're back, you can find the threads that need you under [**Waiting on you**](#see-what-needs-you-in-overview). You can also ask Claude to put part of the work on a schedule as a [cloud scheduled task](/docs/en/routines.md). If one of these is your situation, [create a project](#create-a-project).

3131

3232### When something else fits better

3333

3434A project still fits when only some tasks need your machine. Cloud threads work on GitHub repositories and on the files, folders, and Google Drive folders you upload to the project, and for the occasional task that needs a local database or a tool on your computer, you can ask Claude to [run that task's thread on your computer](#run-a-thread-on-your-own-computer). Something other than a project fits better in these cases:

3535

36* **One task that fits in a session**: "Fix the flaky login test." Start a [cloud session](/docs/en/claude-code-on-the-web) yourself.

37* **Work where every task needs your machine**: a local database, a device emulator, or an API behind your VPN. Use a local session, or [agent view](/docs/en/agent-view) to run several at once. If the work only needs local files, upload them to the project instead.

38* **One task that repeats on a schedule with no conversation around it**: "Post a dependency report every Monday." Create a [cloud scheduled task](/docs/en/routines) on its own.

36* **One task that fits in a session**: "Fix the flaky login test." Start a [cloud session](/docs/en/claude-code-on-the-web.md) yourself.

37* **Work where every task needs your machine**: a local database, a device emulator, or an API behind your VPN. Use a local session, or [agent view](/docs/en/agent-view.md) to run several at once. If the work only needs local files, upload them to the project instead.

38* **One task that repeats on a schedule with no conversation around it**: "Post a dependency report every Monday." Create a [cloud scheduled task](/docs/en/routines.md) on its own.

3939* **Several people giving Claude work and steering it together in a Slack channel**: see [Claude Tag](https://claude.com/docs/claude-tag/overview).

4040

4141A project draws on the same plan limits as your other Claude Code sessions and uses them faster. [Usage and cost](#usage-and-cost) covers what draws on your plan and how to keep it down.

from line 74

7474

7575* **Plan**: you're on Pro or Max and **Projects** shows in your sidebar.

7676* **GitHub, if the project will work on code**: your code is on github.com rather than GitHub Enterprise Server, GitLab, or Bitbucket, your connected GitHub account has push access to it, and the Claude GitHub App is installed on it. If you connected GitHub with [`/web-setup`](/docs/en/web-quickstart#connect-from-your-terminal), that token lets your other cloud sessions reach a repository but isn't enough for a project's cloud threads, which need the Claude GitHub App. [Set up GitHub access](#set-up-github-access) has the steps.

77* **Network access, secrets, and tools**: for cloud threads, these come from the project's [cloud environment](#choose-an-environment-for-threads). The default environment already reaches [common package registries](/docs/en/cloud-environments#default-allowed-domains), so check this only if the work needs other domains, a secret, or a tool that isn't preinstalled. If the work needs an MCP server, check that it shows as connected in your [claude.ai connectors](https://claude.ai/customize/connectors).

77* **Network access, secrets, and tools**: for cloud threads, these come from the project's [cloud environment](#choose-an-environment-for-threads). The default environment already reaches [common package registries](/docs/en/cloud-environments.md#default-allowed-domains), so check this only if the work needs other domains, a secret, or a tool that isn't preinstalled. If the work needs an MCP server, check that it shows as connected in your [claude.ai connectors](https://claude.ai/customize/connectors).

7878

7979### Start a new project from scratch

8080

from line 120

120120

121121**1. Connect your GitHub account**

122122

123If you haven't used claude.ai/code before, your first visit walks you through connecting GitHub; see [Connect GitHub](/docs/en/web-quickstart#connect-github). Otherwise use one of the [GitHub authentication options](/docs/en/claude-code-on-the-web#github-authentication-options).

123If you haven't used claude.ai/code before, your first visit walks you through connecting GitHub; see [Connect GitHub](/docs/en/web-quickstart.md#connect-github). Otherwise use one of the [GitHub authentication options](/docs/en/claude-code-on-the-web.md#github-authentication-options).

124124

125125**2. Install the Claude GitHub App on the project's repositories**

126126

from line 165

165165

166166* **Branch**: works on a new branch, started from the repository's default branch.

167167* **Pull request**: opens one when you ask, and can open one on its own for a bug fix or another concrete change.

168* **After it opens**: watches the pull request with [auto-fix](/docs/en/claude-code-on-the-web#auto-fix-pull-requests) turned on, whether or not auto-fix is on for your other cloud sessions. It pushes fixes when CI fails, addresses review comments, and replies in the thread when checks pass and the pull request is ready for you.

168* **After it opens**: watches the pull request with [auto-fix](/docs/en/claude-code-on-the-web.md#auto-fix-pull-requests) turned on, whether or not auto-fix is on for your other cloud sessions. It pushes fixes when CI fails, addresses review comments, and replies in the thread when checks pass and the pull request is ready for you.

169169

170170When a thread has pushed a branch or opened a pull request, its card in the conversation can show a button for the next step:

171171

from line 196

196196

197197* **Library**: the files and folders you added and the files threads produced

198198* **Pull requests**: shown once threads have opened any

199* **Scheduled tasks**: the [cloud scheduled tasks](/docs/en/routines) Claude set up from this project

199* **Scheduled tasks**: the [cloud scheduled tasks](/docs/en/routines.md) Claude set up from this project

200200

201201### Open a thread when you need control

202202

from line 209

209209

210210### Choose models and let Claude manage context

211211

212Set models and effort in **Project settings > General**. A new project runs Opus everywhere, with high [effort](/docs/en/model-config#adjust-effort-level) for threads and low effort for the conversation:

212Set models and effort in **Project settings > General**. A new project runs Opus everywhere, with high [effort](/docs/en/model-config.md#adjust-effort-level) for threads and low effort for the conversation:

213213

214214* **Thread model** and **Thread effort** apply to threads. To use a different model for one task, ask for it in the task; for a thread already running, use that thread's model picker.

215215* **Coordinator model** and **Coordinator effort** apply to Claude in the project conversation.

from line 233

233233

234234### Unblock a thread waiting on approval

235235

236Threads run in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) when the thread's model supports it, so most tool calls run without asking you. When a thread needs your approval, the prompt is inside that thread and the thread waits until you answer it there. Telling Claude in the project conversation to go ahead doesn't reach it.

236Threads run in [auto mode](/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode) when the thread's model supports it, so most tool calls run without asking you. When a thread needs your approval, the prompt is inside that thread and the thread waits until you answer it there. Telling Claude in the project conversation to go ahead doesn't reach it.

237237

238Each approval covers that prompt, or the rest of that thread if you choose the broader option. Cloud threads don't read [permission rules](/docs/en/permissions) from a repository's `.claude/settings.json`, so you rely on auto mode and on the approvals you give inside each thread.

238Each approval covers that prompt, or the rest of that thread if you choose the broader option. Cloud threads don't read [permission rules](/docs/en/permissions.md) from a repository's `.claude/settings.json`, so you rely on auto mode and on the approvals you give inside each thread.

239239

240240### Run a thread on your own computer

241241

242When a task needs something only your computer has, such as a local database, a device emulator, or an API behind your VPN, ask Claude to run the thread for that task on your computer instead of in the cloud. When you ask in the project conversation, the thread is a Claude Code session in a folder on your machine, connected through [Remote Control](/docs/en/remote-control). The project's other threads keep running in the cloud. Compared with a cloud thread, a thread on your computer:

242When a task needs something only your computer has, such as a local database, a device emulator, or an API behind your VPN, ask Claude to run the thread for that task on your computer instead of in the cloud. When you ask in the project conversation, the thread is a Claude Code session in a folder on your machine, connected through [Remote Control](/docs/en/remote-control.md). The project's other threads keep running in the cloud. Compared with a cloud thread, a thread on your computer:

243243

244244* Works with the files, tools, MCP servers, and Claude Code settings on that machine, including its hooks and permission rules, instead of the project's cloud environment

245245* Starts with the project's instructions, but not with its memory files loaded

from line 250

250250On the computer that has the folder the task needs, make it available through Remote Control in one of two ways. Both need Claude Code v2.1.280 or later on that computer.

251251

252252* **In the Claude desktop app**: open **Settings > Claude Code**, turn on **Use this computer from your phone and claude.ai**, and add the folder to the list under that switch. Threads can run on this computer while the app is open.

253* **In a terminal**: run `claude remote-control` in the folder and leave it running. In a git repository, add `--spawn worktree` to give each thread there its own [worktree](/docs/en/worktrees) instead of the folder itself.

254254

255255**2. Ask for the task with Work locally**

256256

from line 260

260260

261261Claude answers with an **Allow Claude to work in a folder on your device** card. Pick the folder if you connected several. Two threads working in one folder at the same time can overwrite each other's changes, so if the folder is a git repository, you can turn on **Worktree** in the folder's options to give this thread its own worktree instead. Then click **Allow once**.

262262

263The thread runs in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), so Claude runs commands and edits files in that folder without asking you each time. If auto mode is unavailable or turned off in that computer's Claude Code, the thread runs without it, and any permission prompt it raises waits for your answer in the thread, as [Unblock a thread waiting on approval](#unblock-a-thread-waiting-on-approval) describes.

263The thread runs in [auto mode](/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode), so Claude runs commands and edits files in that folder without asking you each time. If auto mode is unavailable or turned off in that computer's Claude Code, the thread runs without it, and any permission prompt it raises waits for your answer in the thread, as [Unblock a thread waiting on approval](#unblock-a-thread-waiting-on-approval) describes.

264264

265265While the thread runs, a laptop icon in its header shows whether your computer is connected. Click it to see which folder the thread is using or to turn the connection off. The thread pauses while that computer is asleep, and stops if the desktop app or `claude remote-control` quits. [Lost contact with your folder](#lost-contact-with-your-folder) covers getting it going again. In the desktop app, turn on **Keep this computer awake for Remote Control** under **Settings > Claude Code** to stop the computer from sleeping on its own.

266266

267A project can't run a thread on your computer while [**Require trusted devices**](/docs/en/remote-control#trusted-devices) is on for your account.

267A project can't run a thread on your computer while [**Require trusted devices**](/docs/en/remote-control.md#trusted-devices) is on for your account.

268268

269269## Give a project standing context

270270

from line 276

276276| Project instructions | Text sent to each new thread and to Claude in the project conversation, up to 16,000 characters. [Write project instructions](#write-project-instructions) covers what to put in it | **Project settings > Memory > Project instructions**, or ask Claude to change the instructions |

277277| Repositories, files, and environment | The repositories every cloud thread clones, the folders and files it can read under `/mnt/project-files`, and the cloud environment it runs in | Repositories and environment in **Project settings > Environment**, or ask Claude in the conversation to add a repository to the project. [Files and folders](#add-files-and-folders) from **Add** on the **Library** tab in **Overview** |

278278

279**Project settings > Memory** lists these files under **Auto memory**, because Claude writes them itself as it works in the project. They're separate from the [auto memory](/docs/en/memory) Claude Code keeps on your machine, even though both use a `MEMORY.md` index. Project memory is also separate from the `CLAUDE.md` files in the project's repositories. Each cloud thread still reads those `CLAUDE.md` files from its clone when it starts, so put instructions about a repository in its `CLAUDE.md` and notes about the project in project memory.

279**Project settings > Memory** lists these files under **Auto memory**, because Claude writes them itself as it works in the project. They're separate from the [auto memory](/docs/en/memory.md) Claude Code keeps on your machine, even though both use a `MEMORY.md` index. Project memory is also separate from the `CLAUDE.md` files in the project's repositories. Each cloud thread still reads those `CLAUDE.md` files from its clone when it starts, so put instructions about a repository in its `CLAUDE.md` and notes about the project in project memory.

280280

281281### Write project instructions

282282

from line 329

329329

330330| In each repository | In a cloud thread |

331331| :- | :- |

332| `CLAUDE.md`, `.claude/CLAUDE.md`, and `.claude/rules/` at the repository root | Loaded from every repository when the thread starts. `CLAUDE.md` files in subdirectories and [path-specific rules](/docs/en/memory#path-specific-rules) aren't loaded |

333333| Skills under `.claude/skills/` | Not loaded. Enable the skill for your claude.ai account instead, as [Get skills, plugins, connectors, and tools into threads](#get-skills-plugins-connectors-and-tools-into-threads) describes |

334334| Agents and commands under `.claude/` | Not loaded. To use them, [run the thread on your own computer](#run-a-thread-on-your-own-computer) |

335335| MCP servers in `.mcp.json` | Not loaded. Use the connectors on your claude.ai account instead, as [Get skills, plugins, connectors, and tools into threads](#get-skills-plugins-connectors-and-tools-into-threads) describes |

from line 340

340340

341341### Choose an environment for threads

342342

343Every new cloud thread starts in the project's [cloud environment](/docs/en/cloud-environments). The environment sets which domains threads can reach, which environment variables they have, which network secrets are added to their requests, and what the setup script installs before Claude starts. Cloud threads use a default Anthropic-hosted environment until you pick one in **Project settings > Environment**.

343Every new cloud thread starts in the project's [cloud environment](/docs/en/cloud-environments.md). The environment sets which domains threads can reach, which environment variables they have, which network secrets are added to their requests, and what the setup script installs before Claude starts. Cloud threads use a default Anthropic-hosted environment until you pick one in **Project settings > Environment**.

344344

345If cloud threads need to reach an internal API or a private package registry, or need a token your machine normally holds, change the environment rather than the project: see [Network access](/docs/en/cloud-environments#network-access), [Add network secrets](/docs/en/cloud-environments#add-network-secrets), and [Setup scripts](/docs/en/cloud-environments#setup-scripts).

345If cloud threads need to reach an internal API or a private package registry, or need a token your machine normally holds, change the environment rather than the project: see [Network access](/docs/en/cloud-environments.md#network-access), [Add network secrets](/docs/en/cloud-environments.md#add-network-secrets), and [Setup scripts](/docs/en/cloud-environments.md#setup-scripts).

346346

347347### Get skills, plugins, connectors, and tools into threads

348348

349Cloud threads don't have the skills, MCP servers, plugins, and tools installed only on your machine. A thread that Claude runs on your machine through [Remote Control](/docs/en/remote-control) uses what's installed there. To make each of these available to cloud threads:

349Cloud threads don't have the skills, MCP servers, plugins, and tools installed only on your machine. A thread that Claude runs on your machine through [Remote Control](/docs/en/remote-control.md) uses what's installed there. To make each of these available to cloud threads:

350350

351* Skills: enable them for your claude.ai account, and cloud threads load the [skills you enable there](/docs/en/skills#skills-in-cowork-and-cloud-sessions), apart from [some threads in a self-hosted environment](/docs/en/self-hosted-environments-configuration#how-each-session’s-config-is-assembled). Skills committed to a repository's `.claude/skills/` don't load in cloud threads.

352* Plugins: add them in **Project settings > Plugins**; they load into each new cloud thread. Plugins that a repository declares in its `.claude/settings.json` [don't load in cloud threads](/docs/en/cloud-environments#what-carries-over-from-your-setup).

353* MCP servers: cloud threads get their MCP tools from the connectors on your claude.ai account, which are MCP servers you connect once at [claude.ai/customize/connectors](https://claude.ai/customize/connectors). Every cloud thread can use all of them with no per-project setup. The project conversation itself has no connectors, so send work that needs one as a task for a cloud thread. [How connectors reach Claude Code](/docs/en/mcp#how-connectors-reach-claude-code) lists the rules for cloud sessions and the settings that turn connectors off.

354* Command-line tools and packages: install them in the environment's [setup script](/docs/en/cloud-environments#setup-scripts).

351* Skills: enable them for your claude.ai account, and cloud threads load the [skills you enable there](/docs/en/skills.md#skills-in-cowork-and-cloud-sessions), apart from [some threads in a self-hosted environment](/docs/en/self-hosted-environments-configuration.md#how-each-session’s-config-is-assembled). Skills committed to a repository's `.claude/skills/` don't load in cloud threads.

353* MCP servers: cloud threads get their MCP tools from the connectors on your claude.ai account, which are MCP servers you connect once at [claude.ai/customize/connectors](https://claude.ai/customize/connectors). Every cloud thread can use all of them with no per-project setup. The project conversation itself has no connectors, so send work that needs one as a task for a cloud thread. [How connectors reach Claude Code](/docs/en/mcp.md#how-connectors-reach-claude-code) lists the rules for cloud sessions and the settings that turn connectors off.

354* Command-line tools and packages: install them in the environment's [setup script](/docs/en/cloud-environments.md#setup-scripts).

355355

356356To see which connectors a running cloud thread has at claude.ai/code, open the thread and select **Connectors** from the **+** menu beside its message box. Turning a connector off there removes it from that thread and saves that as your account default, so new threads and claude.ai chats start without it until you turn it back on. A cloud thread picks up a connector you add or reconnect after the next message you send it.

357357

from line 364

364364| Setting | Section | What it controls |

365365| :- | :- | :- |

366366| Name, icon, and goal | General | The project's name and icon in the sidebar, and its one-line goal |

367| Coordinator model and effort | General | The model and [effort level](/docs/en/model-config#adjust-effort-level) for Claude in the project conversation |

367| Coordinator model and effort | General | The model and [effort level](/docs/en/model-config.md#adjust-effort-level) for Claude in the project conversation |

368368| Thread model and effort | General | The model and effort level for threads |

369369| Project instructions | Memory | [Standing rules](#give-a-project-standing-context) every new thread receives |

370370| Project repositories | Environment | The repositories new cloud threads clone |

from line 385

385385

386386## Usage and cost

387387

388Project usage counts against the same [plan limits](/docs/en/errors#youve-hit-your-session-limit) as your other Claude Code sessions, and a project can't spend past those limits on its own.

388Project usage counts against the same [plan limits](/docs/en/errors.md#youve-hit-your-session-limit) as your other Claude Code sessions, and a project can't spend past those limits on its own.

389389

390390A thread that reaches your plan's limit waits and continues on its own when the limit resets, so work you left running starts using your next usage window without a message from you. [A thread hit the usage limit](#usage-limit-reached) covers what you see, how to stop it, and the one case that doesn't wait.

391391

392Work goes past your plan's limits only if you have turned on [usage credits](/docs/en/costs#add-usage-credits-to-your-subscription) for your account. A thread can't turn them on for you.

392Work goes past your plan's limits only if you have turned on [usage credits](/docs/en/costs.md#add-usage-credits-to-your-subscription) for your account. A thread can't turn them on for you.

393393

394394### What draws on your plan

395395

from line 405

405405

406406Open **Usage** in **Project settings** to see token use by thread and by model, and how much went to the project conversation. To bring it down:

407407

408* A follow-up routed to a thread that has been idle longer than the [cache lifetime](/docs/en/prompt-caching#cache-lifetime), an hour on Pro and Max within your plan's limits, re-reads that thread's whole conversation before doing anything. For new work, asking Claude to start a fresh thread can use less than reviving a large old one.

408* A follow-up routed to a thread that has been idle longer than the [cache lifetime](/docs/en/prompt-caching.md#cache-lifetime), an hour on Pro and Max within your plan's limits, re-reads that thread's whole conversation before doing anything. For new work, asking Claude to start a fresh thread can use less than reviving a large old one.

409409* For work that doesn't need the largest model, [choose a smaller model or a lower effort level](#choose-models-and-let-claude-manage-context) for threads, the conversation, or both.

410410* Ask Claude in the project conversation to run fewer threads at a time, or to answer small questions itself instead of starting a thread.

411411

from line 414

414414Several Claude Code features let more than one session work at the same time, so running work in parallel is not by itself what a project is for. In a project, Claude starts and tracks the sessions instead of you, and each one starts from the same instructions. This is how each neighboring feature connects to a project:

415415

416416* **Claude Tag**: [Claude Tag](https://claude.com/docs/claude-tag/overview) is Claude in your team's Slack channels, on Team and Enterprise plans. Anyone in a channel can give it work, everyone in the channel sees and steers it, and it uses connections an admin set up for that channel. A project is yours alone: you're the only one who sends it work or sees its threads, it uses your own GitHub access and connectors, and it's on Pro and Max. [How Claude Tag differs from Cowork and Claude Code](https://claude.com/docs/claude-tag/concepts/how-it-works#how-claude-tag-differs-from-cowork-and-claude-code) has the side-by-side.

417* **Cloud sessions**: every thread is a [cloud session](/docs/en/claude-code-on-the-web) unless you ask Claude to run it on your machine. Either way, Claude starts and tracks it instead of you. A cloud session you started yourself can become a project or feed one through [**Continue as project** or **Move to project**](#start-from-an-existing-cloud-session).

418* **Scheduled tasks**: when you ask for scheduled work in a project, Claude creates a [cloud scheduled task](/docs/en/routines) that runs as threads in that project and appears on its **Scheduled tasks** tab. Scheduled tasks you create outside a project keep working on their own.

419* **Remote Control**: [Remote Control](/docs/en/remote-control) connects claude.ai to a Claude Code session running on your machine. When you ask Claude in a project to run a thread on your computer, the project [uses Remote Control to do it](#run-a-thread-on-your-own-computer).

420* **Local sessions and agent view**: a session you start yourself in your terminal, IDE, or the desktop app's local environment can't be added to a project. [Agent view](/docs/en/agent-view) is a screen for tracking several local sessions side by side, and you still start each one and give it its task yourself.

421* **Worktrees**: a [worktree](/docs/en/worktrees) gives each local session its own working copy of a repository. Cloud threads don't need them: each clones its repositories into its own cloud sandbox and works on its own branch.

422* **Agent teams**: an [agent team](/docs/en/agent-teams) is one session that starts teammate sessions for a single task, on your machine or inside a cloud session, and ends with that task.

423* **Subagents**: a [subagent](/docs/en/sub-agents) runs inside one session, does a side task in its own context window, and returns a summary to that session. A project's threads are whole sessions that Claude starts and that report back to the project conversation, and a thread can still use subagents for its own side tasks.

417* **Cloud sessions**: every thread is a [cloud session](/docs/en/claude-code-on-the-web.md) unless you ask Claude to run it on your machine. Either way, Claude starts and tracks it instead of you. A cloud session you started yourself can become a project or feed one through [**Continue as project** or **Move to project**](#start-from-an-existing-cloud-session).

418* **Scheduled tasks**: when you ask for scheduled work in a project, Claude creates a [cloud scheduled task](/docs/en/routines.md) that runs as threads in that project and appears on its **Scheduled tasks** tab. Scheduled tasks you create outside a project keep working on their own.

419* **Remote Control**: [Remote Control](/docs/en/remote-control.md) connects claude.ai to a Claude Code session running on your machine. When you ask Claude in a project to run a thread on your computer, the project [uses Remote Control to do it](#run-a-thread-on-your-own-computer).

420* **Local sessions and agent view**: a session you start yourself in your terminal, IDE, or the desktop app's local environment can't be added to a project. [Agent view](/docs/en/agent-view.md) is a screen for tracking several local sessions side by side, and you still start each one and give it its task yourself.

421* **Worktrees**: a [worktree](/docs/en/worktrees.md) gives each local session its own working copy of a repository. Cloud threads don't need them: each clones its repositories into its own cloud sandbox and works on its own branch.

422* **Agent teams**: an [agent team](/docs/en/agent-teams.md) is one session that starts teammate sessions for a single task, on your machine or inside a cloud session, and ends with that task.

423* **Subagents**: a [subagent](/docs/en/sub-agents.md) runs inside one session, does a side task in its own context window, and returns a summary to that session. A project's threads are whole sessions that Claude starts and that report back to the project conversation, and a thread can still use subagents for its own side tasks.

424424* **Projects in claude.ai chat and Cowork**: the [earlier Projects experience](https://support.claude.com/en/articles/9517075-what-are-projects), which groups conversations and reference files without threads or a coordinator. Those projects keep working as they do today until the redesigned experience reaches them.

425425

426[Run agents in parallel](/docs/en/agents) compares these options side by side.

426[Run agents in parallel](/docs/en/agents.md) compares these options side by side.

427427

428428## Limitations

429429

430430* Projects are available at claude.ai/code, in the desktop app, and in the Claude mobile app, not in the terminal CLI, the VS Code extension, or the JetBrains plugin, and not through Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry.

431* Project threads are [cloud sessions](/docs/en/claude-code-on-the-web), or sessions on your own machine through [Remote Control](/docs/en/remote-control), with Anthropic as the model provider in both cases. [Security](/docs/en/security) and [Data usage](/docs/en/data-usage) cover how cloud sessions are isolated and what's retained, and [Connection and security](/docs/en/remote-control#connection-and-security) covers how a thread on your machine connects and what's stored.

431* Project threads are [cloud sessions](/docs/en/claude-code-on-the-web.md), or sessions on your own machine through [Remote Control](/docs/en/remote-control.md), with Anthropic as the model provider in both cases. [Security](/docs/en/security.md) and [Data usage](/docs/en/data-usage.md) cover how cloud sessions are isolated and what's retained, and [Connection and security](/docs/en/remote-control.md#connection-and-security) covers how a thread on your machine connects and what's stored.

432432* You can't add a session you started yourself on your machine to a project. A project reaches your machine only by [running a thread there through Remote Control](#run-a-thread-on-your-own-computer), and that section lists what it needs.

433433* A cloud thread's sandbox pauses between turns and resumes when the thread continues. If the sandbox can't be resumed, the thread continues from a fresh clone, so uncommitted changes can be lost. On long tasks, ask Claude to commit and push work in progress.

434434* A project belongs to one user. You can't share a project or its threads with another user, and thread transcripts don't have the share option other cloud sessions have. There are no organization-level controls for projects during the beta.

from line 440

440440

441441### A thread looks stuck

442442

443Claude doesn't post each step a thread takes, so a thread that shows as running with no new messages in the project conversation is usually still working. A new cloud thread also provisions its [cloud environment](/docs/en/cloud-environments) before Claude begins, so its first update takes a moment. Open the thread to read its transcript. If the thread is waiting on a permission prompt, answer it there.

443Claude doesn't post each step a thread takes, so a thread that shows as running with no new messages in the project conversation is usually still working. A new cloud thread also provisions its [cloud environment](/docs/en/cloud-environments.md) before Claude begins, so its first update takes a moment. Open the thread to read its transcript. If the thread is waiting on a permission prompt, answer it there.

444444

445445### Threads guessed or stalled instead of asking

446446

from line 468

468468

469469When a thread or the project conversation reaches your plan's five-hour or weekly limit, it keeps retrying on its own and continues when the limit resets. A thread that a scheduled task started doesn't wait: its turn stops with a limit error, and you send it a message after the limit resets.

470470

471While a thread waits, it shows **Service is busy** with "Claude is still retrying and will continue automatically." You don't need to do anything for the work to continue. If you'd rather it not use your next usage window, click **Stop** in the thread, or [pause the project](#pause-archive-or-delete-a-project) to hold every thread. [Usage limit errors](/docs/en/errors#youve-hit-your-session-limit) explain the limits and when they reset.

471While a thread waits, it shows **Service is busy** with "Claude is still retrying and will continue automatically." You don't need to do anything for the work to continue. If you'd rather it not use your next usage window, click **Stop** in the thread, or [pause the project](#pause-archive-or-delete-a-project) to hold every thread. [Usage limit errors](/docs/en/errors.md#youve-hit-your-session-limit) explain the limits and when they reset.

472472

473473### Additional usage credits are required

474474

475A thread or the project conversation made a request your plan covers only with usage credits, such as one to a model or context size your plan doesn't include, and usage credits aren't turned on for your account. [Add usage credits to your subscription](/docs/en/costs#add-usage-credits-to-your-subscription) covers who can turn them on or buy them on each plan. Once credits are available, send another message to retry.

475A thread or the project conversation made a request your plan covers only with usage credits, such as one to a model or context size your plan doesn't include, and usage credits aren't turned on for your account. [Add usage credits to your subscription](/docs/en/costs.md#add-usage-credits-to-your-subscription) covers who can turn them on or buy them on each plan. Once credits are available, send another message to retry.

476476

477477### Lost contact with your folder

478478

from line 488

488488| "Unable to connect to repository" with "Claude couldn't access your repository or environment" | Your GitHub account needs push access to the repository, and the environment must still exist. Check both in **Project settings > Environment**, then retry |

489489| "Couldn't show the setup proposal" | The app you have open is older than the **Setup recommendations** Claude sent. Refresh the page or restart the desktop app, or ask Claude to propose the setup again |

490490| "The project's environment was removed" | Choose a different environment in **Project settings > Environment**; the change applies to new threads |

491| "Setup script failed" | Click **Edit setup script** on the error, fix the script in the environment, then send another message. [Setup script failed](/docs/en/web-quickstart#setup-script-failed) lists common causes |

492492| "Claude ran out of context on this turn" | The thread filled its context window. If the message says the thread continues in a fresh session, it carries on by itself; otherwise ask Claude in the project conversation to start a new thread for the remaining work |

493493| "Couldn't start in" followed by your folder's name | You allowed a thread to run on your computer, but the session couldn't start there. When a line under the message gives the reason, fix that, then ask Claude to run the task again |

494494| "Claude is out of date on your device" | The computer you picked to run a thread has a Claude Code version older than v2.1.280. Update Claude Code there, or update the desktop app if that's what connects the folder, then ask Claude to run the task again |

from line 496

496496

497497## Related resources

498498

499* [Use Claude Code in the cloud](/docs/en/claude-code-on-the-web): how the cloud sessions behind each cloud thread work, including GitHub access options and auto-fix on pull requests

500* [Configure cloud environments](/docs/en/cloud-environments): change what cloud threads can reach on the network, give them environment variables and network secrets, and install tools with a setup script

501* [Automate work with scheduled tasks](/docs/en/routines): schedules, triggers, and management for scheduled tasks, including the ones Claude creates from a project

502* [Manage multiple agents with agent view](/docs/en/agent-view): run and track several sessions on your own machine when the work needs tools or services only your machine can reach

499* [Use Claude Code in the cloud](/docs/en/claude-code-on-the-web.md): how the cloud sessions behind each cloud thread work, including GitHub access options and auto-fix on pull requests

500* [Configure cloud environments](/docs/en/cloud-environments.md): change what cloud threads can reach on the network, give them environment variables and network secrets, and install tools with a setup script

501* [Automate work with scheduled tasks](/docs/en/routines.md): schedules, triggers, and management for scheduled tasks, including the ones Claude creates from a project

502* [Manage multiple agents with agent view](/docs/en/agent-view.md): run and track several sessions on your own machine when the work needs tools or services only your machine can reach

503503* [Projects redesigned: from folder to conversation](https://claude.com/blog/projects-redesigned): the launch announcement, with the thinking behind making a project a conversation with Claude

504504

claude-security Changed · +20 / -20 lines

from line 4

55The Claude Security plugin runs a multi-agent vulnerability scan of your codebase inside a Claude Code session. A team of Claude agents maps your architecture, builds a threat model, hunts for vulnerabilities, and independently reviews every finding before writing the report. Use the plugin to scan a whole repository or [only a set of changes](#scan-only-your-changes), such as a branch's diff, a pull request's diff, or a single commit, then turn the findings you choose into patches that you review and apply yourself.

7The plugin runs locally in your session, uses [whichever models you have access to in Claude Code](#models-and-providers), and each scan counts toward your [usage](/docs/en/costs). If you want a managed service that monitors your repositories, or want to run scans on [Claude Mythos](https://platform.claude.com/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5), see the [Claude Security](https://claude.com/product/claude-security) product, available on the Enterprise plan.

7The plugin runs locally in your session, uses [whichever models you have access to in Claude Code](#models-and-providers), and each scan counts toward your [usage](/docs/en/costs.md). If you want a managed service that monitors your repositories, or want to run scans on [Claude Mythos](https://platform.claude.com/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5), see the [Claude Security](https://claude.com/product/claude-security) product, available on the Enterprise plan.

9The plugin is also distinct from the review tools already in Claude Code: the [security guidance plugin](/docs/en/security-guidance) reviews code as Claude writes it, [`/security-review`](/docs/en/commands#all-commands) runs a single pass over your branch, and [Code Review](/docs/en/code-review) reviews pull requests. For how the layers stack, see [How the plugin fits with other security tools](#how-the-plugin-fits-with-other-security-tools).

9The plugin is also distinct from the review tools already in Claude Code: the [security guidance plugin](/docs/en/security-guidance.md) reviews code as Claude writes it, [`/security-review`](/docs/en/commands#all-commands) runs a single pass over your branch, and [Code Review](/docs/en/code-review.md) reviews pull requests. For how the layers stack, see [How the plugin fits with other security tools](#how-the-plugin-fits-with-other-security-tools).

1010

1111## Prerequisites

1212

1313To run the plugin, you need:

1414

15* A paid plan, Anthropic API access, or a [third-party provider](#models-and-providers), for the [dynamic workflows](/docs/en/workflows) the scan uses to orchestrate its agents. On Pro, turn them on from the Dynamic workflows row in `/config`.

15* A paid plan, Anthropic API access, or a [third-party provider](#models-and-providers), for the [dynamic workflows](/docs/en/workflows.md) the scan uses to orchestrate its agents. On Pro, turn them on from the Dynamic workflows row in `/config`.

1616* Python 3.9 or later available on your `PATH` as `python3`. Check with `python3 --version`. The plugin's tooling uses only the Python standard library, so nothing is installed.

1717* Linux, macOS, or Windows.

1818* Git, for change scans and for turning findings into patches; those jobs don't support other version control systems. A full scan works in any directory, with or without version control.

from line 21

2121

2222A scan runs inside your Claude Code session. The plugin makes no model calls of its own, so there's no separate API key or provider setting to configure.

2323

24* **Model**: the agents that hunt for vulnerabilities, verify findings, and write and review patches run on [your session's model](/docs/en/sub-agents#choose-a-model). To change it, run [`/model`](/docs/en/model-config#setting-your-model) in your session before you start a scan. A few supporting steps, such as mapping the repository, use the [`sonnet` alias](/docs/en/model-config#model-aliases) instead.

25* **Provider**: scans run on a paid plan, with Anthropic API access, or on a [third-party provider](/docs/en/third-party-integrations) such as [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), or [Microsoft Foundry](/docs/en/microsoft-foundry).

24* **Model**: the agents that hunt for vulnerabilities, verify findings, and write and review patches run on [your session's model](/docs/en/sub-agents.md#choose-a-model). To change it, run [`/model`](/docs/en/model-config#setting-your-model) in your session before you start a scan. A few supporting steps, such as mapping the repository, use the [`sonnet` alias](/docs/en/model-config#model-aliases) instead.

25* **Provider**: scans run on a paid plan, with Anthropic API access, or on a [third-party provider](/docs/en/third-party-integrations.md) such as [Amazon Bedrock](/docs/en/amazon-bedrock.md), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai.md), or [Microsoft Foundry](/docs/en/microsoft-foundry.md).

2626

27On a third-party provider, the `sonnet` alias can resolve to a different version than it does on the Anthropic API. If your account can't use that version, [pin your model versions](/docs/en/model-config#pin-models-for-third-party-deployments), including `ANTHROPIC_DEFAULT_SONNET_MODEL`.

27On a third-party provider, the `sonnet` alias can resolve to a different version than it does on the Anthropic API. If your account can't use that version, [pin your model versions](/docs/en/model-config.md#pin-models-for-third-party-deployments), including `ANTHROPIC_DEFAULT_SONNET_MODEL`.

2828

29[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) re-runs a request that a model's safeguards flag. On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, the request can end with a refusal message instead, depending on [how your deployment is set up](/docs/en/model-config#enable-fallback-on-bedrock-agent-platform-and-foundry).

29[Automatic model fallback](/docs/en/model-config.md#automatic-model-fallback) re-runs a request that a model's safeguards flag. On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, the request can end with a refusal message instead, depending on [how your deployment is set up](/docs/en/model-config.md#enable-fallback-on-bedrock-agent-platform-and-foundry).

3030

3131## Install the plugin

3232

33In the VS Code extension or the desktop app, install it by following [Install a plugin](/docs/en/plugins/install#install-a-plugin). In a terminal, start Claude Code by running `claude`, then enter this at its prompt to install from the [official Anthropic marketplace](/docs/en/plugins/anthropic-marketplaces):

33In the VS Code extension or the desktop app, install it by following [Install a plugin](/docs/en/plugins/install.md#install-a-plugin). In a terminal, start Claude Code by running `claude`, then enter this at its prompt to install from the [official Anthropic marketplace](/docs/en/plugins/anthropic-marketplaces.md):

3434

3535```text theme={null}

3636/plugin install claude-security@claude-plugins-official

3737```

3838

39The command opens the plugin's details, where you choose an [installation scope](/docs/en/plugins/install#install-a-plugin) to start the install.

39The command opens the plugin's details, where you choose an [installation scope](/docs/en/plugins/install.md#install-a-plugin) to start the install.

4040

4141If the install fails, match the message Claude Code reports:

4242

4343* `Marketplace "claude-plugins-official" not found`: add the marketplace with `/plugin marketplace add anthropics/claude-plugins-official`, then retry the install.

44* `Plugin "claude-security" not found in marketplace "claude-plugins-official"`: your local copy of the marketplace catalog may be out of date. Refresh it with `/plugin marketplace update claude-plugins-official`, then retry the install. If the retry prints the same message, see [Plugin not found in marketplace](/docs/en/plugins/troubleshooting#plugin-not-found-in-marketplace).

4545

46Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activate the plugin in your current session.

46Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference.md#reload-plugins) to activate the plugin in your current session.

4747

4848Once the plugin is active, you're ready to [scan and fix your codebase](#scan-and-fix-your-codebase).

4949

from line 79

7979

8080Apply each patch from your shell with `git apply`, in its own pull request. Patches are never applied automatically.

8181

82You don't have to start from the menu: ask for a job directly, as arguments to the command, such as `/claude-security scan my branch`, or in plain language, such as "scan commit abc1234". The plugin works best in [auto mode](/docs/en/permission-modes), which lets the scan's agents proceed without a permission prompt at each step.

82You don't have to start from the menu: ask for a job directly, as arguments to the command, such as `/claude-security scan my branch`, or in plain language, such as "scan commit abc1234". The plugin works best in [auto mode](/docs/en/permission-modes.md), which lets the scan's agents proceed without a permission prompt at each step.

8383

8484### Scan only your changes

8585

from line 122

122122

123123## How the plugin fits with other security tools

124124

125The Claude Security plugin is the on-demand deep-scan layer in a defense-in-depth stack, alongside the [security guidance plugin](/docs/en/security-guidance), [`/security-review`](/docs/en/commands#all-commands), [Code Review](/docs/en/code-review), the managed [Claude Security](https://claude.com/product/claude-security) product, and your existing scanners:

125The Claude Security plugin is the on-demand deep-scan layer in a defense-in-depth stack, alongside the [security guidance plugin](/docs/en/security-guidance.md), [`/security-review`](/docs/en/commands#all-commands), [Code Review](/docs/en/code-review.md), the managed [Claude Security](https://claude.com/product/claude-security) product, and your existing scanners:

126126

127127| Stage | Tool | What it covers |

128128| :- | :- | :- |

129| In session | [Security guidance plugin](/docs/en/security-guidance) | Common vulnerabilities in code Claude writes, fixed in the same session |

129| In session | [Security guidance plugin](/docs/en/security-guidance.md) | Common vulnerabilities in code Claude writes, fixed in the same session |

130130| On demand, single pass | [`/security-review`](/docs/en/commands#all-commands) | One-time security pass on the current branch |

131131| On demand, deep scan | Claude Security plugin | Multi-agent scan of a repository or diff, with independently reviewed findings and patches |

132| On pull request | [Code Review](/docs/en/code-review), Team and Enterprise plans | Multi-agent correctness and security review with full codebase context |

132| On pull request | [Code Review](/docs/en/code-review.md), Team and Enterprise plans | Multi-agent correctness and security review with full codebase context |

133133| Managed | [Claude Security](https://claude.com/product/claude-security), Enterprise plan | Hosted scanning that monitors connected repositories |

134134| In CI | Your existing static analysis and dependency scanners | Language-specific rules, supply-chain checks, and policy enforcement |

135135

from line 139

139139

140140**The `/claude-security` menu opens with a Python warning.** The plugin needs `python3` 3.9 or later on your `PATH`. When it can't find `python3` at all, the menu warns that Claude Security won't work until one is installed; when the first `python3` on your `PATH` is older, the warning names the version it found. Install Python 3, or put a newer `python3` first on your `PATH`, then start a new session.

141141

142**You may see a "safeguards flagged this message" notice when scanning on a Fable model.** The message names the model you're running. Fable's cybersecurity safety classifiers flag certain requests, and Claude Code re-runs a flagged request on an Opus model through [automatic model fallback](/docs/en/model-config#automatic-model-fallback). This is expected. When the request re-runs, the scan should still complete successfully.

142**You may see a "safeguards flagged this message" notice when scanning on a Fable model.** The message names the model you're running. Fable's cybersecurity safety classifiers flag certain requests, and Claude Code re-runs a flagged request on an Opus model through [automatic model fallback](/docs/en/model-config.md#automatic-model-fallback). This is expected. When the request re-runs, the scan should still complete successfully.

143143

144144## Related resources

145145

146146To go deeper on the pieces this page touches:

147147

148* [Security guidance plugin](/docs/en/security-guidance): catch issues in code as Claude writes it, in the same session

149* [Code Review](/docs/en/code-review): set up the PR-time multi-agent review

148* [Security guidance plugin](/docs/en/security-guidance.md): catch issues in code as Claude writes it, in the same session

149* [Code Review](/docs/en/code-review.md): set up the PR-time multi-agent review

150150* [Claude Security](https://claude.com/product/claude-security): the managed service that monitors connected repositories

151* [Claude Code security](/docs/en/security): how Claude Code approaches trust, permissions, and safeguards

152* [Install and manage plugins](/docs/en/plugins/install): find and install other plugins from the official marketplace

151* [Claude Code security](/docs/en/security.md): how Claude Code approaches trust, permissions, and safeguards

152* [Install and manage plugins](/docs/en/plugins/install.md): find and install other plugins from the official marketplace

153153

claude-tag Changed · +4 / -4 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 1

1<!DOCTYPE html><html lang="en" class="inter_1d81deff-module__CYM0aG__variable papermono_89c757f2-module__6aS5zq__variable dark" data-banner-state="visible" data-assistant-state="closed" data-page-mode="none" data-current-path="/"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover"/><link rel="preload" href="/docs/_next/static/media/83afe278b6a6bb3c.p.3a6ba036.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" href="/docs/_next/static/media/PaperMono_Variable.p.4fb029ee.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" href="/docs/_next/static/media/f67ad414ed34149c.p.84166d94.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/light.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=e870c19cb781d8a7c7b7d19de53b0a10"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/dark.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=80cc0b06d8fd9aeefec8acb226de6866"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/logo/clay-spark.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=032101c39ca3b1af9f72fc4af8e60d12"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/illustrations/Hand-Key.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=1b7a9675728f971bc7a4663c7f1ea599"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/illustrations/Hand-NodePair.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=c64df4c6d27a6da752aa32c9e0622781"/><link rel="stylesheet" href="/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" data-precedence="next"/><link rel="stylesheet" href="/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" data-precedence="next"/><style data-precedence="base-ui:low" data-href="base-ui-disable-scrollbar">.base-ui-disable-scrollbar{scrollbar-width:none}.base-ui-disable-scrollbar::-webkit-scrollbar{display:none}</style><link rel="preload" as="script" fetchPriority="low" href="/docs/_next/static/chunks/3fcb76f539c93820.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq"/><script src="/docs/_next/static/chunks/44795504c795ca32.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/f35b424bcd8059ef.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/896d8c6b2a391d2d.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/a2beb89300e5de0c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/turbopack-e0f35481e9718856.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/a2a714cf193b029a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/2ef7b8b76773d1cd.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/94d2303c1cf0e7a6.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/c3bc6629a7fa7c34.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/524bce83f7b2f674.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/1347c67505f8d6ff.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/4fb629d8ce053f08.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/1ab82a2e4905d2c6.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/e7049fc815953dcd.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/f944c986e78b445f.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><script src="/docs/_next/static/chunks/bb93bffa4794797f.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" async=""></script><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="anonymous"/><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="anonymous"/><title>Work with Claude Tag - Claude.ai Documentation</title><meta name="description" content="Claude Tag puts Claude in your Slack channels with admin-governed access. See what to hand it, how setup works, and where to start as an admin or end user."/><meta name="application-name" content="Claude.ai Documentation"/><meta name="generator" content="Mintlify"/><meta name="msapplication-config" content="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/browserconfig.xml"/><meta name="apple-mobile-web-app-title" content="Claude.ai Documentation"/><meta name="msapplication-TileColor" content="#0E0E0E"/><link rel="canonical" href="https://claude.com/docs/claude-tag/overview"/><link rel="alternate" type="application/xml" href="/docs/sitemap.xml"/><link rel="alternate" type="text/markdown" href="/docs/claude-tag/overview.md"/><meta property="og:title" content="Work with Claude Tag - Claude.ai Documentation"/><meta property="og:description" content="Claude Tag puts Claude in your Slack channels with admin-governed access. See what to hand it, how setup works, and where to start as an admin or end user."/><meta property="og:url" content="https://claude.com/docs/claude-tag/overview"/><meta property="og:site_name" content="Claude.ai Documentation"/><meta property="og:image" content="https://claude-ai.mintlify.app/_mintlify/api/og/v2?division=+&title=Work+with+Claude+Tag&description=Claude+Tag+puts+Claude+in+your+Slack+channels+with+admin-governed+access.+See+what+to+hand+it%2C+how+setup+works%2C+and+where+to+start+as+an+admin+or+end+user.&theme=25fa76e0782ecdcbf2e9c357&signature=997ebf3faebd938bda7ef71f6e8f0a913e72af016dbe5aba123cbe1493f4ea79"/><meta property="og:image:width" content="1200"/><meta property="og:image:height" content="630"/><meta property="og:type" content="website"/><meta name="twitter:card" content="summary_large_image"/><meta name="twitter:title" content="Work with Claude Tag - Claude.ai Documentation"/><meta name="twitter:description" content="Claude Tag puts Claude in your Slack channels with admin-governed access. See what to hand it, how setup works, and where to start as an admin or end user."/><meta name="twitter:image" content="https://claude-ai.mintlify.app/_mintlify/api/og/v2?division=+&title=Work+with+Claude+Tag&description=Claude+Tag+puts+Claude+in+your+Slack+channels+with+admin-governed+access.+See+what+to+hand+it%2C+how+setup+works%2C+and+where+to+start+as+an+admin+or+end+user.&theme=25fa76e0782ecdcbf2e9c357&signature=997ebf3faebd938bda7ef71f6e8f0a913e72af016dbe5aba123cbe1493f4ea79"/><meta name="twitter:image:width" content="1200"/><meta name="twitter:image:height" content="630"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/android-chrome-192x192.png" type="image/png" sizes="192x192" media="(prefers-color-scheme: light)"/><link rel="apple-touch-icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/apple-touch-icon.png" type="image/png" sizes="180x180"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/favicon-16x16.png" type="image/png" sizes="16x16" media="(prefers-color-scheme: light)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/favicon-32x32.png" type="image/png" sizes="32x32" media="(prefers-color-scheme: light)"/><link rel="shortcut icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/favicon.ico" type="image/x-icon" media="(prefers-color-scheme: light)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/android-chrome-192x192.png" type="image/png" sizes="192x192" media="(prefers-color-scheme: dark)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/favicon-16x16.png" type="image/png" sizes="16x16" media="(prefers-color-scheme: dark)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/favicon-32x32.png" type="image/png" sizes="32x32" media="(prefers-color-scheme: dark)"/><link rel="shortcut icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/favicon.ico" type="image/x-icon" media="(prefers-color-scheme: dark)"/><script type="text/javascript">!function(){var b="/docs";

1<!DOCTYPE html><html lang="en" class="inter_1d81deff-module__CYM0aG__variable papermono_89c757f2-module__6aS5zq__variable dark" data-banner-state="visible" data-assistant-state="closed" data-page-mode="none" data-current-path="/"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover"/><link rel="preload" href="/docs/_next/static/media/83afe278b6a6bb3c.p.3a6ba036.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" href="/docs/_next/static/media/PaperMono_Variable.p.4fb029ee.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" href="/docs/_next/static/media/f67ad414ed34149c.p.84166d94.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/light.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=e870c19cb781d8a7c7b7d19de53b0a10"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/dark.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=80cc0b06d8fd9aeefec8acb226de6866"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/logo/clay-spark.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=032101c39ca3b1af9f72fc4af8e60d12"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/illustrations/Hand-Key.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=1b7a9675728f971bc7a4663c7f1ea599"/><link rel="preload" as="image" href="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/illustrations/Hand-NodePair.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=c64df4c6d27a6da752aa32c9e0622781"/><link rel="stylesheet" href="/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" data-precedence="next"/><link rel="stylesheet" href="/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" data-precedence="next"/><style data-precedence="base-ui:low" data-href="base-ui-disable-scrollbar">.base-ui-disable-scrollbar{scrollbar-width:none}.base-ui-disable-scrollbar::-webkit-scrollbar{display:none}</style><link rel="preload" as="script" fetchPriority="low" href="/docs/_next/static/chunks/3fcb76f539c93820.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp"/><script src="/docs/_next/static/chunks/44795504c795ca32.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/fc0d9bde4242238c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/896d8c6b2a391d2d.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/282644fd76c5ad9f.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/turbopack-0b4a039cd6040e34.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/96f05c525d790774.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/c45fc5c3fa69ca32.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/94a43ec1201b91d0.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/524bce83f7b2f674.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/1347c67505f8d6ff.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/91cc018f0b521f3f.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/1ab82a2e4905d2c6.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/e7049fc815953dcd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/f944c986e78b445f.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><script src="/docs/_next/static/chunks/3a59f568b026e98e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" async=""></script><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="anonymous"/><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="anonymous"/><title>Work with Claude Tag - Claude.ai Documentation</title><meta name="description" content="Claude Tag puts Claude in your Slack channels with admin-governed access. See what to hand it, how setup works, and where to start as an admin or end user."/><meta name="application-name" content="Claude.ai Documentation"/><meta name="generator" content="Mintlify"/><meta name="msapplication-config" content="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/browserconfig.xml"/><meta name="apple-mobile-web-app-title" content="Claude.ai Documentation"/><meta name="msapplication-TileColor" content="#0E0E0E"/><link rel="canonical" href="https://claude.com/docs/claude-tag/overview"/><link rel="alternate" type="application/xml" href="/docs/sitemap.xml"/><link rel="alternate" type="text/markdown" href="/docs/claude-tag/overview.md"/><meta property="og:title" content="Work with Claude Tag - Claude.ai Documentation"/><meta property="og:description" content="Claude Tag puts Claude in your Slack channels with admin-governed access. See what to hand it, how setup works, and where to start as an admin or end user."/><meta property="og:url" content="https://claude.com/docs/claude-tag/overview"/><meta property="og:site_name" content="Claude.ai Documentation"/><meta property="og:image" content="https://claude-ai.mintlify.app/_mintlify/api/og/v2?division=+&title=Work+with+Claude+Tag&description=Claude+Tag+puts+Claude+in+your+Slack+channels+with+admin-governed+access.+See+what+to+hand+it%2C+how+setup+works%2C+and+where+to+start+as+an+admin+or+end+user.&theme=25fa76e0782ecdcbf2e9c357&signature=997ebf3faebd938bda7ef71f6e8f0a913e72af016dbe5aba123cbe1493f4ea79"/><meta property="og:image:width" content="1200"/><meta property="og:image:height" content="630"/><meta property="og:type" content="website"/><meta name="twitter:card" content="summary_large_image"/><meta name="twitter:title" content="Work with Claude Tag - Claude.ai Documentation"/><meta name="twitter:description" content="Claude Tag puts Claude in your Slack channels with admin-governed access. See what to hand it, how setup works, and where to start as an admin or end user."/><meta name="twitter:image" content="https://claude-ai.mintlify.app/_mintlify/api/og/v2?division=+&title=Work+with+Claude+Tag&description=Claude+Tag+puts+Claude+in+your+Slack+channels+with+admin-governed+access.+See+what+to+hand+it%2C+how+setup+works%2C+and+where+to+start+as+an+admin+or+end+user.&theme=25fa76e0782ecdcbf2e9c357&signature=997ebf3faebd938bda7ef71f6e8f0a913e72af016dbe5aba123cbe1493f4ea79"/><meta name="twitter:image:width" content="1200"/><meta name="twitter:image:height" content="630"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/android-chrome-192x192.png" type="image/png" sizes="192x192" media="(prefers-color-scheme: light)"/><link rel="apple-touch-icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/apple-touch-icon.png" type="image/png" sizes="180x180"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/favicon-16x16.png" type="image/png" sizes="16x16" media="(prefers-color-scheme: light)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/favicon-32x32.png" type="image/png" sizes="32x32" media="(prefers-color-scheme: light)"/><link rel="shortcut icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon/favicon.ico" type="image/x-icon" media="(prefers-color-scheme: light)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/android-chrome-192x192.png" type="image/png" sizes="192x192" media="(prefers-color-scheme: dark)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/favicon-16x16.png" type="image/png" sizes="16x16" media="(prefers-color-scheme: dark)"/><link rel="icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/favicon-32x32.png" type="image/png" sizes="32x32" media="(prefers-color-scheme: dark)"/><link rel="shortcut icon" href="/docs/_mintlify/favicons/claude-ai/zHw4o4W7dZma2XXV/_generated/favicon-dark/favicon.ico" type="image/x-icon" media="(prefers-color-scheme: dark)"/><script type="text/javascript">!function(){var b="/docs";

22function a(p){if(p==null)return"/";p=""+p;if(""===p)return"/";return"/"===p.charAt(0)?p:"/"+p}

33function u(p){if(p==null)return p;p=""+p;if(!p||p.charAt(p.length-1)==="/")return p.slice(0,-1);return p}

44function i(p){if(p==null)return p;p=""+p;if(6<=p.length&&p.substring(p.length-6)==="/index")return p.substring(0,p.length-6);if("index"===p)return"";return p}

from line 57

5757})();</script><script type="text/javascript">(function(a,b){try{let c=document.querySelector("div#banner")?.innerText;if(c){for(let d=0;d<localStorage.length;d++){let e=localStorage.key(d);if(e?.endsWith(a)&&localStorage.getItem(e)===c)return void document.documentElement.setAttribute(b,"hidden")}document.documentElement.setAttribute(b,"visible");return}for(let c=0;c<localStorage.length;c++){let d=localStorage.key(c);if(d?.endsWith(a)&&localStorage.getItem(d))return void document.documentElement.setAttribute(b,"hidden")}document.documentElement.setAttribute(b,"visible")}catch(a){document.documentElement.setAttribute(b,"hidden")}})(

5858 "bannerDismissed",

5959 "data-banner-state",

60)</script><script src="/docs/_next/static/chunks/a6dad97d9634a72d.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" noModule=""></script></head><body class="antialiased"><div hidden=""></div><script>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem("isDarkMode")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'&&p!=='dark'&&p!=='system')p="system"}var r=p==='system'?(matchMedia("(prefers-color-scheme: dark)").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute("data-theme-preference",p)})();</script><blockquote class="sr-only" data-agent-docs-index="true" aria-hidden="true"><h2>Documentation Index</h2><p>Fetch the complete documentation index at: <a href="/docs/llms.txt" tabindex="-1">/docs/llms.txt</a></p><p>Use this file to discover all available pages before exploring further.</p></blockquote><style>:root{--banner-height:0px!important}</style><script id="_mintlify-banner-script">(function i(a,b,c,d,e){try{let f,g,h=[];try{h=window.location.pathname.split("/").filter(a=>""!==a&&"global"!==a).slice(0,2)}catch{h=[]}let i=h.map(a=>c.find(b=>b.toLowerCase()===a.toLowerCase())).find(a=>void 0!==a),j=[];for(let c of(i?j.push(i):j.push(b),j.push("global"),j)){if(!c)continue;let b=a[c];if(b?.content){f=b.content,g=c;break}}if(!f)return void document.documentElement.setAttribute(d,"hidden");let k=!0,l=0;for(;l<localStorage.length;){let a=localStorage.key(l);if(l++,!a?.endsWith(e))continue;let b=localStorage.getItem(a);if(b&&b===f){k=!1;break}g&&(a.startsWith(`lang:${g}_`)||!a.startsWith("lang:"))&&(localStorage.removeItem(a),l--)}document.documentElement.setAttribute(d,k?"visible":"hidden")}catch(a){console.error(a),document.documentElement.setAttribute(d,"hidden")}})(

60)</script><script src="/docs/_next/static/chunks/a6dad97d9634a72d.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" noModule=""></script></head><body class="antialiased"><div hidden=""></div><script>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem("isDarkMode")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'&&p!=='dark'&&p!=='system')p="system"}var r=p==='system'?(matchMedia("(prefers-color-scheme: dark)").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute("data-theme-preference",p)})();</script><blockquote class="sr-only" data-agent-docs-index="true" aria-hidden="true"><h2>Documentation Index</h2><p>Fetch the complete documentation index at: <a href="/docs/llms.txt" tabindex="-1">/docs/llms.txt</a></p><p>Use this file to discover all available pages before exploring further.</p></blockquote><style>:root{--banner-height:0px!important}</style><script id="_mintlify-banner-script">(function i(a,b,c,d,e){try{let f,g,h=[];try{h=window.location.pathname.split("/").filter(a=>""!==a&&"global"!==a).slice(0,2)}catch{h=[]}let i=h.map(a=>c.find(b=>b.toLowerCase()===a.toLowerCase())).find(a=>void 0!==a),j=[];for(let c of(i?j.push(i):j.push(b),j.push("global"),j)){if(!c)continue;let b=a[c];if(b?.content){f=b.content,g=c;break}}if(!f)return void document.documentElement.setAttribute(d,"hidden");let k=!0,l=0;for(;l<localStorage.length;){let a=localStorage.key(l);if(l++,!a?.endsWith(e))continue;let b=localStorage.getItem(a);if(b&&b===f){k=!1;break}g&&(a.startsWith(`lang:${g}_`)||!a.startsWith("lang:"))&&(localStorage.removeItem(a),l--)}document.documentElement.setAttribute(d,k?"visible":"hidden")}catch(a){console.error(a),document.documentElement.setAttribute(d,"hidden")}})(

6161 {},

6262 "en",

6363 [],

from line 3148

31483148<span data-as="p"><a class="link" href="/docs/claude-tag/admins/setup-overview">Set up Claude Tag</a> walks through setup and connecting tools, with what to have ready, what each choice means, and how to verify Claude Tag works once you launch.</span>

31493149<div class="tm-strip"><div class="tm-strip-head"><p class="tm-strip-title">Security review</p><a class="link tm-strip-all" href="/docs/claude-tag/concepts/security-and-data">Security and data handling</a></div><p>The security model, what admins can and can’t restrict, audit trails, and network requirements.</p></div>

31503150<h2 class="flex whitespace-pre-wrap group font-semibold" id="where-to-start-with-claude-tag"><div class="absolute" tabindex="-1"><a href="#where-to-start-with-claude-tag" class="-ml-10 flex items-center opacity-0 border-0 group-hover:opacity-100 focus:opacity-100 focus:outline-0 group/link" aria-label="Navigate to header"><div class="size-6 rounded-md flex items-center justify-center shadow-xs text-gray-400 dark:text-white/50 dark:bg-background-dark dark:brightness-[1.35] dark:ring-1 dark:hover:brightness-150 bg-white ring-1 ring-gray-400/30 dark:ring-gray-700/25 hover:ring-gray-400/60 dark:hover:ring-white/20 group-focus/link:border-2 group-focus/link:border-primary dark:group-focus/link:border-primary-light"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-3 shrink-0"><path d="M8.50001 6.827C8.14801 6.995 7.81801 7.225 7.52701 7.517L7.51701 7.527C6.13601 8.908 6.13601 11.146 7.51701 12.527L9.69201 14.702C11.073 16.083 13.311 16.083 14.692 14.702L14.702 14.692C16.083 13.311 16.083 11.073 14.702 9.692L13.771 8.761" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M9.50002 11.173C9.85202 11.005 10.182 10.775 10.473 10.483L10.483 10.473C11.864 9.092 11.864 6.854 10.483 5.473L8.30802 3.298C6.92702 1.917 4.68902 1.917 3.30802 3.298L3.29802 3.308C1.91702 4.689 1.91702 6.927 3.29802 8.308L4.22902 9.239" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div></a></div><span class="cursor-pointer">Where to start with Claude Tag</span></h2>

3151<div class="columns prose dark:prose-invert grid max-w-none gap-4 sm:grid-cols-[repeat(var(--cols),minmax(0,1fr))] @2xl/columns-container:grid-cols-[repeat(var(--cols),minmax(0,1fr))] @[0px]/columns-container:grid-cols-1 card-group dark:prose-dark gap-y-0 sm:grid-cols-[repeat(var(--cols),minmax(0,1fr))]!" style="--cols:2"><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_675dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/gear.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/gear.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_675dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">Set up Claude Tag</h2><div id="_R_675dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">Admins: pair your Slack workspace and launch</span></div></div></div></div><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_a75dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/paper-plane.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/paper-plane.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_a75dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">Hand Claude Tag your first task</h2><div id="_R_a75dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">It’s already in your channel: send your first message</span></div></div></div></div><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_e75dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/diagram-project.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/diagram-project.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_e75dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">How Claude Tag works</h2><div id="_R_e75dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">The session model, what it can read, and how memory follows places</span></div></div></div></div><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_i75dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/list.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/list.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_i75dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">Use case library</h2><div id="_R_i75dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">Prompts to paste, by team and connection</span></div></div></div></div></div></div><div class="feedback-toolbar pb-16 w-full flex flex-col gap-y-8"><div class="flex flex-row flex-wrap gap-4 items-center justify-between"><p class="inline-block text-sm text-gray-600 dark:text-gray-400 whitespace-nowrap">Was this page helpful?</p><div class="flex flex-wrap grow gap-3 items-center justify-end"><div class="flex gap-3 items-center"><button id="feedback-thumbs-up" class="px-3.5 py-2 flex flex-row gap-3 items-center border-standard rounded-xl text-gray-600 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300 bg-white/50 dark:bg-codeblock/50 hover:border-gray-500 hover:dark:border-gray-500 focus-visible:outline-2 focus-visible:-outline-offset-2 focus-visible:outline-primary dark:focus-visible:outline-primary-light"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-4 shrink-0 text-current"><path d="M5.25 7.494C5.25 7.014 5.423 6.55 5.736 6.187L10 1.25C10.854 1.677 11.25 2.678 10.92 3.574L9.75 6.75H14.152C15.465 6.75 16.421 7.993 16.085 9.262L14.894 13.762C14.662 14.639 13.868 15.25 12.961 15.25H7.25C6.145 15.25 5.25 14.355 5.25 13.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.25 6.75H2.75C2.19772 6.75 1.75 7.19772 1.75 7.75V14.25C1.75 14.8023 2.19772 15.25 2.75 15.25H4.25C4.80228 15.25 5.25 14.8023 5.25 14.25V7.75C5.25 7.19772 4.80228 6.75 4.25 6.75Z" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg><small class="text-sm font-normal leading-4">Yes</small></button><button id="feedback-thumbs-down" class="px-3.5 py-2 flex flex-row gap-3 items-center border-standard rounded-xl text-gray-600 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300 bg-white/50 dark:bg-codeblock/50 hover:border-gray-500 hover:dark:border-gray-500 focus-visible:outline-2 focus-visible:-outline-offset-2 focus-visible:outline-primary dark:focus-visible:outline-primary-light"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-4 shrink-0 text-current"><path d="M5.25 10.506C5.25 10.986 5.423 11.45 5.736 11.813L10 16.75C10.854 16.323 11.25 15.322 10.92 14.426L9.75 11.25H14.152C15.465 11.25 16.421 10.007 16.085 8.738L14.894 4.238C14.662 3.361 13.868 2.75 12.961 2.75H7.25C6.145 2.75 5.25 3.645 5.25 4.75" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.25 2.75H2.75C2.19772 2.75 1.75 3.19772 1.75 3.75V10.25C1.75 10.8023 2.19772 11.25 2.75 11.25H4.25C4.80228 11.25 5.25 10.8023 5.25 10.25V3.75C5.25 3.19772 4.80228 2.75 4.25 2.75Z" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg><small class="text-sm font-normal leading-4">No</small></button></div><div class="flex gap-3"></div></div></div></div><nav id="pagination" aria-label="Pagination" class="px-0.5 flex items-center gap-6 text-sm font-semibold text-gray-700 dark:text-gray-200"><a rel="next" aria-label="Next: How Claude Tag works" data-component-part="pagination-next" class="group flex items-center min-w-0 focus-visible:outline-2 focus-visible:outline-offset-2 focus-visible:outline-primary dark:focus-visible:outline-primary-light gap-3 rounded-sm ml-auto pagination-next" href="/docs/claude-tag/concepts/how-it-works"><div class="truncate group-hover:text-gray-900 dark:group-hover:text-white" data-component-part="pagination-title">How Claude Tag works</div><svg viewBox="0 0 3 6" aria-hidden="true" data-component-part="pagination-chevron" class="h-1.5 shrink-0 stroke-gray-400 overflow-visible group-hover:stroke-gray-600 dark:group-hover:stroke-gray-300 rotate-180"><path d="M3 0L0 3L3 6" fill="none" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"></path></svg></a></nav><div data-assistant-bar="" class="left-0 right-0 sticky bottom-0 w-full overflow-hidden z-20 pointer-events-none print:hidden"><div class="chat-assistant-floating-input w-full group/assistant-bar relative translate-y-[100px] opacity-0"><div class="relative pb-4 sm:pb-6 max-w-2xl mx-auto"><div class="flex flex-col w-full rounded-2xl pointer-events-auto bg-background-light dark:bg-background-dark border border-gray-200 dark:border-white/10 focus-within:border-primary dark:focus-within:border-primary-light transition-colors"><div class="relative flex items-end"><textarea id="chat-assistant-textarea" aria-label="Ask a question..." autoComplete="off" placeholder="Ask a question..." class="chat-assistant-input w-full bg-transparent border-0 peer/input text-gray-900 dark:text-gray-100 placeholder-gray-600 dark:placeholder-gray-300 outline-hidden! focus:outline-hidden! focus:ring-0 py-2.5 pl-3.5 pr-10 font-bodyWeight text-sm" style="resize:none"></textarea><button class="chat-assistant-send-button flex justify-center items-center rounded-full p-1 size-6 bg-primary/30 dark:bg-primary-dark/30 absolute right-2.5 bottom-2" aria-label="Send message" disabled=""><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-2.5 shrink-0 text-white dark:text-white"><path d="M9.0 1.5754L8.9999 16.4171" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.2563 8.319L8.9999 1.5754L15.7435 8.3191" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button></div></div></div></div></div></div></div></main></div><footer id="footer" class="advanced-footer flex flex-col items-center mx-auto border-t border-gray-100 dark:border-gray-800/50 peer-[.is-custom]:hidden! peer-[.is-custom]:sm:hidden! peer-[.is-custom]:md:hidden! peer-[.is-custom]:lg:hidden! peer-[.is-custom]:xl:hidden!"><div class="flex w-full flex-col gap-12 justify-between px-8 py-16 md:py-20 lg:py-28 max-w-246 z-20"><div class="flex flex-col md:flex-row gap-8 justify-between min-h-19"><div class="flex md:flex-col justify-between items-center md:items-start min-w-16 md:min-w-20 lg:min-w-48 md:gap-y-24"><a class="select-none" style="-webkit-touch-callout:none" href="/docs"><span class="sr-only">Claude.ai Documentation home page</span><img class="nav-logo w-auto relative object-contain shrink-0 block dark:hidden max-w-48 h-[26px]" src="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/light.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=e870c19cb781d8a7c7b7d19de53b0a10" alt="light logo"/><img class="nav-logo w-auto relative object-contain shrink-0 hidden dark:block max-w-48 h-[26px]" src="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/dark.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=80cc0b06d8fd9aeefec8acb226de6866" alt="dark logo"/></a><div class="gap-4 min-w-[140px] max-w-[492px] flex-wrap h-fit flex justify-end md:justify-start"><a href="https://x.com/AnthropicAI" target="_blank" rel="noopener noreferrer" class="h-fit"><span class="sr-only">x</span><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! w-5 h-5 bg-gray-500 dark:bg-gray-600 hover:bg-gray-600 dark:hover:bg-gray-500" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/x-twitter.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/x-twitter.svg");mask-repeat:no-repeat;mask-position:center"></svg></a><a href="https://www.linkedin.com/company/anthropicresearch" target="_blank" rel="noopener noreferrer" class="h-fit"><span class="sr-only">linkedin</span><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! w-5 h-5 bg-gray-500 dark:bg-gray-600 hover:bg-gray-600 dark:hover:bg-gray-500" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/linkedin.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/linkedin.svg");mask-repeat:no-repeat;mask-position:center"></svg></a></div></div><div class="flex flex-col sm:grid max-md:grid-cols-2! gap-8 flex-1" style="grid-template-columns:repeat(4, minmax(0, 1fr))"><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Company</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/company" target="_blank" rel="noreferrer">Anthropic</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/careers" target="_blank" rel="noreferrer">Careers</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/economic-futures" target="_blank" rel="noreferrer">Economic Futures</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/research" target="_blank" rel="noreferrer">Research</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/news" target="_blank" rel="noreferrer">News</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://trust.anthropic.com/" target="_blank" rel="noreferrer">Trust center</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/transparency" target="_blank" rel="noreferrer">Transparency</a></div></div><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Help and security</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/supported-countries" target="_blank" rel="noreferrer">Availability</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://status.anthropic.com/" target="_blank" rel="noreferrer">Status</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://support.claude.com/" target="_blank" rel="noreferrer">Support center</a></div></div><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Learn</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://academy.claude.com/" target="_blank" rel="noreferrer">Courses</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/partners/mcp" target="_blank" rel="noreferrer">MCP connectors</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.claude.com/customers" target="_blank" rel="noreferrer">Customer stories</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/engineering" target="_blank" rel="noreferrer">Engineering blog</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/events" target="_blank" rel="noreferrer">Events</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/partners/powered-by-claude" target="_blank" rel="noreferrer">Powered by Claude</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/partners/services" target="_blank" rel="noreferrer">Service partners</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/programs/startups" target="_blank" rel="noreferrer">Startups program</a></div></div><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Terms and policies</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/privacy" target="_blank" rel="noreferrer">Privacy policy</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/responsible-disclosure-policy" target="_blank" rel="noreferrer">Disclosure policy</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/aup" target="_blank" rel="noreferrer">Usage policy</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/commercial-terms" target="_blank" rel="noreferrer">Commercial terms</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/consumer-terms" target="_blank" rel="noreferrer">Consumer terms</a></div></div></div></div></div></footer></div><template id="B:0"></template></div></div><script>requestAnimationFrame(function(){$RT=performance.now()});</script><script src="/docs/_next/static/chunks/3fcb76f539c93820.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq" id="_R_" async=""></script><div hidden id="S:0"><div data-assistant-sheet-container="" class="sticky shrink-0 z-22 bg-background-light dark:bg-background-dark mt-(--banner-height,0px) top-(--banner-height,0px) h-[calc(100vh-var(--banner-height,0px))] max-lg:hidden print:hidden" style="width:var(--assistant-sheet-width, 0px);overflow:hidden"><div class="absolute left-0 top-0 bottom-0 w-px z-10 cursor-col-resize after:content-[""] after:absolute after:inset-y-0 after:-inset-x-2 after:select-none bg-gray-100 dark:bg-gray-800 hover:bg-gray-200 dark:hover:bg-gray-700"></div><div id="chat-assistant-sheet" class="flex flex-col overflow-hidden shrink-0 relative h-full bg-background-light dark:bg-background-dark chat-assistant-sheet" aria-hidden="true"><div class="w-full flex flex-col flex-1 min-h-0 lg:pt-3"><div class="chat-assistant-sheet-header flex items-center justify-between pb-3 px-4"><div class="flex items-center gap-2"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="size-5 text-primary dark:text-primary-light shrink-0" aria-hidden="true"><path d="M5.65799 2.99L4.39499 2.569L3.97399 1.306C3.83699 0.898 3.16199 0.898 3.02499 1.306L2.60399 2.569L1.34099 2.99C1.13699 3.058 0.998993 3.249 0.998993 3.464C0.998993 3.679 1.13699 3.87 1.34099 3.938L2.60399 4.359L3.02499 5.622C3.09299 5.826 3.28499 5.964 3.49999 5.964C3.71499 5.964 3.90599 5.826 3.97499 5.622L4.39599 4.359L5.65899 3.938C5.86299 3.87 6.00099 3.679 6.00099 3.464C6.00099 3.249 5.86199 3.058 5.65799 2.99Z" fill="currentColor" stroke="none"></path><path d="M9.5 2.75L11.412 7.587L16.25 9.5L11.412 11.413L9.5 16.25L7.587 11.413L2.75 9.5L7.587 7.587L9.5 2.75Z" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg><span class="font-medium text-gray-900 dark:text-gray-100">Assistant</span></div><div class="flex items-center gap-1"><button class="group hover:bg-gray-100 dark:hover:bg-white/10 p-1.5 rounded-lg" aria-label="Maximize assistant panel"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" focusable="false" class="size-4 sm:size-3.5 text-gray-500 group-hover:text-gray-700 dark:group-hover:text-gray-300 shrink-0"><path d="M10.75 2.75H15.25V7.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M15.25 2.75L10.75 7.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.75 10.75V15.25H7.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.75 15.25L7.25 10.75" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button><button class="group hover:bg-gray-100 dark:hover:bg-white/10 p-1.5 rounded-lg" aria-label="Close assistant panel"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" focusable="false" class="size-[20px] sm:size-4 text-gray-500 group-hover:text-gray-700 dark:group-hover:text-gray-300 shrink-0"><path d="M14 4L4 14" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4 4L14 14" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button></div></div><div id="chat-content" class="chat-assistant-sheet-content flex flex-col-reverse flex-1 overflow-y-auto relative px-5 min-h-0"><div class="grow"></div><div class="h-full flex flex-col justify-between"><div class="mt-4 flex flex-col items-center text-sm"><div class="mx-8 text-center text-gray-400 dark:text-gray-600 text-xs chat-assistant-disclaimer-text">Responses are generated using AI and may contain mistakes.</div></div></div></div><div class="px-4 pb-4 shrink-0"><div class=""><div class="flex flex-col w-full rounded-2xl pointer-events-auto bg-background-light dark:bg-background-dark border border-gray-200 dark:border-white/10 focus-within:border-primary dark:focus-within:border-primary-light transition-colors"><div class="relative flex items-end"><textarea id="chat-assistant-textarea" aria-label="Ask a question..." autoComplete="off" placeholder="Ask a question..." class="chat-assistant-input w-full bg-transparent border-0 peer/input text-gray-900 dark:text-gray-100 placeholder-gray-600 dark:placeholder-gray-300 outline-hidden! focus:outline-hidden! focus:ring-0 py-2.5 pl-3.5 pr-10 font-bodyWeight text-sm pb-0!" style="resize:none" rows="2"></textarea></div><div class="flex items-center justify-between px-2 pb-2"><input type="file" accept="image/*,.pdf,.js,.jsx,.ts,.tsx,.mjs,.cjs,.md,.mdx,.json,.html,.css,.py,.csv,.txt,.yaml,.yml,.xml,.sql,.sh,.bash,.zsh,.graphql,.gql,.toml,.env,.go,.rs,.rb,.java,.kt,.swift,.c,.cpp,.cc,.h,.hpp,.cs,.php,.dart,.lua,.r,.scala,.ini,.cfg,.conf,.log,.dockerfile,.makefile,.gitignore" multiple="" class="hidden"/><button type="button" class="p-1 rounded-lg text-gray-500 hover:text-gray-700 dark:text-gray-400 dark:hover:text-gray-200 hover:bg-gray-100 dark:hover:bg-white/10" aria-label="Add attachment"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" focusable="false" class="size-3.5 shrink-0"><path d="M7.75 5V11.75C7.75 12.578 8.422 13.25 9.25 13.25C10.078 13.25 10.75 12.578 10.75 11.75V4.75C10.75 3.093 9.407 1.75 7.75 1.75C6.093 1.75 4.75 3.093 4.75 4.75V11.75C4.75 14.235 6.765 16.25 9.25 16.25C11.735 16.25 13.75 14.235 13.75 11.75V5" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button><button class="chat-assistant-send-button flex justify-center items-center rounded-full p-1 size-6 bg-primary/30 dark:bg-primary-dark/30" aria-label="Send message" disabled=""><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-2.5 shrink-0 text-white dark:text-white"><path d="M9.0 1.5754L8.9999 16.4171" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.2563 8.319L8.9999 1.5754L15.7435 8.3191" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button></div></div></div></div></div></div></div></div><script>$RB=[];$RV=function(a){$RT=performance.now();for(var b=0;b<a.length;b+=2){var c=a[b],e=a[b+1];null!==e.parentNode&&e.parentNode.removeChild(e);var f=c.parentNode;if(f){var g=c.previousSibling,h=0;do{if(c&&8===c.nodeType){var d=c.data;if("/$"===d||"/&"===d)if(0===h)break;else h--;else"$"!==d&&"$?"!==d&&"$~"!==d&&"$!"!==d&&"&"!==d||h++}d=c.nextSibling;f.removeChild(c);c=d}while(c);for(;e.firstChild;)f.insertBefore(e.firstChild,c);g.data="$";g._reactRetry&&requestAnimationFrame(g._reactRetry)}}a.length=0};

3152$RC=function(a,b){if(b=document.getElementById(b))(a=document.getElementById(a))?(a.previousSibling.data="$~",$RB.push(a,b),2===$RB.length&&("number"!==typeof $RT?requestAnimationFrame($RV.bind(null,$RB)):(a=performance.now(),setTimeout($RV.bind(null,$RB),2300>a&&2E3<a?2300-a:$RT+300-a)))):b.parentNode.removeChild(b)};$RC("B:0","S:0")</script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\nb:I[168027,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"default\"]\n:HL[\"/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"style\"]\n:HL[\"/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"style\"]\n:HL[\"/docs/_next/static/media/83afe278b6a6bb3c.p.3a6ba036.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/docs/_next/static/media/PaperMono_Variable.p.4fb029ee.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/docs/_next/static/media/f67ad414ed34149c.p.84166d94.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"J_sBhkrYCnqrcAl2B9n_I\",\"p\":\"/docs\",\"c\":[\"\",\"_sites\",\"claude-ai\",\"claude-tag\",\"overview\"],\"i\":false,\"f\":[[[\"\",{\"children\":[\"%5Fsites\",{\"children\":[[\"subdomain\",\"claude-ai\",\"d\"],{\"children\":[\"(multitenant)\",{\"children\":[[\"slug\",\"claude-tag/overview\",\"oc\"],{\"children\":[\"__PAGE__\",{}]}]}]}]}]},\"$undefined\",\"$undefined\",true],[\"\",[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"link\",\"1\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"suppressHydrationWarning\":true,\"lang\":\"en\",\"className\":\"inter_1d81deff-module__CYM0aG__variable papermono_89c757f2-module__6aS5zq__variable dark\",\"data-banner-state\":\"visible\",\"data-assistant-state\":\"closed\",\"data-page-mode\":\"none\",\"data-current-path\":\"/\",\"children\":[[\"$\",\"head\",null,{\"children\":[[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"!function(){var b=\\\"/docs\\\";\\nfunction a(p){if(p==null)return\\\"/\\\";p=\\\"\\\"+p;if(\\\"\\\"===p)return\\\"/\\\";return\\\"/\\\"===p.charAt(0)?p:\\\"/\\\"+p}\\nfunction u(p){if(p==null)return p;p=\\\"\\\"+p;if(!p||p.charAt(p.length-1)===\\\"/\\\")return p.slice(0,-1);return p}\\nfunction i(p){if(p==null)return p;p=\\\"\\\"+p;if(6\u003c=p.length\u0026\u0026p.substring(p.length-6)===\\\"/index\\\")return p.substring(0,p.length-6);if(\\\"index\\\"===p)return\\\"\\\";return p}\\nvar p=(location.pathname||\\\"\\\").split(\\\"?\\\")[0].split(\\\"#\\\")[0]||\\\"\\\";\\nif(b)if(p===b)p=\\\"\\\";else if(0===p.indexOf(b+\\\"/\\\"))p=p.substring(b.length);\\np=a(p);p=u(p);p=i(p);p=\\\"\\\"===p||\\\"index\\\"===p?\\\"/\\\":a(p);\\ndocument.documentElement.setAttribute(\\\"data-current-path\\\",p);\\n}();\"}}],\"$undefined\",[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"(() =\u003e {\\n const isIOS =\\n /iP(hone|ad|od)/.test(navigator.userAgent) ||\\n (/Macintosh/.test(navigator.userAgent) \u0026\u0026 navigator.maxTouchPoints \u003e 1);\\n if (!isIOS) return;\\n const apply = () =\u003e {\\n for (const meta of document.querySelectorAll('meta[name=\\\"viewport\\\"]')) {\\n const content = meta.getAttribute('content') || '';\\n if (!content.includes('maximum-scale')) {\\n meta.setAttribute('content', content + ', maximum-scale=1');\\n }\\n }\\n };\\n apply();\\n new MutationObserver(apply).observe(document.head, {\\n childList: true,\\n subtree: true,\\n attributes: true,\\n attributeFilter: ['content'],\\n });\\n})();\"}}],[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"!function(){\\nfunction read(){try{\\nvar e=performance.getEntriesByType?performance.getEntriesByType(\\\"navigation\\\"):[];\\nvar st=(e[0]\u0026\u0026e[0].serverTiming)||[];\\nvar g={};\\nfor(var i=0;i\u003cst.length;i++){var n=st[i].name,d=st[i].description;if(!d)continue;try{d=decodeURIComponent(d)}catch(x){}\\nif(n===\\\"country\\\")g.country=d;else if(n===\\\"region\\\")g.region=d;else if(n===\\\"continent\\\")g.continent=d;}\\nvar w=window;w.mintlify=w.mintlify||{};w.mintlify.geo=g;\\n}catch(x){}}\\nread();document.addEventListener(\\\"DOMContentLoaded\\\",read);\\n}();\"}}],[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"!function(){try{\\nvar w=window;w.mintlify=w.mintlify||{};\\nvar q=w.mintlify.__apiPlaygroundInputsQueue;\\nif(!Array.isArray(q)){q=[];w.mintlify.__apiPlaygroundInputsQueue=q;}\\nw.mintlify.api=w.mintlify.api||{};\\nw.mintlify.api.playground=w.mintlify.api.playground||{};\\nif(typeof w.mintlify.api.playground.setServerVariables!==\\\"function\\\"){\\nw.mintlify.api.playground.setServerVariables=function(v){q.push({type:\\\"set\\\",variables:v});};\\n}\\nif(typeof w.mintlify.api.playground.clearServerVariables!==\\\"function\\\"){\\nw.mintlify.api.playground.clearServerVariables=function(){q.push({type:\\\"clear\\\"});};\\n}\\n}catch(e){}}();\"}}],\"$L2\",\"$L3\",false]}],\"$L4\"]}]]}],{\"children\":[\"%5Fsites\",\"$L5\",{\"children\":[[\"subdomain\",\"claude-ai\",\"d\"],\"$L6\",{\"children\":[\"(multitenant)\",\"$L7\",{\"children\":[[\"slug\",\"claude-tag/overview\",\"oc\"],\"$L8\",{\"children\":[\"__PAGE__\",\"$L9\",{},null,false]},null,false]},null,false]},null,false]},null,false]},null,false],\"$La\",false]],\"m\":\"$undefined\",\"G\":[\"$b\",[\"$Lc\",\"$Ld\"]],\"s\":false,\"S\":true}\n"])</script><script>self.__next_f.push([1,"e:I[667786,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"MintlifyApiPlaygroundInputsInit\"]\nf:I[339756,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"default\"]\n10:I[556357,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/a2a714cf193b029a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"default\"]\n11:I[837457,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"default\"]\n"])</script><script>self.__next_f.push([1,"12:I[894587,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"ThemeProvider\"]\n"])</script><script>self.__next_f.push([1,"13:I[152823,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"ColorVariables\"]\n"])</script><script>self.__next_f.push([1,"14:I[531961,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"FontScript\"]\n"])</script><script>self.__next_f.push([1,"15:I[649328,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"RoundedVariables\"]\n"])</script><script>self.__next_f.push([1,"16:I[702910,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/2ef7b8b76773d1cd.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"RecommendedPagesList\"]\n17:I[570420,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"DataCurrentPathUpdater\"]\n18:I[172816,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"MintlifyNavigateEvents\"]\n19:I[341175,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/94d2303c1cf0e7a6.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"default\"]\n1c:I[897367,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"OutletBoundary\"]\n1e:I[711533,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"AsyncMetadataOutlet\"]\n20:I[897367,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add9"])</script><script>self.__next_f.push([1,"3a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"ViewportBoundary\"]\n22:I[897367,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"MetadataBoundary\"]\n23:\"$Sreact.suspense\"\n2:[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"(function(){\\nif(typeof CSS===\\\"undefined\\\"||!(\\\"registerProperty\\\" in CSS))return;\\nif(CSS.supports\u0026\u0026CSS.supports(\\\"-webkit-backdrop-filter:none\\\"))return;\\nvar n=[\\\"--scroll-area-overflow-x-start\\\",\\\"--scroll-area-overflow-x-end\\\",\\\"--scroll-area-overflow-y-start\\\",\\\"--scroll-area-overflow-y-end\\\"];\\nvar d={\\\"syntax\\\":\\\"\u003clength\u003e\\\",\\\"inherits\\\":false,\\\"initialValue\\\":\\\"0px\\\"};\\nfor(var i=0;i\u003cn.length;i++){try{CSS.registerProperty({name:n[i],syntax:d.syntax,inherits:d.inherits,initialValue:d.initialValue})}catch(e){}}\\n})();\"}}]\n"])</script><script>self.__next_f.push([1,"3:[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"(function(a,b){try{let c=document.querySelector(\\\"div#banner\\\")?.innerText;if(c){for(let d=0;d\u003clocalStorage.length;d++){let e=localStorage.key(d);if(e?.endsWith(a)\u0026\u0026localStorage.getItem(e)===c)return void document.documentElement.setAttribute(b,\\\"hidden\\\")}document.documentElement.setAttribute(b,\\\"visible\\\");return}for(let c=0;c\u003clocalStorage.length;c++){let d=localStorage.key(c);if(d?.endsWith(a)\u0026\u0026localStorage.getItem(d))return void document.documentElement.setAttribute(b,\\\"hidden\\\")}document.documentElement.setAttribute(b,\\\"visible\\\")}catch(a){document.documentElement.setAttribute(b,\\\"hidden\\\")}})(\\n \\\"bannerDismissed\\\",\\n \\\"data-banner-state\\\",\\n)\"}}]\n"])</script><script>self.__next_f.push([1,"4:[\"$\",\"body\",null,{\"className\":\"antialiased\",\"children\":[[\"$\",\"$Le\",null,{}],false,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$10\",\"errorStyles\":[],\"errorScripts\":[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/a2a714cf193b029a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}]],\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"$L12\",null,{\"children\":[[\"$\",\"$L13\",null,{}],[\"$\",\"$L14\",null,{}],[\"$\",\"$L15\",null,{}],[\"$\",\"style\",null,{\"children\":\":root {\\n --primary: 17 120 102;\\n --primary-light: 74 222 128;\\n --primary-dark: 22 101 52;\\n --background-light: 255 255 255;\\n --background-dark: 15 17 23;\\n}\"}],[\"$\",\"main\",null,{\"className\":\"h-screen bg-background-light dark:bg-background-dark text-left\",\"children\":[\"$\",\"article\",null,{\"className\":\"bg-custom bg-fixed bg-center bg-cover relative flex flex-col items-center justify-center h-full\",\"children\":[\"$\",\"div\",null,{\"className\":\"w-full max-w-xl px-10\",\"children\":[[\"$\",\"span\",null,{\"className\":\"inline-flex mb-6 rounded-full px-3 py-1 text-sm font-semibold mr-4 text-white p-1 bg-primary\",\"children\":[\"Error \",404]}],[\"$\",\"h1\",null,{\"className\":\"font-semibold mb-3 text-3xl\",\"children\":\"Page not found!\"}],[\"$\",\"p\",null,{\"className\":\"text-lg text-gray-600 dark:text-gray-400 mb-6\",\"children\":\"We couldn't find the page.\"}],[\"$\",\"$L16\",null,{}]]}]}]}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}],false,[\"$\",\"$L17\",null,{}],[\"$\",\"$L18\",null,{}]]}]\n"])</script><script>self.__next_f.push([1,"5:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"6:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$19\",\"errorStyles\":[],\"errorScripts\":[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/94d2303c1cf0e7a6.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true}]],\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"$L12\",null,{\"children\":[[\"$\",\"$L13\",null,{}],[\"$\",\"$L14\",null,{}],[\"$\",\"$L15\",null,{}],[\"$\",\"style\",null,{\"children\":\":root {\\n --primary: 17 120 102;\\n --primary-light: 74 222 128;\\n --primary-dark: 22 101 52;\\n --background-light: 255 255 255;\\n --background-dark: 15 17 23;\\n}\"}],[\"$\",\"main\",null,{\"className\":\"h-screen bg-background-light dark:bg-background-dark text-left\",\"children\":[\"$\",\"article\",null,{\"className\":\"bg-custom bg-fixed bg-center bg-cover relative flex flex-col items-center justify-center h-full\",\"children\":[\"$\",\"div\",null,{\"className\":\"w-full max-w-xl px-10\",\"children\":[[\"$\",\"span\",null,{\"className\":\"inline-flex mb-6 rounded-full px-3 py-1 text-sm font-semibold mr-4 text-white p-1 bg-primary\",\"children\":[\"Error \",404]}],[\"$\",\"h1\",null,{\"className\":\"font-semibold mb-3 text-3xl\",\"children\":\"Page not found!\"}],[\"$\",\"p\",null,{\"className\":\"text-lg text-gray-600 dark:text-gray-400 mb-6\",\"children\":\"We couldn't find the page.\"}],[\"$\",\"$L16\",null,{}]]}]}]}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"7:[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-4\",{\"src\":\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-5\",{\"src\":\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-6\",{\"src\":\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-7\",{\"src\":\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-8\",{\"src\":\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-9\",{\"src\":\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-10\",{\"src\":\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-11\",{\"src\":\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-12\",{\"src\":\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-13\",{\"src\":\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-14\",{\"src\":\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-15\",{\"src\":\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-16\",{\"src\":\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-17\",{\"src\":\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-18\",{\"src\":\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}]],\"$L1a\"]}]\n"])</script><script>self.__next_f.push([1,"8:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"9:[\"$\",\"$1\",\"c\",{\"children\":[\"$L1b\",[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/c3bc6629a7fa7c34.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/524bce83f7b2f674.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/1347c67505f8d6ff.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/4fb629d8ce053f08.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-4\",{\"src\":\"/docs/_next/static/chunks/1ab82a2e4905d2c6.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-5\",{\"src\":\"/docs/_next/static/chunks/e7049fc815953dcd.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-6\",{\"src\":\"/docs/_next/static/chunks/f944c986e78b445f.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"$L1c\",null,{\"children\":[\"$L1d\",[\"$\",\"$L1e\",null,{\"promise\":\"$@1f\"}]]}]]}]\n"])</script><script>self.__next_f.push([1,"a:[\"$\",\"$1\",\"h\",{\"children\":[null,[[\"$\",\"$L20\",null,{\"children\":\"$L21\"}],null],[\"$\",\"$L22\",null,{\"children\":[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$23\",null,{\"fallback\":null,\"children\":\"$L24\"}]}]}]]}]\nc:[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]\nd:[\"$\",\"link\",\"1\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]\n"])</script><script>self.__next_f.push([1,"21:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1, viewport-fit=cover\"}]]\n1d:null\n"])</script><script>self.__next_f.push([1,"25:I[707934,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"WebMcpRegistration\"]\n"])</script><script>self.__next_f.push([1,"26:I[590280,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"LivePreviewProvider\"]\n"])</script><script>self.__next_f.push([1,"27:I[973254,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"LivePreviewFavicon\"]\n"])</script><script>self.__next_f.push([1,"28:I[197336,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"default\"]\n"])</script><script>self.__next_f.push([1,"29:I[91557,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/fd4246cf5bf12598.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/224337c8971b9d9a.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/c3bc6629a7fa7c34.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/524bce83f7b2f674.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1347c67505f8d6ff.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4fb629d8ce053f08.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1ab82a2e4905d2c6.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/e7049fc815953dcd.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/f944c986e78b445f.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\"],\"AuthProvider\"]\n"])</script><script>self.__next_f.push([1,"2a:I[91557,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/7107e565fd735ebb.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/af1d00b42ca32cc2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_5ouYV7vfCcy3TTZ8C33Jmttbiqsq\",\"/docs/_next/static/ch

3151<div class="columns prose dark:prose-invert grid max-w-none gap-4 sm:grid-cols-[repeat(var(--cols),minmax(0,1fr))] @2xl/columns-container:grid-cols-[repeat(var(--cols),minmax(0,1fr))] @[0px]/columns-container:grid-cols-1 card-group dark:prose-dark gap-y-0 sm:grid-cols-[repeat(var(--cols),minmax(0,1fr))]!" style="--cols:2"><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_675dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/gear.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/gear.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_675dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">Set up Claude Tag</h2><div id="_R_675dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">Admins: pair your Slack workspace and launch</span></div></div></div></div><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_a75dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/paper-plane.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/paper-plane.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_a75dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">Hand Claude Tag your first task</h2><div id="_R_a75dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">It’s already in your channel: send your first message</span></div></div></div></div><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_e75dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/diagram-project.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/diagram-project.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_e75dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">How Claude Tag works</h2><div id="_R_e75dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">The session model, what it can read, and how memory follows places</span></div></div></div></div><div class="card block font-normal group relative my-2 ring-2 ring-transparent rounded-2xl bg-white dark:bg-background-dark border border-gray-950/10 dark:border-white/10 overflow-hidden w-full cursor-pointer hover:border-primary! dark:hover:border-primary-light!" aria-labelledby="_R_i75dd7av5tcd74t9snpfiutb_" tabindex="0" role="link"><div class="px-6 py-5 relative flex items-center gap-x-4" data-component-part="card-content-container"><div class="absolute text-gray-400 dark:text-gray-500 group-hover:text-primary dark:group-hover:text-primary-light top-5 right-5"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="m-0.5 size-3 shrink-0"><path d="M14.25 3.75L3.75525 14.2446" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.71301 3.75H14.2499V13.2869" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></div><div aria-hidden="true" class="size-6 fill-gray-800 dark:fill-gray-100 text-gray-800 dark:text-gray-100 [&>svg]:size-6" data-component-part="card-icon"><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! size-6 m-0! shrink-0 bg-primary dark:bg-primary-light" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/list.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/regular/list.svg");mask-repeat:no-repeat;mask-position:center"></svg></div><div class="w-full"><h2 id="_R_i75dd7av5tcd74t9snpfiutb_" class="not-prose font-semibold text-base text-gray-800 dark:text-white" contentEditable="false" data-component-part="card-title">Use case library</h2><div id="_R_i75dd7av5tcd74t9snpfiutbH1_" class="prose font-normal text-base text-gray-600 dark:text-gray-400 leading-6 mt-0" data-component-part="card-content"><span data-as="p">Prompts to paste, by team and connection</span></div></div></div></div></div></div><div class="feedback-toolbar pb-16 w-full flex flex-col gap-y-8"><div class="flex flex-row flex-wrap gap-4 items-center justify-between"><p class="inline-block text-sm text-gray-600 dark:text-gray-400 whitespace-nowrap">Was this page helpful?</p><div class="flex flex-wrap grow gap-3 items-center justify-end"><div class="flex gap-3 items-center"><button id="feedback-thumbs-up" class="px-3.5 py-2 flex flex-row gap-3 items-center border-standard rounded-xl text-gray-600 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300 bg-white/50 dark:bg-codeblock/50 hover:border-gray-500 hover:dark:border-gray-500 focus-visible:outline-2 focus-visible:-outline-offset-2 focus-visible:outline-primary dark:focus-visible:outline-primary-light"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-4 shrink-0 text-current"><path d="M5.25 7.494C5.25 7.014 5.423 6.55 5.736 6.187L10 1.25C10.854 1.677 11.25 2.678 10.92 3.574L9.75 6.75H14.152C15.465 6.75 16.421 7.993 16.085 9.262L14.894 13.762C14.662 14.639 13.868 15.25 12.961 15.25H7.25C6.145 15.25 5.25 14.355 5.25 13.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.25 6.75H2.75C2.19772 6.75 1.75 7.19772 1.75 7.75V14.25C1.75 14.8023 2.19772 15.25 2.75 15.25H4.25C4.80228 15.25 5.25 14.8023 5.25 14.25V7.75C5.25 7.19772 4.80228 6.75 4.25 6.75Z" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg><small class="text-sm font-normal leading-4">Yes</small></button><button id="feedback-thumbs-down" class="px-3.5 py-2 flex flex-row gap-3 items-center border-standard rounded-xl text-gray-600 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300 bg-white/50 dark:bg-codeblock/50 hover:border-gray-500 hover:dark:border-gray-500 focus-visible:outline-2 focus-visible:-outline-offset-2 focus-visible:outline-primary dark:focus-visible:outline-primary-light"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-4 shrink-0 text-current"><path d="M5.25 10.506C5.25 10.986 5.423 11.45 5.736 11.813L10 16.75C10.854 16.323 11.25 15.322 10.92 14.426L9.75 11.25H14.152C15.465 11.25 16.421 10.007 16.085 8.738L14.894 4.238C14.662 3.361 13.868 2.75 12.961 2.75H7.25C6.145 2.75 5.25 3.645 5.25 4.75" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4.25 2.75H2.75C2.19772 2.75 1.75 3.19772 1.75 3.75V10.25C1.75 10.8023 2.19772 11.25 2.75 11.25H4.25C4.80228 11.25 5.25 10.8023 5.25 10.25V3.75C5.25 3.19772 4.80228 2.75 4.25 2.75Z" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg><small class="text-sm font-normal leading-4">No</small></button></div><div class="flex gap-3"></div></div></div></div><nav id="pagination" aria-label="Pagination" class="px-0.5 flex items-center gap-6 text-sm font-semibold text-gray-700 dark:text-gray-200"><a rel="next" aria-label="Next: How Claude Tag works" data-component-part="pagination-next" class="group flex items-center min-w-0 focus-visible:outline-2 focus-visible:outline-offset-2 focus-visible:outline-primary dark:focus-visible:outline-primary-light gap-3 rounded-sm ml-auto pagination-next" href="/docs/claude-tag/concepts/how-it-works"><div class="truncate group-hover:text-gray-900 dark:group-hover:text-white" data-component-part="pagination-title">How Claude Tag works</div><svg viewBox="0 0 3 6" aria-hidden="true" data-component-part="pagination-chevron" class="h-1.5 shrink-0 stroke-gray-400 overflow-visible group-hover:stroke-gray-600 dark:group-hover:stroke-gray-300 rotate-180"><path d="M3 0L0 3L3 6" fill="none" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"></path></svg></a></nav><div data-assistant-bar="" class="left-0 right-0 sticky bottom-0 w-full overflow-hidden z-20 pointer-events-none print:hidden"><div class="chat-assistant-floating-input w-full group/assistant-bar relative translate-y-[100px] opacity-0"><div class="relative pb-4 sm:pb-6 max-w-2xl mx-auto"><div class="flex flex-col w-full rounded-2xl pointer-events-auto bg-background-light dark:bg-background-dark border border-gray-200 dark:border-white/10 focus-within:border-primary dark:focus-within:border-primary-light transition-colors"><div class="relative flex items-end"><textarea id="chat-assistant-textarea" aria-label="Ask a question..." autoComplete="off" placeholder="Ask a question..." class="chat-assistant-input w-full bg-transparent border-0 peer/input text-gray-900 dark:text-gray-100 placeholder-gray-600 dark:placeholder-gray-300 outline-hidden! focus:outline-hidden! focus:ring-0 py-2.5 pl-3.5 pr-10 font-bodyWeight text-sm" style="resize:none"></textarea><button class="chat-assistant-send-button flex justify-center items-center rounded-full p-1 size-6 bg-primary/30 dark:bg-primary-dark/30 absolute right-2.5 bottom-2" aria-label="Send message" disabled=""><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-2.5 shrink-0 text-white dark:text-white"><path d="M9.0 1.5754L8.9999 16.4171" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.2563 8.319L8.9999 1.5754L15.7435 8.3191" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button></div></div></div></div></div></div></div></main></div><footer id="footer" class="advanced-footer flex flex-col items-center mx-auto border-t border-gray-100 dark:border-gray-800/50 peer-[.is-custom]:hidden! peer-[.is-custom]:sm:hidden! peer-[.is-custom]:md:hidden! peer-[.is-custom]:lg:hidden! peer-[.is-custom]:xl:hidden!"><div class="flex w-full flex-col gap-12 justify-between px-8 py-16 md:py-20 lg:py-28 max-w-246 z-20"><div class="flex flex-col md:flex-row gap-8 justify-between min-h-19"><div class="flex md:flex-col justify-between items-center md:items-start min-w-16 md:min-w-20 lg:min-w-48 md:gap-y-24"><a class="select-none" style="-webkit-touch-callout:none" href="/docs"><span class="sr-only">Claude.ai Documentation home page</span><img class="nav-logo w-auto relative object-contain shrink-0 block dark:hidden max-w-48 h-[26px]" src="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/light.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=e870c19cb781d8a7c7b7d19de53b0a10" alt="light logo"/><img class="nav-logo w-auto relative object-contain shrink-0 hidden dark:block max-w-48 h-[26px]" src="https://mintcdn.com/claude-ai/1fyDNLAICe3KG6rB/logo/dark.svg?fit=max&auto=format&n=1fyDNLAICe3KG6rB&q=85&s=80cc0b06d8fd9aeefec8acb226de6866" alt="dark logo"/></a><div class="gap-4 min-w-[140px] max-w-[492px] flex-wrap h-fit flex justify-end md:justify-start"><a href="https://x.com/AnthropicAI" target="_blank" rel="noopener noreferrer" class="h-fit"><span class="sr-only">x</span><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! w-5 h-5 bg-gray-500 dark:bg-gray-600 hover:bg-gray-600 dark:hover:bg-gray-500" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/x-twitter.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/x-twitter.svg");mask-repeat:no-repeat;mask-position:center"></svg></a><a href="https://www.linkedin.com/company/anthropicresearch" target="_blank" rel="noopener noreferrer" class="h-fit"><span class="sr-only">linkedin</span><svg class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! w-5 h-5 bg-gray-500 dark:bg-gray-600 hover:bg-gray-600 dark:hover:bg-gray-500" aria-hidden="true" focusable="false" style="-webkit-mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/linkedin.svg");-webkit-mask-repeat:no-repeat;-webkit-mask-position:center;mask-image:url("https://d3gk2c5xim1je2.cloudfront.net/fontawesome/v7.2.0/brands/linkedin.svg");mask-repeat:no-repeat;mask-position:center"></svg></a></div></div><div class="flex flex-col sm:grid max-md:grid-cols-2! gap-8 flex-1" style="grid-template-columns:repeat(4, minmax(0, 1fr))"><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Company</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/company" target="_blank" rel="noreferrer">Anthropic</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/careers" target="_blank" rel="noreferrer">Careers</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/economic-futures" target="_blank" rel="noreferrer">Economic Futures</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/research" target="_blank" rel="noreferrer">Research</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/news" target="_blank" rel="noreferrer">News</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://trust.anthropic.com/" target="_blank" rel="noreferrer">Trust center</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/transparency" target="_blank" rel="noreferrer">Transparency</a></div></div><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Help and security</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/supported-countries" target="_blank" rel="noreferrer">Availability</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://status.anthropic.com/" target="_blank" rel="noreferrer">Status</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://support.claude.com/" target="_blank" rel="noreferrer">Support center</a></div></div><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Learn</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://academy.claude.com/" target="_blank" rel="noreferrer">Courses</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/partners/mcp" target="_blank" rel="noreferrer">MCP connectors</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.claude.com/customers" target="_blank" rel="noreferrer">Customer stories</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/engineering" target="_blank" rel="noreferrer">Engineering blog</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/events" target="_blank" rel="noreferrer">Events</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/partners/powered-by-claude" target="_blank" rel="noreferrer">Powered by Claude</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/partners/services" target="_blank" rel="noreferrer">Service partners</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://claude.com/programs/startups" target="_blank" rel="noreferrer">Startups program</a></div></div><div class="flex flex-col gap-4 flex-1 whitespace-nowrap w-full md:items-center"><div class="flex gap-4 flex-col"><p class="text-sm font-semibold text-gray-950 dark:text-white mb-1">Terms and policies</p><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/privacy" target="_blank" rel="noreferrer">Privacy policy</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/responsible-disclosure-policy" target="_blank" rel="noreferrer">Disclosure policy</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/aup" target="_blank" rel="noreferrer">Usage policy</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/commercial-terms" target="_blank" rel="noreferrer">Commercial terms</a><a class="text-sm max-w-36 whitespace-normal md:truncate text-gray-950/50 dark:text-white/50 hover:text-gray-950/70 dark:hover:text-white/70" href="https://www.anthropic.com/legal/consumer-terms" target="_blank" rel="noreferrer">Consumer terms</a></div></div></div></div></div></footer></div><template id="B:0"></template></div></div><script>requestAnimationFrame(function(){$RT=performance.now()});</script><script src="/docs/_next/static/chunks/3fcb76f539c93820.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp" id="_R_" async=""></script><div hidden id="S:0"><div data-assistant-sheet-container="" class="sticky shrink-0 z-22 bg-background-light dark:bg-background-dark mt-(--banner-height,0px) top-(--banner-height,0px) h-[calc(100vh-var(--banner-height,0px))] max-lg:hidden print:hidden" style="width:var(--assistant-sheet-width, 0px);overflow:hidden"><div class="absolute left-0 top-0 bottom-0 w-px z-10 cursor-col-resize after:content-[""] after:absolute after:inset-y-0 after:-inset-x-2 after:select-none bg-gray-100 dark:bg-gray-800 hover:bg-gray-200 dark:hover:bg-gray-700"></div><div id="chat-assistant-sheet" class="flex flex-col overflow-hidden shrink-0 relative h-full bg-background-light dark:bg-background-dark chat-assistant-sheet" aria-hidden="true"><div class="w-full flex flex-col flex-1 min-h-0 lg:pt-3"><div class="chat-assistant-sheet-header flex items-center justify-between pb-3 px-4"><div class="flex items-center gap-2"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="size-5 text-primary dark:text-primary-light shrink-0" aria-hidden="true"><path d="M5.65799 2.99L4.39499 2.569L3.97399 1.306C3.83699 0.898 3.16199 0.898 3.02499 1.306L2.60399 2.569L1.34099 2.99C1.13699 3.058 0.998993 3.249 0.998993 3.464C0.998993 3.679 1.13699 3.87 1.34099 3.938L2.60399 4.359L3.02499 5.622C3.09299 5.826 3.28499 5.964 3.49999 5.964C3.71499 5.964 3.90599 5.826 3.97499 5.622L4.39599 4.359L5.65899 3.938C5.86299 3.87 6.00099 3.679 6.00099 3.464C6.00099 3.249 5.86199 3.058 5.65799 2.99Z" fill="currentColor" stroke="none"></path><path d="M9.5 2.75L11.412 7.587L16.25 9.5L11.412 11.413L9.5 16.25L7.587 11.413L2.75 9.5L7.587 7.587L9.5 2.75Z" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg><span class="font-medium text-gray-900 dark:text-gray-100">Assistant</span></div><div class="flex items-center gap-1"><button class="group hover:bg-gray-100 dark:hover:bg-white/10 p-1.5 rounded-lg" aria-label="Maximize assistant panel"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" focusable="false" class="size-4 sm:size-3.5 text-gray-500 group-hover:text-gray-700 dark:group-hover:text-gray-300 shrink-0"><path d="M10.75 2.75H15.25V7.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M15.25 2.75L10.75 7.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.75 10.75V15.25H7.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.75 15.25L7.25 10.75" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button><button class="group hover:bg-gray-100 dark:hover:bg-white/10 p-1.5 rounded-lg" aria-label="Close assistant panel"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" focusable="false" class="size-[20px] sm:size-4 text-gray-500 group-hover:text-gray-700 dark:group-hover:text-gray-300 shrink-0"><path d="M14 4L4 14" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M4 4L14 14" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button></div></div><div id="chat-content" class="chat-assistant-sheet-content flex flex-col-reverse flex-1 overflow-y-auto relative px-5 min-h-0"><div class="grow"></div><div class="h-full flex flex-col justify-between"><div class="mt-4 flex flex-col items-center text-sm"><div class="mx-8 text-center text-gray-400 dark:text-gray-600 text-xs chat-assistant-disclaimer-text">Responses are generated using AI and may contain mistakes.</div></div></div></div><div class="px-4 pb-4 shrink-0"><div class=""><div class="flex flex-col w-full rounded-2xl pointer-events-auto bg-background-light dark:bg-background-dark border border-gray-200 dark:border-white/10 focus-within:border-primary dark:focus-within:border-primary-light transition-colors"><div class="relative flex items-end"><textarea id="chat-assistant-textarea" aria-label="Ask a question..." autoComplete="off" placeholder="Ask a question..." class="chat-assistant-input w-full bg-transparent border-0 peer/input text-gray-900 dark:text-gray-100 placeholder-gray-600 dark:placeholder-gray-300 outline-hidden! focus:outline-hidden! focus:ring-0 py-2.5 pl-3.5 pr-10 font-bodyWeight text-sm pb-0!" style="resize:none" rows="2"></textarea></div><div class="flex items-center justify-between px-2 pb-2"><input type="file" accept="image/*,.pdf,.js,.jsx,.ts,.tsx,.mjs,.cjs,.md,.mdx,.json,.html,.css,.py,.csv,.txt,.yaml,.yml,.xml,.sql,.sh,.bash,.zsh,.graphql,.gql,.toml,.env,.go,.rs,.rb,.java,.kt,.swift,.c,.cpp,.cc,.h,.hpp,.cs,.php,.dart,.lua,.r,.scala,.ini,.cfg,.conf,.log,.dockerfile,.makefile,.gitignore" multiple="" class="hidden"/><button type="button" class="p-1 rounded-lg text-gray-500 hover:text-gray-700 dark:text-gray-400 dark:hover:text-gray-200 hover:bg-gray-100 dark:hover:bg-white/10" aria-label="Add attachment"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" focusable="false" class="size-3.5 shrink-0"><path d="M7.75 5V11.75C7.75 12.578 8.422 13.25 9.25 13.25C10.078 13.25 10.75 12.578 10.75 11.75V4.75C10.75 3.093 9.407 1.75 7.75 1.75C6.093 1.75 4.75 3.093 4.75 4.75V11.75C4.75 14.235 6.765 16.25 9.25 16.25C11.735 16.25 13.75 14.235 13.75 11.75V5" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button><button class="chat-assistant-send-button flex justify-center items-center rounded-full p-1 size-6 bg-primary/30 dark:bg-primary-dark/30" aria-label="Send message" disabled=""><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-2.5 shrink-0 text-white dark:text-white"><path d="M9.0 1.5754L8.9999 16.4171" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.2563 8.319L8.9999 1.5754L15.7435 8.3191" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg></button></div></div></div></div></div></div></div></div><script>$RB=[];$RV=function(a){$RT=performance.now();for(var b=0;b<a.length;b+=2){var c=a[b],e=a[b+1];null!==e.parentNode&&e.parentNode.removeChild(e);var f=c.parentNode;if(f){var g=c.previousSibling,h=0;do{if(c&&8===c.nodeType){var d=c.data;if("/$"===d||"/&"===d)if(0===h)break;else h--;else"$"!==d&&"$?"!==d&&"$~"!==d&&"$!"!==d&&"&"!==d||h++}d=c.nextSibling;f.removeChild(c);c=d}while(c);for(;e.firstChild;)f.insertBefore(e.firstChild,c);g.data="$";g._reactRetry&&requestAnimationFrame(g._reactRetry)}}a.length=0};

3152$RC=function(a,b){if(b=document.getElementById(b))(a=document.getElementById(a))?(a.previousSibling.data="$~",$RB.push(a,b),2===$RB.length&&("number"!==typeof $RT?requestAnimationFrame($RV.bind(null,$RB)):(a=performance.now(),setTimeout($RV.bind(null,$RB),2300>a&&2E3<a?2300-a:$RT+300-a)))):b.parentNode.removeChild(b)};$RC("B:0","S:0")</script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\nb:I[168027,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"default\"]\n:HL[\"/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"style\"]\n:HL[\"/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"style\"]\n:HL[\"/docs/_next/static/media/83afe278b6a6bb3c.p.3a6ba036.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/docs/_next/static/media/PaperMono_Variable.p.4fb029ee.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/docs/_next/static/media/f67ad414ed34149c.p.84166d94.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"3A0wR7imVG784X7IexfLa\",\"p\":\"/docs\",\"c\":[\"\",\"_sites\",\"claude-ai\",\"claude-tag\",\"overview\"],\"i\":false,\"f\":[[[\"\",{\"children\":[\"%5Fsites\",{\"children\":[[\"subdomain\",\"claude-ai\",\"d\"],{\"children\":[\"(multitenant)\",{\"children\":[[\"slug\",\"claude-tag/overview\",\"oc\"],{\"children\":[\"__PAGE__\",{}]}]}]}]}]},\"$undefined\",\"$undefined\",true],[\"\",[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"link\",\"1\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"suppressHydrationWarning\":true,\"lang\":\"en\",\"className\":\"inter_1d81deff-module__CYM0aG__variable papermono_89c757f2-module__6aS5zq__variable dark\",\"data-banner-state\":\"visible\",\"data-assistant-state\":\"closed\",\"data-page-mode\":\"none\",\"data-current-path\":\"/\",\"children\":[[\"$\",\"head\",null,{\"children\":[[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"!function(){var b=\\\"/docs\\\";\\nfunction a(p){if(p==null)return\\\"/\\\";p=\\\"\\\"+p;if(\\\"\\\"===p)return\\\"/\\\";return\\\"/\\\"===p.charAt(0)?p:\\\"/\\\"+p}\\nfunction u(p){if(p==null)return p;p=\\\"\\\"+p;if(!p||p.charAt(p.length-1)===\\\"/\\\")return p.slice(0,-1);return p}\\nfunction i(p){if(p==null)return p;p=\\\"\\\"+p;if(6\u003c=p.length\u0026\u0026p.substring(p.length-6)===\\\"/index\\\")return p.substring(0,p.length-6);if(\\\"index\\\"===p)return\\\"\\\";return p}\\nvar p=(location.pathname||\\\"\\\").split(\\\"?\\\")[0].split(\\\"#\\\")[0]||\\\"\\\";\\nif(b)if(p===b)p=\\\"\\\";else if(0===p.indexOf(b+\\\"/\\\"))p=p.substring(b.length);\\np=a(p);p=u(p);p=i(p);p=\\\"\\\"===p||\\\"index\\\"===p?\\\"/\\\":a(p);\\ndocument.documentElement.setAttribute(\\\"data-current-path\\\",p);\\n}();\"}}],\"$undefined\",[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"(() =\u003e {\\n const isIOS =\\n /iP(hone|ad|od)/.test(navigator.userAgent) ||\\n (/Macintosh/.test(navigator.userAgent) \u0026\u0026 navigator.maxTouchPoints \u003e 1);\\n if (!isIOS) return;\\n const apply = () =\u003e {\\n for (const meta of document.querySelectorAll('meta[name=\\\"viewport\\\"]')) {\\n const content = meta.getAttribute('content') || '';\\n if (!content.includes('maximum-scale')) {\\n meta.setAttribute('content', content + ', maximum-scale=1');\\n }\\n }\\n };\\n apply();\\n new MutationObserver(apply).observe(document.head, {\\n childList: true,\\n subtree: true,\\n attributes: true,\\n attributeFilter: ['content'],\\n });\\n})();\"}}],[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"!function(){\\nfunction read(){try{\\nvar e=performance.getEntriesByType?performance.getEntriesByType(\\\"navigation\\\"):[];\\nvar st=(e[0]\u0026\u0026e[0].serverTiming)||[];\\nvar g={};\\nfor(var i=0;i\u003cst.length;i++){var n=st[i].name,d=st[i].description;if(!d)continue;try{d=decodeURIComponent(d)}catch(x){}\\nif(n===\\\"country\\\")g.country=d;else if(n===\\\"region\\\")g.region=d;else if(n===\\\"continent\\\")g.continent=d;}\\nvar w=window;w.mintlify=w.mintlify||{};w.mintlify.geo=g;\\n}catch(x){}}\\nread();document.addEventListener(\\\"DOMContentLoaded\\\",read);\\n}();\"}}],[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"!function(){try{\\nvar w=window;w.mintlify=w.mintlify||{};\\nvar q=w.mintlify.__apiPlaygroundInputsQueue;\\nif(!Array.isArray(q)){q=[];w.mintlify.__apiPlaygroundInputsQueue=q;}\\nw.mintlify.api=w.mintlify.api||{};\\nw.mintlify.api.playground=w.mintlify.api.playground||{};\\nif(typeof w.mintlify.api.playground.setServerVariables!==\\\"function\\\"){\\nw.mintlify.api.playground.setServerVariables=function(v){q.push({type:\\\"set\\\",variables:v});};\\n}\\nif(typeof w.mintlify.api.playground.clearServerVariables!==\\\"function\\\"){\\nw.mintlify.api.playground.clearServerVariables=function(){q.push({type:\\\"clear\\\"});};\\n}\\n}catch(e){}}();\"}}],\"$L2\",\"$L3\",false]}],\"$L4\"]}]]}],{\"children\":[\"%5Fsites\",\"$L5\",{\"children\":[[\"subdomain\",\"claude-ai\",\"d\"],\"$L6\",{\"children\":[\"(multitenant)\",\"$L7\",{\"children\":[[\"slug\",\"claude-tag/overview\",\"oc\"],\"$L8\",{\"children\":[\"__PAGE__\",\"$L9\",{},null,false]},null,false]},null,false]},null,false]},null,false]},null,false],\"$La\",false]],\"m\":\"$undefined\",\"G\":[\"$b\",[\"$Lc\",\"$Ld\"]],\"s\":false,\"S\":true}\n"])</script><script>self.__next_f.push([1,"e:I[667786,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"MintlifyApiPlaygroundInputsInit\"]\nf:I[339756,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"default\"]\n10:I[556357,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/96f05c525d790774.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"default\"]\n11:I[837457,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"default\"]\n"])</script><script>self.__next_f.push([1,"12:I[894587,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"ThemeProvider\"]\n"])</script><script>self.__next_f.push([1,"13:I[152823,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"ColorVariables\"]\n"])</script><script>self.__next_f.push([1,"14:I[531961,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"FontScript\"]\n"])</script><script>self.__next_f.push([1,"15:I[649328,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"RoundedVariables\"]\n"])</script><script>self.__next_f.push([1,"16:I[702910,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"RecommendedPagesList\"]\n"])</script><script>self.__next_f.push([1,"17:I[570420,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"DataCurrentPathUpdater\"]\n18:I[172816,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"MintlifyNavigateEvents\"]\n19:I[341175,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c45fc5c3fa69ca32.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"default\"]\n1c:I[897367,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"OutletBoundary\"]\n1e:I[711533,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"AsyncMetadataOutlet\"]\n20:I[897367,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"ViewportBoundary\"]\n22:I[897367,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"MetadataBoundary\"]\n23:\"$Sreact.suspense\"\n2:[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"(function(){\\nif(typeof CSS===\\\"undefined\\\"||!(\\\"registerProperty\\\" in CSS))return;\\nif(CSS.supports\u0026\u0026CSS.supports(\\\"-webkit-backdrop-filter:none\\\"))return;\\nvar n=[\\\"--s"])</script><script>self.__next_f.push([1,"croll-area-overflow-x-start\\\",\\\"--scroll-area-overflow-x-end\\\",\\\"--scroll-area-overflow-y-start\\\",\\\"--scroll-area-overflow-y-end\\\"];\\nvar d={\\\"syntax\\\":\\\"\u003clength\u003e\\\",\\\"inherits\\\":false,\\\"initialValue\\\":\\\"0px\\\"};\\nfor(var i=0;i\u003cn.length;i++){try{CSS.registerProperty({name:n[i],syntax:d.syntax,inherits:d.inherits,initialValue:d.initialValue})}catch(e){}}\\n})();\"}}]\n"])</script><script>self.__next_f.push([1,"3:[\"$\",\"script\",null,{\"type\":\"text/javascript\",\"dangerouslySetInnerHTML\":{\"__html\":\"(function(a,b){try{let c=document.querySelector(\\\"div#banner\\\")?.innerText;if(c){for(let d=0;d\u003clocalStorage.length;d++){let e=localStorage.key(d);if(e?.endsWith(a)\u0026\u0026localStorage.getItem(e)===c)return void document.documentElement.setAttribute(b,\\\"hidden\\\")}document.documentElement.setAttribute(b,\\\"visible\\\");return}for(let c=0;c\u003clocalStorage.length;c++){let d=localStorage.key(c);if(d?.endsWith(a)\u0026\u0026localStorage.getItem(d))return void document.documentElement.setAttribute(b,\\\"hidden\\\")}document.documentElement.setAttribute(b,\\\"visible\\\")}catch(a){document.documentElement.setAttribute(b,\\\"hidden\\\")}})(\\n \\\"bannerDismissed\\\",\\n \\\"data-banner-state\\\",\\n)\"}}]\n"])</script><script>self.__next_f.push([1,"4:[\"$\",\"body\",null,{\"className\":\"antialiased\",\"children\":[[\"$\",\"$Le\",null,{}],false,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$10\",\"errorStyles\":[],\"errorScripts\":[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/96f05c525d790774.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}]],\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"$L12\",null,{\"children\":[[\"$\",\"$L13\",null,{}],[\"$\",\"$L14\",null,{}],[\"$\",\"$L15\",null,{}],[\"$\",\"style\",null,{\"children\":\":root {\\n --primary: 17 120 102;\\n --primary-light: 74 222 128;\\n --primary-dark: 22 101 52;\\n --background-light: 255 255 255;\\n --background-dark: 15 17 23;\\n}\"}],[\"$\",\"main\",null,{\"className\":\"h-screen bg-background-light dark:bg-background-dark text-left\",\"children\":[\"$\",\"article\",null,{\"className\":\"bg-custom bg-fixed bg-center bg-cover relative flex flex-col items-center justify-center h-full\",\"children\":[\"$\",\"div\",null,{\"className\":\"w-full max-w-xl px-10\",\"children\":[[\"$\",\"span\",null,{\"className\":\"inline-flex mb-6 rounded-full px-3 py-1 text-sm font-semibold mr-4 text-white p-1 bg-primary\",\"children\":[\"Error \",404]}],[\"$\",\"h1\",null,{\"className\":\"font-semibold mb-3 text-3xl\",\"children\":\"Page not found!\"}],[\"$\",\"p\",null,{\"className\":\"text-lg text-gray-600 dark:text-gray-400 mb-6\",\"children\":\"We couldn't find the page.\"}],[\"$\",\"$L16\",null,{}]]}]}]}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}],false,[\"$\",\"$L17\",null,{}],[\"$\",\"$L18\",null,{}]]}]\n"])</script><script>self.__next_f.push([1,"5:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"6:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$19\",\"errorStyles\":[],\"errorScripts\":[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/c45fc5c3fa69ca32.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true}]],\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"$L12\",null,{\"children\":[[\"$\",\"$L13\",null,{}],[\"$\",\"$L14\",null,{}],[\"$\",\"$L15\",null,{}],[\"$\",\"style\",null,{\"children\":\":root {\\n --primary: 17 120 102;\\n --primary-light: 74 222 128;\\n --primary-dark: 22 101 52;\\n --background-light: 255 255 255;\\n --background-dark: 15 17 23;\\n}\"}],[\"$\",\"main\",null,{\"className\":\"h-screen bg-background-light dark:bg-background-dark text-left\",\"children\":[\"$\",\"article\",null,{\"className\":\"bg-custom bg-fixed bg-center bg-cover relative flex flex-col items-center justify-center h-full\",\"children\":[\"$\",\"div\",null,{\"className\":\"w-full max-w-xl px-10\",\"children\":[[\"$\",\"span\",null,{\"className\":\"inline-flex mb-6 rounded-full px-3 py-1 text-sm font-semibold mr-4 text-white p-1 bg-primary\",\"children\":[\"Error \",404]}],[\"$\",\"h1\",null,{\"className\":\"font-semibold mb-3 text-3xl\",\"children\":\"Page not found!\"}],[\"$\",\"p\",null,{\"className\":\"text-lg text-gray-600 dark:text-gray-400 mb-6\",\"children\":\"We couldn't find the page.\"}],[\"$\",\"$L16\",null,{}]]}]}]}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"7:[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-4\",{\"src\":\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-5\",{\"src\":\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-6\",{\"src\":\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-7\",{\"src\":\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-8\",{\"src\":\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-9\",{\"src\":\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-10\",{\"src\":\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-11\",{\"src\":\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-12\",{\"src\":\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-13\",{\"src\":\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-14\",{\"src\":\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-15\",{\"src\":\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-16\",{\"src\":\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-17\",{\"src\":\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-18\",{\"src\":\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}]],\"$L1a\"]}]\n"])</script><script>self.__next_f.push([1,"8:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Lf\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L11\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"9:[\"$\",\"$1\",\"c\",{\"children\":[\"$L1b\",[[\"$\",\"script\",\"script-0\",{\"src\":\"/docs/_next/static/chunks/94a43ec1201b91d0.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/docs/_next/static/chunks/524bce83f7b2f674.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/docs/_next/static/chunks/1347c67505f8d6ff.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/docs/_next/static/chunks/91cc018f0b521f3f.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-4\",{\"src\":\"/docs/_next/static/chunks/1ab82a2e4905d2c6.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-5\",{\"src\":\"/docs/_next/static/chunks/e7049fc815953dcd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-6\",{\"src\":\"/docs/_next/static/chunks/f944c986e78b445f.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"$L1c\",null,{\"children\":[\"$L1d\",[\"$\",\"$L1e\",null,{\"promise\":\"$@1f\"}]]}]]}]\n"])</script><script>self.__next_f.push([1,"a:[\"$\",\"$1\",\"h\",{\"children\":[null,[[\"$\",\"$L20\",null,{\"children\":\"$L21\"}],null],[\"$\",\"$L22\",null,{\"children\":[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$23\",null,{\"fallback\":null,\"children\":\"$L24\"}]}]}]]}]\nc:[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/1ddb69276dca9f27.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]\nd:[\"$\",\"link\",\"1\",{\"rel\":\"stylesheet\",\"href\":\"/docs/_next/static/chunks/8b33240f23923228.css?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]\n"])</script><script>self.__next_f.push([1,"21:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1, viewport-fit=cover\"}]]\n1d:null\n"])</script><script>self.__next_f.push([1,"25:I[707934,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"WebMcpRegistration\"]\n"])</script><script>self.__next_f.push([1,"26:I[590280,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"LivePreviewProvider\"]\n"])</script><script>self.__next_f.push([1,"27:I[973254,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"LivePreviewFavicon\"]\n"])</script><script>self.__next_f.push([1,"28:I[197336,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\"],\"default\"]\n"])</script><script>self.__next_f.push([1,"29:I[91557,[\"/docs/_next/static/chunks/0ea0e179f06dc225.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1e7a188add93a653.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5dbc86df6bf555b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1b1b59ab8946b354.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/69d346b521ee05f9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b7de6f750ae860e1.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d3a642b23f31e8e2.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/6f6228a978343b4c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/4c2a38aad66c9452.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b2483d01d47db298.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/5c186094c9fda2b5.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/e07fdeaa7fc096e9.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/7698e61585ff109e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b241678460c3859c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/79deac81143c6431.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/d862bd6fb239b5b8.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/ad7419efb0e48aa3.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/db80d0f10b43a156.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/b6cc1d841f12879e.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/c7d45773caa7629c.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/2e9a232d689746bd.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/94a43ec1201b91d0.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/524bce83f7b2f674.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/1347c67505f8d6ff.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AVp\",\"/docs/_next/static/chunks/91cc018f0b521f3f.js?dpl=dpl_GCn6nRjMXPzUh9EXsZMh5m1Y5AV

cloud-environments Changed · +55 / -55 lines

from line 4

55> [!NOTE]

66>

7> Cloud environments apply to [cloud sessions](/docs/en/claude-code-on-the-web), which are available on Pro, Max, and Team plans, and for Enterprise users with [premium seats or Chat + Claude Code seats](https://support.claude.com/en/articles/11845131-use-claude-code-with-your-team-or-enterprise-plan).

7> Cloud environments apply to [cloud sessions](/docs/en/claude-code-on-the-web.md), which are available on Pro, Max, and Team plans, and for Enterprise users with [premium seats or Chat + Claude Code seats](https://support.claude.com/en/articles/11845131-use-claude-code-with-your-team-or-enterprise-plan).

9Each [cloud session](/docs/en/claude-code-on-the-web) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environment variables](#set-environment-variables) for the session, store [network secrets](#add-network-secrets) that sessions use without seeing them, and run a [setup script](#setup-scripts) before Claude starts working.

9Each [cloud session](/docs/en/claude-code-on-the-web.md) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environment variables](#set-environment-variables) for the session, store [network secrets](#add-network-secrets) that sessions use without seeing them, and run a [setup script](#setup-scripts) before Claude starts working.

1010

1111The same environments apply wherever you start a cloud session:

1212

13* The [Desktop app](/docs/en/desktop)

14* The [Claude mobile app](/docs/en/mobile)

13* The [Desktop app](/docs/en/desktop.md)

14* The [Claude mobile app](/docs/en/mobile.md)

1515* Your browser at [claude.ai/code](https://claude.ai/code)

1616* The terminal with [`claude --cloud`](/docs/en/claude-code-on-the-web#from-terminal-to-cloud)

17* [Cloud scheduled tasks](/docs/en/routines)

17* [Cloud scheduled tasks](/docs/en/routines.md)

1818* [Claude Tag](https://claude.com/docs/claude-tag/overview)

1919

2020Each of these surfaces can also route to a [self-hosted environment](/docs/en/self-hosted-environments). [Availability and limitations](/docs/en/self-hosted-environments#availability-and-limitations) covers what Claude can't use yet when a Claude Tag session runs in one.

from line 21

2121

2222> [!NOTE]

2323>

24> [Remote Control](/docs/en/remote-control) sessions connect the web and mobile interfaces to a session on your own machine, which uses your machine's network and files, not a cloud environment. Claude Tag channel sessions use organization-level environments only, either [shared environments](#organization-shared-environments) or [self-hosted environments](/docs/en/self-hosted-environments).

24> [Remote Control](/docs/en/remote-control.md) sessions connect the web and mobile interfaces to a session on your own machine, which uses your machine's network and files, not a cloud environment. Claude Tag channel sessions use organization-level environments only, either [shared environments](#organization-shared-environments) or [self-hosted environments](/docs/en/self-hosted-environments).

2525

2626## The Default environment

2727

from line 29

2929

3030* **CLI flows such as `/web-setup`**: create **Default** for you

3131* **Web onboarding on Pro and Max**: creates **Default** for you

32* **Web onboarding on Team and Enterprise**: shows a **Create your first cloud environment** form unless an Owner has turned on [Quick setup](/docs/en/claude-code-on-the-web#quick-setup-for-team-and-enterprise); keep the form's defaults and click **Create & finish** to get the same **Default** environment

32* **Web onboarding on Team and Enterprise**: shows a **Create your first cloud environment** form unless an Owner has turned on [Quick setup](/docs/en/claude-code-on-the-web.md#quick-setup-for-team-and-enterprise); keep the form's defaults and click **Create & finish** to get the same **Default** environment

3333

3434**Default** carries no configuration of its own:

3535

from line 38

3838

3939With only **Default** available, every session runs in it. When you have more than one environment, sessions choose one per surface:

4040

41* In the Desktop app, the mobile app, and at claude.ai/code, sessions you start yourself use the environment shown in the [selector](#configure-your-environment). An [organization default](#organization-shared-environments) set by an Owner fills the selection when you haven't picked one. Threads in a [project](/docs/en/claude-projects#project-settings-reference) use the environment set in the project's settings instead.

42* From the CLI, Claude Code uses your [`/remote-env` pick](#select-an-environment-from-the-cli), or falls back to the Anthropic-hosted environment when your list has one, and otherwise to the first environment in your list that isn't a bridge environment, an entry [Remote Control](/docs/en/remote-control) registers to represent your own machine rather than a cloud environment. For a [self-hosted environment](/docs/en/self-hosted-environments), passing `--environment <environment-id>` with its `ccpool_` ID [when you dispatch a session](/docs/en/self-hosted-environments-testing#run-the-test-loop) overrides the `/remote-env` pick and the fallback for that invocation. Claude Code rejects Anthropic-hosted `env_` IDs passed to the flag, so use `/remote-env` to target those. The flag requires Claude Code v2.1.224 or later.

41* In the Desktop app, the mobile app, and at claude.ai/code, sessions you start yourself use the environment shown in the [selector](#configure-your-environment). An [organization default](#organization-shared-environments) set by an Owner fills the selection when you haven't picked one. Threads in a [project](/docs/en/claude-projects.md#project-settings-reference) use the environment set in the project's settings instead.

42* From the CLI, Claude Code uses your [`/remote-env` pick](#select-an-environment-from-the-cli), or falls back to the Anthropic-hosted environment when your list has one, and otherwise to the first environment in your list that isn't a bridge environment, an entry [Remote Control](/docs/en/remote-control.md) registers to represent your own machine rather than a cloud environment. For a [self-hosted environment](/docs/en/self-hosted-environments), passing `--environment <environment-id>` with its `ccpool_` ID [when you dispatch a session](/docs/en/self-hosted-environments-testing.md#run-the-test-loop) overrides the `/remote-env` pick and the fallback for that invocation. Claude Code rejects Anthropic-hosted `env_` IDs passed to the flag, so use `/remote-env` to target those. The flag requires Claude Code v2.1.224 or later.

4343

4444Configure an environment when the default isn't enough: when Claude needs to reach domains outside the [default allowlist](#default-allowed-domains), needs environment variables set for its sessions, or needs dependencies installed before it starts working.

4545

4646## Configure your environment

4747

48Add, edit, and archive environments from the environment selector under the message box on the screen where you start a new session at [claude.ai/code](https://claude.ai/code). To reach that screen, complete [web onboarding](/docs/en/web-quickstart). For the Desktop app, see [Cloud sessions](/docs/en/desktop#cloud-sessions). Environments you create are personal to your account; [shared environments](#organization-shared-environments) created by an Owner appear in the selector alongside them. See [Installed tools](#installed-tools) for what's available without any configuration.

48Add, edit, and archive environments from the environment selector under the message box on the screen where you start a new session at [claude.ai/code](https://claude.ai/code). To reach that screen, complete [web onboarding](/docs/en/web-quickstart.md). For the Desktop app, see [Cloud sessions](/docs/en/desktop.md#cloud-sessions). Environments you create are personal to your account; [shared environments](#organization-shared-environments) created by an Owner appear in the selector alongside them. See [Installed tools](#installed-tools) for what's available without any configuration.

4949

5050The selector appears only until you send a new session's first message. To edit the environment of a running cloud session of your own, select the caret after the session title at the top, then select **Edit cloud environment**.

5151

from line 72

7272DATABASE_URL=postgres://localhost:5432/myapp

7373```

7474

75A session reads the environment's values into ordinary environment variables that any command Claude runs can read, except `OTEL_*` variables. Claude Code uses those for its own [telemetry export](/docs/en/monitoring-usage#telemetry-from-cloud-sessions-and-claude-tag) and doesn't pass them to the commands it runs.

75A session reads the environment's values into ordinary environment variables that any command Claude runs can read, except `OTEL_*` variables. Claude Code uses those for its own [telemetry export](/docs/en/monitoring-usage.md#telemetry-from-cloud-sessions-and-claude-tag) and doesn't pass them to the commands it runs.

7676

7777In an Anthropic-hosted environment, a session reads the environment's values when you create it and again each time Claude Code starts in the session's VM afterward, which happens in two cases:

7878

7979* **The VM is restored after being idle**: after a few minutes without activity, a session's VM pauses with its files saved. Your next message restores the same VM and starts Claude Code again.

80* **The VM was reclaimed and is rebuilt**: if the paused VM has since been [reclaimed](/docs/en/claude-code-on-the-web#environment-expired), reopening the session provisions a fresh VM.

80* **The VM was reclaimed and is rebuilt**: if the paused VM has since been [reclaimed](/docs/en/claude-code-on-the-web.md#environment-expired), reopening the session provisions a fresh VM.

8181

8282After you edit, add, or remove a variable, an existing session in an Anthropic-hosted environment keeps the values it last read until its VM is next restored or rebuilt, and uses your change from then on. Its VM pauses on its own once the session is idle, and you can't pause it yourself. To use a new value right away, ask Claude to set it on the command it runs, for example `LOG_LEVEL=trace npm test`, or start a new session.

8383

from line 148

148148* **GitHub**: the [GitHub proxy](#github-proxy) authenticates requests to GitHub instead, so you don't need a network secret for it

149149* **The Anthropic API and public package registries**: `api.anthropic.com`, `registry.npmjs.org`, `jsr.io`, `npm.jsr.io`, `pypi.org`, `files.pythonhosted.org`, `index.crates.io`, and `proxy.golang.org`

150150* **Setup script requests**: Claude Code connects to the agent proxy when it launches, after the [setup script](#setup-scripts) has run

151* **Claude Code's telemetry export**: Claude Code sends its [telemetry export](/docs/en/monitoring-usage#telemetry-from-cloud-sessions-and-claude-tag) itself rather than through a command it runs, and that request doesn't go through the agent proxy

151* **Claude Code's telemetry export**: Claude Code sends its [telemetry export](/docs/en/monitoring-usage.md#telemetry-from-cloud-sessions-and-claude-tag) itself rather than through a command it runs, and that request doesn't go through the agent proxy

152152

153153### Select an environment from the CLI

154154

155Run `/remote-env` in your terminal to choose the default environment for cloud sessions you create from the CLI, such as [`claude --cloud`](/docs/en/claude-code-on-the-web#from-terminal-to-cloud). The command opens a picker of your existing environments and saves your choice to the `remote.defaultEnvironmentId` key in your [user settings](/docs/en/settings#where-settings-live), so it applies in every project on your machine until you change it, unless the same key is set at a higher-precedence [settings layer](/docs/en/settings#settings-precedence), such as a repo's project settings.

155Run `/remote-env` in your terminal to choose the default environment for cloud sessions you create from the CLI, such as [`claude --cloud`](/docs/en/claude-code-on-the-web#from-terminal-to-cloud). The command opens a picker of your existing environments and saves your choice to the `remote.defaultEnvironmentId` key in your [user settings](/docs/en/settings.md#where-settings-live), so it applies in every project on your machine until you change it, unless the same key is set at a higher-precedence [settings layer](/docs/en/settings.md#settings-precedence), such as a repo's project settings.

156156

157157A [self-hosted environment](/docs/en/self-hosted-environments) ID, which has the form `ccpool_...`, follows a stricter source rule. See [`remote.defaultEnvironmentId`](/docs/en/settings-reference#remote-defaultenvironmentid) for the settings layers Claude Code honors it from.

158158

from line 169

169169* Network secrets on the environment stay attached in its running sessions. Delete any you no longer want before you archive.

170170* No new session can start in an archived environment, on any surface:

171171 * **Saved CLI default**: if the environment was your saved [CLI default](#select-an-environment-from-the-cli), Claude Code starts CLI cloud sessions in the Anthropic-hosted environment when your list has one. Otherwise, it starts them in the first environment in your list that isn't a [Remote Control bridge environment](#the-default-environment).

172 * **Configured explicitly**: anything configured with the environment explicitly, such as a [cloud scheduled task](/docs/en/routines#environments-and-network-access), can't start new sessions in it. Point it at another environment.

172 * **Configured explicitly**: anything configured with the environment explicitly, such as a [cloud scheduled task](/docs/en/routines.md#environments-and-network-access), can't start new sessions in it. Point it at another environment.

173173

174174When you no longer need an Anthropic-hosted environment, archive it. Neither the environment dialog nor the **Cloud environments** admin page has an option to delete an Anthropic-hosted environment. If the environment is [self-hosted](/docs/en/self-hosted-environments), an Owner can delete it from the **Cloud environments** page in admin settings. If you aren't an Owner, ask one to delete it.

175175

176176### Organization-shared environments

177177

178On Team and Enterprise plans, an Owner can create cloud environments that are shared with every member of the organization. The same role manages everything else on the **Cloud environments** admin page, including [self-hosted environments](/docs/en/self-hosted-environments); the Admin role can't open the page. The full list of roles that can open it is the one for [managing server-managed settings](/docs/en/server-managed-settings#access-control).

179179

180180Shared environments appear in each member's [environment selector](#configure-your-environment) under an **Organization** heading, after the member's own environments under **Personal**, so a team can standardize on one configuration instead of each member recreating it. Selecting a shared environment's settings icon there opens a read-only summary of its configuration for every member, Owners included.

181181

from line 199

199199

200200Each environment sets one network access level, which controls the outbound connections its sessions can make. The default level, **Trusted**, allows package registries and other [allowlisted domains](#default-allowed-domains); **Custom** takes your own domain list.

201201

202To change an environment's network access, [open it for editing](#configure-your-environment) and use the **Network access** selector in the dialog. A [shared environment](#organization-shared-environments) opens read-only there, so an Owner changes its network access from the **Cloud environments** page in [admin settings](https://claude.ai/admin-settings) instead. The control that opens the selector appears on the app surfaces listed under [The Default environment](#the-default-environment) and in the [cloud scheduled task editor](/docs/en/routines#environments-and-network-access). Personal environments don't have a separate page in your claude.ai account settings.

202To change an environment's network access, [open it for editing](#configure-your-environment) and use the **Network access** selector in the dialog. A [shared environment](#organization-shared-environments) opens read-only there, so an Owner changes its network access from the **Cloud environments** page in [admin settings](https://claude.ai/admin-settings) instead. The control that opens the selector appears on the app surfaces listed under [The Default environment](#the-default-environment) and in the [cloud scheduled task editor](/docs/en/routines.md#environments-and-network-access). Personal environments don't have a separate page in your claude.ai account settings.

203203

204204When you change an Anthropic-hosted environment's network access, its existing sessions follow the new setting within about a minute, for requests that go through the session's [network allowlist](#access-levels). You don't need to start a new session.

205205

206206> [!NOTE]

207207>

208> MCP connectors you enable on a session or scheduled task work without adding their hosts to **Allowed domains**, because connector traffic travels through Anthropic's servers rather than the session's network. This relies on the same Anthropic-bound channel noted under [Security and isolation](/docs/en/claude-code-on-the-web#security-and-isolation). Turn off any connector you don't need to limit which tools Claude can reach.

208> MCP connectors you enable on a session or scheduled task work without adding their hosts to **Allowed domains**, because connector traffic travels through Anthropic's servers rather than the session's network. This relies on the same Anthropic-bound channel noted under [Security and isolation](/docs/en/claude-code-on-the-web.md#security-and-isolation). Turn off any connector you don't need to limit which tools Claude can reach.

209209

210210### Access levels

211211

from line 223

223223* GitHub, through its [separate proxy](#github-proxy)

224224* [MCP connectors](#network-access) you enable, whose traffic travels through Anthropic's servers

225225* The hosts you listed on the environment's [network secrets](#add-network-secrets), except the [hosts that never get the secret](#requests-that-never-get-the-credential)

226* The Anthropic API, for Claude Code's own requests, even at **None**, as noted under [Security and isolation](/docs/en/claude-code-on-the-web#security-and-isolation)

226* The Anthropic API, for Claude Code's own requests, even at **None**, as noted under [Security and isolation](/docs/en/claude-code-on-the-web.md#security-and-isolation)

227227

228228### Allow specific domains

229229

from line 237

237237

238238Sessions in this environment can now reach `api.example.com`, any subdomain of `internal.example.com`, and `registry.example.com`, and no other domains through the session's network. [GitHub traffic](#github-proxy), [MCP connector traffic](#network-access), and requests to the hosts of the environment's [network secrets](#add-network-secrets), other than the [hosts that never get the secret](#requests-that-never-get-the-credential), don't go through this allowlist. A leading `*.` matches every subdomain. To keep the [Trusted domains](#default-allowed-domains) too, check **Also include default list of common package managers**; leave it unchecked to allow only what you list.

239239

240If your organization uses [artifacts](/docs/en/artifacts#availability), you don't need `*.frame.claudeusercontent.com` in the list for sessions to read them. When the list leaves that host out, Claude Code reads artifact content through the session's connection to Anthropic instead. Keep the host in an allowlist in two situations:

240If your organization uses [artifacts](/docs/en/artifacts.md#availability), you don't need `*.frame.claudeusercontent.com` in the list for sessions to read them. When the list leaves that host out, Claude Code reads artifact content through the session's connection to Anthropic instead. Keep the host in an allowlist in two situations:

241241

242242* **Sessions in this environment open another organization's public artifacts**: Claude Code fetches those from the host directly, so add it to this list.

243* **You're configuring the local CLI or a self-hosted runner**: keep the host in that allowlist. See [network access requirements](/docs/en/network-config#network-access-requirements) and the self-hosted [network requirements](/docs/en/self-hosted-environments-deploy#network-requirements).

243* **You're configuring the local CLI or a self-hosted runner**: keep the host in that allowlist. See [network access requirements](/docs/en/network-config.md#network-access-requirements) and the self-hosted [network requirements](/docs/en/self-hosted-environments-deploy.md#network-requirements).

244244

245Each environment has its own allowed-domains list; there's no organization-level allowlist that admins can push to every member's environments. No [server-managed setting](/docs/en/server-managed-settings) adds domains to an environment's network allowlist either. To give a team one standard list, an Owner can create an [organization-shared environment](#organization-shared-environments) with **Custom** network access and that list.

245Each environment has its own allowed-domains list; there's no organization-level allowlist that admins can push to every member's environments. No [server-managed setting](/docs/en/server-managed-settings.md) adds domains to an environment's network allowlist either. To give a team one standard list, an Owner can create an [organization-shared environment](#organization-shared-environments) with **Custom** network access and that list.

246246

247247### GitHub proxy

248248

249In Anthropic-hosted environments, all GitHub operations go through a dedicated proxy that keeps your real GitHub credentials outside the session's VM, independent of the environment's [access level](#access-levels). Sessions in a self-hosted environment authenticate git operations with credentials your deployment provides; [Configure git](/docs/en/self-hosted-environments-deploy#configure-git) covers the options, including per-session minted credentials and an opt-in to this same proxy. The proxy provides:

249In Anthropic-hosted environments, all GitHub operations go through a dedicated proxy that keeps your real GitHub credentials outside the session's VM, independent of the environment's [access level](#access-levels). Sessions in a self-hosted environment authenticate git operations with credentials your deployment provides; [Configure git](/docs/en/self-hosted-environments-deploy.md#configure-git) covers the options, including per-session minted credentials and an opt-in to this same proxy. The proxy provides:

250250

251251* **Git credentials**: the git client inside the VM uses a scoped credential, which the proxy verifies and swaps for your actual GitHub token.

252252* **API requests**: requests from the built-in GitHub tools, and from `gh` under the [`proxy-injected` placeholder](#work-with-github-issues-and-pull-requests), go out with your real credentials substituted.

from line 258

258258

259259### Security proxy

260260

261Cloud sessions in Anthropic-hosted environments run behind an HTTP/HTTPS network proxy for security and abuse prevention purposes; in a [self-hosted environment](/docs/en/self-hosted-environments-deploy#default-deny-egress), outbound traffic leaves through your own network boundary instead. All outbound internet traffic from an Anthropic-hosted session passes through this proxy, which provides:

261Cloud sessions in Anthropic-hosted environments run behind an HTTP/HTTPS network proxy for security and abuse prevention purposes; in a [self-hosted environment](/docs/en/self-hosted-environments-deploy.md#default-deny-egress), outbound traffic leaves through your own network boundary instead. All outbound internet traffic from an Anthropic-hosted session passes through this proxy, which provides:

262262

263263* Protection against malicious requests

264264* Rate limiting and abuse prevention

from line 275

275275

276276> [!NOTE]

277277>

278> Of the repository configuration in this table, a cloud thread in a [project](/docs/en/claude-projects) loads only the repository root's `CLAUDE.md`, `.claude/CLAUDE.md`, and `.claude/rules/` files that aren't [path-specific](/docs/en/memory#path-specific-rules). See [What threads pick up from your repositories](/docs/en/claude-projects#what-threads-pick-up-from-your-repositories).

278> Of the repository configuration in this table, a cloud thread in a [project](/docs/en/claude-projects.md) loads only the repository root's `CLAUDE.md`, `.claude/CLAUDE.md`, and `.claude/rules/` files that aren't [path-specific](/docs/en/memory.md#path-specific-rules). See [What threads pick up from your repositories](/docs/en/claude-projects.md#what-threads-pick-up-from-your-repositories).

279279

280Cloud sessions start from a fresh clone of your repository. Anything you commit to the repo is available. Anything you've installed or configured only on your own machine isn't available in the session. Your organization's policy arrives separately through [server-managed settings](/docs/en/server-managed-settings).

281281

282282| | Available in cloud sessions | Why |

283283| :- | :- | :- |

284284| Your repo's `CLAUDE.md` | Yes | Part of the clone |

285| Your repo's `.claude/settings.json` hooks and permission rules | Yes, in a session with one repository | Part of the clone. For a session with several repositories, see [which settings it reads](/docs/en/settings#settings-in-cloud-sessions) |

286| Your repo's `.mcp.json` MCP servers | Yes, in a session with one repository | Part of the clone, found from the session's working directory. For a self-hosted environment, see [which repository's settings apply](/docs/en/self-hosted-environments-configuration#repository-settings-in-sessions-with-several-repositories) |

286| Your repo's `.mcp.json` MCP servers | Yes, in a session with one repository | Part of the clone, found from the session's working directory. For a self-hosted environment, see [which repository's settings apply](/docs/en/self-hosted-environments-configuration.md#repository-settings-in-sessions-with-several-repositories) |

287287| Your repo's `.claude/rules/` | Yes | Part of the clone |

288288| Your repo's `.claude/skills/`, `.claude/agents/`, `.claude/commands/` | Yes | Part of the clone |

289289| Plugins and marketplaces declared in your repo's `.claude/settings.json` | No | A cloud session doesn't install the plugins a repository turns on under [`enabledPlugins`](/docs/en/settings-reference#enabledplugins), including ones from the marketplaces it lists under [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces) |

290| Your organization's [server-managed settings](/docs/en/server-managed-settings) | Yes, except in [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions | Fetched from Anthropic's servers when the session starts. See [Surface coverage](/docs/en/model-config#surface-coverage) for how `availableModels` is enforced in cloud sessions. Settings deployed to your device through MDM or managed settings files don't apply, because the session runs on an Anthropic-managed VM; in a [self-hosted environment](/docs/en/self-hosted-environments), sessions also read the managed settings file in the runner image, per [how Claude Code combines managed sources](/docs/en/managed-settings#how-claude-code-combines-managed-sources) |

290| Your organization's [server-managed settings](/docs/en/server-managed-settings.md) | Yes, except in [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions | Fetched from Anthropic's servers when the session starts. See [Surface coverage](/docs/en/model-config.md#surface-coverage) for how `availableModels` is enforced in cloud sessions. Settings deployed to your device through MDM or managed settings files don't apply, because the session runs on an Anthropic-managed VM; in a [self-hosted environment](/docs/en/self-hosted-environments), sessions also read the managed settings file in the runner image, per [how Claude Code combines managed sources](/docs/en/managed-settings.md#how-claude-code-combines-managed-sources) |

291291| Your user `~/.claude/CLAUDE.md` | No | Lives on your machine, not in the repo. See [Add personal preferences without committing to the repo](#add-personal-preferences-without-committing-to-the-repo) |

292| Your user `~/.claude/skills/`, `~/.claude/agents/`, `~/.claude/commands/` | No | Live on your machine, not in the repo. Commit them to the repo's `.claude/` directory instead. Cloud sessions automatically load [skills you enable on claude.ai](/docs/en/skills#skills-in-cowork-and-cloud-sessions) |

293293| Plugins enabled only in your user settings | No | User-scoped `enabledPlugins` lives in `~/.claude/settings.json` on your machine |

294294| MCP servers you added with `claude mcp add` at the default local scope or the user scope | No | Those write to `~/.claude.json` on your machine, not the repo. Add the server with `claude mcp add --scope project`, which writes the repo's [`.mcp.json`](/docs/en/mcp#project-scope), and commit that file. A session with one repository loads it |

295| Transport variables in your repo's `.claude/settings.json` `env` block, such as `NODE_EXTRA_CA_CERTS` and the [mTLS client certificate variables](/docs/en/network-config#mtls-authentication) | No | The hosting environment manages the session's API connection, so Claude Code ignores these keys and notes each ignored key in the session's debug log |

295| Transport variables in your repo's `.claude/settings.json` `env` block, such as `NODE_EXTRA_CA_CERTS` and the [mTLS client certificate variables](/docs/en/network-config.md#mtls-authentication) | No | The hosting environment manages the session's API connection, so Claude Code ignores these keys and notes each ignored key in the session's debug log |

296296| API keys and tokens for services Claude calls | In an Anthropic-hosted environment, as [network secrets](#add-network-secrets) | You add the key once on the environment and the agent proxy attaches it to requests for the hosts you list. A key the agent proxy [can't attach](#requests-that-never-get-the-credential) stays in an environment variable |

297297| Interactive auth like AWS SSO | No | Not supported. SSO requires browser-based login that can't run in a cloud session |

298298

from line 302

302302

303303#### Add personal preferences without committing to the repo

304304

305In an Anthropic-hosted environment, add a [setup script](#setup-scripts) that writes `~/.claude/CLAUDE.md` for preferences you'd rather not put in a shared repository. Claude Code loads that file as [user instructions](/docs/en/memory#choose-where-to-put-claude-md-files) in the session. This example sets a commit-message preference:

305In an Anthropic-hosted environment, add a [setup script](#setup-scripts) that writes `~/.claude/CLAUDE.md` for preferences you'd rather not put in a shared repository. Claude Code loads that file as [user instructions](/docs/en/memory.md#choose-where-to-put-claude-md-files) in the session. This example sets a commit-message preference:

306306

307307```bash theme={null}

308308#!/bin/bash

from line 344

344344

345345### Work with GitHub issues and pull requests

346346

347Cloud sessions include built-in GitHub tools that let Claude read issues, list pull requests, fetch diffs, and post comments without any setup. These tools authenticate through the [GitHub proxy](#github-proxy) using whichever method you configured under [GitHub authentication options](/docs/en/claude-code-on-the-web#github-authentication-options), so your token never enters the container.

347Cloud sessions include built-in GitHub tools that let Claude read issues, list pull requests, fetch diffs, and post comments without any setup. These tools authenticate through the [GitHub proxy](#github-proxy) using whichever method you configured under [GitHub authentication options](/docs/en/claude-code-on-the-web.md#github-authentication-options), so your token never enters the container.

348348

349349You can set `GH_TOKEN` or `GITHUB_TOKEN` yourself in [environment settings](#set-environment-variables), or leave both unset and let the [GitHub proxy](#github-proxy) authenticate for you:

350350

from line 405

405405* 16 GB of RAM

406406* 30 GB of disk

407407

408The VM may stop tasks that need significantly more memory, such as large build jobs or memory-intensive tests. For workloads beyond these limits, use [Remote Control](/docs/en/remote-control) to run Claude Code on your own hardware, or run cloud sessions in a [self-hosted environment](/docs/en/self-hosted-environments) on compute your organization operates.

408The VM may stop tasks that need significantly more memory, such as large build jobs or memory-intensive tests. For workloads beyond these limits, use [Remote Control](/docs/en/remote-control.md) to run Claude Code on your own hardware, or run cloud sessions in a [self-hosted environment](/docs/en/self-hosted-environments) on compute your organization operates.

409409

410410### Time limits

411411

from line 413

413413

414414* **Commands Claude runs**: a cloud environment doesn't set its own command timeout, so the Bash tool's defaults apply. Claude waits 2 minutes for a foreground command by default and can ask for up to 10 minutes.

415415

416 When a command reaches its [timeout](/docs/en/tools-reference#timeout-and-output-limits), Claude Code [moves it to the background](/docs/en/tools-reference#foreground-commands-that-move-to-the-background) instead of stopping it, unless the command starts with `sleep`. A command moved this way can keep running for up to 30 more minutes before Claude Code stops it at its [background time limit](/docs/en/tools-reference#time-limit-for-background-commands). Setting `BASH_DEFAULT_TIMEOUT_MS` above `1800000` milliseconds lengthens that limit as well as the foreground default.

416 When a command reaches its [timeout](/docs/en/tools-reference.md#timeout-and-output-limits), Claude Code [moves it to the background](/docs/en/tools-reference.md#foreground-commands-that-move-to-the-background) instead of stopping it, unless the command starts with `sleep`. A command moved this way can keep running for up to 30 more minutes before Claude Code stops it at its [background time limit](/docs/en/tools-reference.md#time-limit-for-background-commands). Setting `BASH_DEFAULT_TIMEOUT_MS` above `1800000` milliseconds lengthens that limit as well as the foreground default.

417417* **SessionStart hooks**: Claude Code cancels a `command` hook after 600 seconds unless you set [`timeout`](/docs/en/hooks#common-fields), in seconds, on the hook entry. Claude Code doesn't enforce the timeout on a hook you run with [`async: true`](/docs/en/hooks#run-hooks-in-the-background).

418418* **Setup script**: a script that takes longer than roughly five minutes isn't cached. [Script requirements](#script-requirements) covers how to stay under that.

419* **Idle sessions**: after a few minutes without activity, a session's VM pauses with its files saved, and a paused VM can later be reclaimed. [Set environment variables](#set-environment-variables) describes what a session picks up in each case, and [Environment expired](/docs/en/claude-code-on-the-web#environment-expired) covers how to reopen a session whose VM was reclaimed.

419* **Idle sessions**: after a few minutes without activity, a session's VM pauses with its files saved, and a paused VM can later be reclaimed. [Set environment variables](#set-environment-variables) describes what a session picks up in each case, and [Environment expired](/docs/en/claude-code-on-the-web.md#environment-expired) covers how to reopen a session whose VM was reclaimed.

420420

421421To raise the command timeouts for an environment's sessions, add [`BASH_DEFAULT_TIMEOUT_MS` and `BASH_MAX_TIMEOUT_MS`](/docs/en/env-vars#variables) to its [environment variables](#set-environment-variables). Both take milliseconds. For example, `BASH_DEFAULT_TIMEOUT_MS=600000` makes 10 minutes the default.

422422

from line 440

440440A setup script has three constraints to write around:

441441

442442* **Exit zero**: if the script exits non-zero, the session fails to start. Append `|| true` to non-critical commands so an intermittent install failure doesn't block the session.

443* **Finish within five minutes**: keep the script's total runtime under roughly five minutes so the [environment cache](#environment-caching) can build. When setup takes longer than that, the environment isn't cached. Run independent installs in parallel with `&` and `wait`, and move any single download that won't fit into a [SessionStart hook](#setup-scripts-vs-sessionstart-hooks) that launches it in the background. If new sessions stall or fail during setup, see [New sessions hang or time out during setup](/docs/en/web-quickstart#new-sessions-hang-or-time-out-during-setup).

444444* **Network access for installs**: package installs need to reach registries. The default **Trusted** level covers [common package registries](#default-allowed-domains) including npm, PyPI, RubyGems, and crates.io; with **None** network access, installs fail.

445445

446446### Environment caching

from line 449

449449

450450The cache is a filesystem snapshot, so it keeps what the setup script writes to disk and loses anything that was only running. Packages you install, Docker images you pull, and files you write all carry over. A database the script started, a `docker compose up` stack, or any other background process doesn't; start those per session by asking Claude or with a [SessionStart hook](#setup-scripts-vs-sessionstart-hooks).

451451

452The setup script runs again to rebuild the cache when you change the environment's setup script or allowed network hosts, and when the cache reaches its expiry after roughly seven days. In an Anthropic-hosted environment, the setup script doesn't run when a session's VM is [restored after being idle](#set-environment-variables), so a change to the script reaches an existing session only when its VM was [reclaimed](/docs/en/claude-code-on-the-web#environment-expired) and is rebuilt. To apply a change right away, run the commands in the session or start a new session.

452The setup script runs again to rebuild the cache when you change the environment's setup script or allowed network hosts, and when the cache reaches its expiry after roughly seven days. In an Anthropic-hosted environment, the setup script doesn't run when a session's VM is [restored after being idle](#set-environment-variables), so a change to the script reaches an existing session only when its VM was [reclaimed](/docs/en/claude-code-on-the-web.md#environment-expired) and is rebuilt. To apply a change right away, run the commands in the session or start a new session.

453453

454454You don't need to enable caching or manage snapshots yourself.

455455

456456### Setup scripts vs. SessionStart hooks

457457

458Use a setup script to provision the VM itself: toolchains and CLI tools that aren't [pre-installed](#installed-tools). Use a [SessionStart hook](/docs/en/hooks#sessionstart) for project setup that should run everywhere, cloud and local, like `npm install`.

458Use a setup script to provision the VM itself: toolchains and CLI tools that aren't [pre-installed](#installed-tools). Use a [SessionStart hook](/docs/en/hooks.md#sessionstart) for project setup that should run everywhere, cloud and local, like `npm install`.

459459

460460Setup scripts and SessionStart hooks run in a fixed order when a cloud session starts. The table compares where you configure them, when they run, and where they run.

461461

462462| | Setup scripts | SessionStart hooks |

463463| - | - | - |

464| **Where you configure them** | The environment dialog at [claude.ai/code](https://claude.ai/code), plus the **Cloud environments** admin page for [shared environments](#organization-shared-environments) | A [settings file](/docs/en/settings#where-settings-live) such as your repo's `.claude/settings.json`; see [What carries over from your setup](#what-carries-over-from-your-setup) for which files reach a cloud session |

464| **Where you configure them** | The environment dialog at [claude.ai/code](https://claude.ai/code), plus the **Cloud environments** admin page for [shared environments](#organization-shared-environments) | A [settings file](/docs/en/settings.md#where-settings-live) such as your repo's `.claude/settings.json`; see [What carries over from your setup](#what-carries-over-from-your-setup) for which files reach a cloud session |

465465| **When they run** | Before Claude Code launches, skipped when a [cached environment](#environment-caching) exists | After Claude Code launches, on every session including resumed |

466466| **Where they run** | Cloud sessions only | Local and cloud sessions |

467467

468468If you have SessionStart hooks in your user-level `~/.claude/settings.json`, don't expect them in the cloud. User-level settings stay on your machine. Which other hooks run depends on where the session runs:

469469

470* **Anthropic-hosted environment**: Claude Code runs hooks from your organization's [server-managed settings](/docs/en/server-managed-settings) and, outside a [project](/docs/en/claude-projects#what-threads-pick-up-from-your-repositories) thread, from the repository. [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions don't receive server-managed settings, so hooks from server-managed settings don't run there.

471* **[Self-hosted environment](/docs/en/self-hosted-environments-configuration#permissions-and-tool-approval)**: Claude Code also runs the hooks the operator seeded from the runner host's `~/.claude/`, and the hooks in the runner image's managed settings file when that file is one of the [managed sources Claude Code applies](/docs/en/managed-settings#how-claude-code-combines-managed-sources).

470* **Anthropic-hosted environment**: Claude Code runs hooks from your organization's [server-managed settings](/docs/en/server-managed-settings.md) and, outside a [project](/docs/en/claude-projects.md#what-threads-pick-up-from-your-repositories) thread, from the repository. [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions don't receive server-managed settings, so hooks from server-managed settings don't run there.

471* **[Self-hosted environment](/docs/en/self-hosted-environments-configuration.md#permissions-and-tool-approval)**: Claude Code also runs the hooks the operator seeded from the runner host's `~/.claude/`, and the hooks in the runner image's managed settings file when that file is one of the [managed sources Claude Code applies](/docs/en/managed-settings.md#how-claude-code-combines-managed-sources).

472472

473473### Install dependencies with a SessionStart hook

474474

475To install dependencies only in cloud sessions outside a [project](/docs/en/claude-projects#what-threads-pick-up-from-your-repositories)'s threads, pair a SessionStart hook with a script that checks where it's running.

475To install dependencies only in cloud sessions outside a [project](/docs/en/claude-projects.md#what-threads-pick-up-from-your-repositories)'s threads, pair a SessionStart hook with a script that checks where it's running.

476476

477477First, add a SessionStart hook to your repo's `.claude/settings.json`. This configuration tells Claude Code to run `scripts/install_pkgs.sh` from your repository whenever a session starts or resumes:

478478

from line 533

533533

534534SessionStart hooks behave the same in the cloud as locally, with these caveats:

535535

536* **One repository per session**: in an Anthropic-hosted environment, a session with several repositories doesn't load hooks from any repository's `.claude/settings.json`, so a SessionStart hook you define there doesn't run. Install dependencies for those sessions with a [setup script](#setup-scripts) instead. For a self-hosted environment, see [which repository's settings apply](/docs/en/self-hosted-environments-configuration#repository-settings-in-sessions-with-several-repositories).

537* **Not in a project's cloud threads**: a cloud thread in a [project](/docs/en/claude-projects#what-threads-pick-up-from-your-repositories) doesn't run hooks from a repository's `.claude/settings.json`, whatever the number of repositories. In an Anthropic-hosted environment, install dependencies for threads with a [setup script](#setup-scripts). In a self-hosted environment, use a hook in the [runner host's settings](/docs/en/self-hosted-environments-configuration#repository-settings-in-sessions-with-several-repositories) instead.

536* **One repository per session**: in an Anthropic-hosted environment, a session with several repositories doesn't load hooks from any repository's `.claude/settings.json`, so a SessionStart hook you define there doesn't run. Install dependencies for those sessions with a [setup script](#setup-scripts) instead. For a self-hosted environment, see [which repository's settings apply](/docs/en/self-hosted-environments-configuration.md#repository-settings-in-sessions-with-several-repositories).

537* **Not in a project's cloud threads**: a cloud thread in a [project](/docs/en/claude-projects.md#what-threads-pick-up-from-your-repositories) doesn't run hooks from a repository's `.claude/settings.json`, whatever the number of repositories. In an Anthropic-hosted environment, install dependencies for threads with a [setup script](#setup-scripts). In a self-hosted environment, use a hook in the [runner host's settings](/docs/en/self-hosted-environments-configuration.md#repository-settings-in-sessions-with-several-repositories) instead.

538538* **No cloud-only scoping**: hooks run in both local and cloud sessions. To skip local execution, exit early unless the `CLAUDE_CODE_REMOTE` environment variable is `true`, the way the [dependency install script](#install-dependencies-with-a-sessionstart-hook) does.

539539* **Requires network access**: install commands need to reach package registries. If your environment uses **None** network access, these hooks fail. The [default allowlist](#default-allowed-domains) under **Trusted** covers npm, PyPI, RubyGems, and crates.io.

540* **Proxy compatibility**: in Anthropic-hosted environments, all outbound traffic passes through a [security proxy](#security-proxy), and some package managers don't work correctly with it; Bun is a known example. In a [self-hosted environment](/docs/en/self-hosted-environments-deploy#default-deny-egress), outbound traffic goes through your own network boundary instead.

540* **Proxy compatibility**: in Anthropic-hosted environments, all outbound traffic passes through a [security proxy](#security-proxy), and some package managers don't work correctly with it; Bun is a known example. In a [self-hosted environment](/docs/en/self-hosted-environments-deploy.md#default-deny-egress), outbound traffic goes through your own network boundary instead.

541541* **Adds startup latency**: hooks run each time a session starts or resumes, unlike setup scripts which benefit from [environment caching](#environment-caching). Keep install scripts fast by skipping work that's already done, the way the [dependency install script](#install-dependencies-with-a-sessionstart-hook) does.

542542

543543To customize the base image, use a setup script to install what you need on top of the [provided image](#installed-tools), or run your own image as a container alongside Claude with `docker compose`. Replacing the base image entirely isn't supported yet.

from line 803

803803

804804## Related resources

805805

806* [Cloud sessions reference](/docs/en/claude-code-on-the-web): start, manage, and share cloud sessions

807* [Cloud sessions quickstart](/docs/en/web-quickstart): connect GitHub and start your first cloud session

806* [Cloud sessions reference](/docs/en/claude-code-on-the-web.md): start, manage, and share cloud sessions

807* [Cloud sessions quickstart](/docs/en/web-quickstart.md): connect GitHub and start your first cloud session

808808* [Claude Tag](https://claude.com/docs/claude-tag/overview): sessions Claude starts from Slack run in the same environments

809* [Cloud scheduled tasks](/docs/en/routines): scheduled runs use the same environments and network access levels

810* [Remote Control](/docs/en/remote-control): run sessions on your own machine's network and files instead

809* [Cloud scheduled tasks](/docs/en/routines.md): scheduled runs use the same environments and network access levels

810* [Remote Control](/docs/en/remote-control.md): run sessions on your own machine's network and files instead

811811* [Self-hosted environments](/docs/en/self-hosted-environments): run cloud sessions on your organization's own infrastructure

812* [SessionStart hooks](/docs/en/hooks#sessionstart): repo-committed setup that runs in local and cloud sessions

813* [Server-managed settings](/docs/en/server-managed-settings): organization policy delivered from the admin console

812* [SessionStart hooks](/docs/en/hooks.md#sessionstart): repo-committed setup that runs in local and cloud sessions

813* [Server-managed settings](/docs/en/server-managed-settings.md): organization policy delivered from the admin console

814814

code-review-costs Changed · +10 / -10 lines

from line 2

33> Estimate and cap what your organization spends on Claude Code Review: how reviews are billed through usage credits, what drives cost, and where to track usage.

5[Code Review](/docs/en/code-review) has no flat per-review price. What you spend depends on the cost of each review and on how many reviews run:

5[Code Review](/docs/en/code-review.md) has no flat per-review price. What you spend depends on the cost of each review and on how many reviews run:

7* **Cost of each review**: scales with the [review level](/docs/en/code-review-setup#set-the-default-review-level), the size of the change, the complexity of the surrounding code, and how many candidate issues need verification

7* **Cost of each review**: scales with the [review level](/docs/en/code-review-setup.md#set-the-default-review-level), the size of the change, the complexity of the surrounding code, and how many candidate issues need verification

88* **Number of reviews**: set by [how often reviews run](#how-often-reviews-run) in each repository

1010## Pricing

from line 13

1313

1414### How often reviews run

1515

16A repository you add from the admin page starts at **After every push**, which runs the most reviews. Each repository's [**Review runs** setting](/docs/en/code-review-setup#set-when-reviews-run) decides how many reviews a pull request gets:

16A repository you add from the admin page starts at **After every push**, which runs the most reviews. Each repository's [**Review runs** setting](/docs/en/code-review-setup.md#set-when-reviews-run) decides how many reviews a pull request gets:

1717

1818* **Once after PR creation**: a review runs when the pull request is opened, reopened, or marked ready for review

1919* **After every push**: runs on each push, multiplying cost by the number of pushes

from line 21

2121

2222Comment commands, drafts, and pull requests from forks adjust those counts:

2323

24* **`@claude review always` in Once after PR creation or Manual mode**: [opts the PR into push-triggered reviews](/docs/en/code-review-pull-requests#comment-commands), so additional cost accrues per push after that comment

24* **`@claude review always` in Once after PR creation or Manual mode**: [opts the PR into push-triggered reviews](/docs/en/code-review-pull-requests.md#comment-commands), so additional cost accrues per push after that comment

2525* **`@claude review always` in After every push mode**: pushes already trigger reviews, so the subscription doesn't change per-push cost

2626* **`@claude review`**: runs a single review without subscribing to future pushes

27* **Drafts and pull requests from forks**: [automatic reviews skip both](/docs/en/code-review-pull-requests#review-drafts-and-pull-requests-from-forks), so pushes to them don't add reviews

27* **Drafts and pull requests from forks**: [automatic reviews skip both](/docs/en/code-review-pull-requests.md#review-drafts-and-pull-requests-from-forks), so pushes to them don't add reviews

2828

2929## Estimate your spend

3030

from line 47

4747* **Organization spend limit**: your organization's overall monthly spend limit for usage credits. Raise it on the same page.

4848* **Usage credits balance**: your organization's balance of usage credits. Add credits on the same page.

4949

50Code Review also skips reviews once what's left is less than the expected cost of one review. When a review is skipped, developers see a [comment on the PR](/docs/en/code-review-troubleshooting#review-didn’t-run-and-the-pr-shows-a-budget-message) that names the cause and links to the usage settings.

50Code Review also skips reviews once what's left is less than the expected cost of one review. When a review is skipped, developers see a [comment on the PR](/docs/en/code-review-troubleshooting.md#review-didn’t-run-and-the-pr-shows-a-budget-message) that names the cause and links to the usage settings.

5151

5252To monitor spend, use the [analytics dashboard](#view-usage).

5353

from line 66

6666

6767## Related resources

6868

69* [Set up Code Review](/docs/en/code-review-setup): where to choose the review level and when reviews run in each repository

70* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests): the comment commands, pull requests from forks, and the budget message developers see when a review is skipped

71* [Code Review](/docs/en/code-review): what a review checks and what it posts

72* [Manage costs effectively](/docs/en/costs): spend controls and usage tracking for the rest of Claude Code

69* [Set up Code Review](/docs/en/code-review-setup.md): where to choose the review level and when reviews run in each repository

70* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests.md): the comment commands, pull requests from forks, and the budget message developers see when a review is skipped

71* [Code Review](/docs/en/code-review.md): what a review checks and what it posts

72* [Manage costs effectively](/docs/en/costs.md): spend controls and usage tracking for the rest of Claude Code

7373

code-review-customize Changed · +10 / -10 lines

from line 2

33> Tune what Code Review flags on your pull requests with REVIEW.md and CLAUDE.md: recalibrate severity, skip paths, add checks, and see which copy applies.

5You can change what [Code Review](/docs/en/code-review) flags on your repository by committing instructions to it. This is how you cut nit volume, stop comments on generated files, or add a rule your team cares about. Put them in one of two files:

5You can change what [Code Review](/docs/en/code-review.md) flags on your repository by committing instructions to it. This is how you cut nit volume, stop comments on generated files, or add a rule your team cares about. Put them in one of two files:

7* **`CLAUDE.md`**: [project instructions](/docs/en/memory) that Claude Code reads for every task, reviews included. Code Review reads them as project context and flags changes that violate them.

7* **`CLAUDE.md`**: [project instructions](/docs/en/memory.md) that Claude Code reads for every task, reviews included. Code Review reads them as project context and flags changes that violate them.

88* **`REVIEW.md`**: instructions for reviews alone. Use it to say what your team wants flagged, at what severity, and what to skip.

1010Add `REVIEW.md` at your repository root and merge it. Then [protect your default branch](#which-branch-review-md-is-read-from).

from line 11

1111

1212> [!NOTE]

1313>

14> To change how thorough reviews are or when they run, ask an Owner to change the [review level](/docs/en/code-review-setup#set-the-default-review-level) or the [**Review runs** setting](/docs/en/code-review-setup#set-when-reviews-run).

14> To change how thorough reviews are or when they run, ask an Owner to change the [review level](/docs/en/code-review-setup.md#set-the-default-review-level) or the [**Review runs** setting](/docs/en/code-review-setup.md#set-when-reviews-run).

1515

1616## Use CLAUDE.md for project-wide rules

1717

18Code Review reads your repository's `CLAUDE.md` files as project context. A change that violates one of their rules becomes a finding at whichever [severity level](/docs/en/code-review-pull-requests#severity-levels) fits the issue.

1919

2020A review reads the `CLAUDE.md` at your repository root and the `CLAUDE.md` files in the parent directories of each changed file. A subdirectory's `CLAUDE.md` is read when the pull request changes a file under that path.

2121

from line 123

123123* **Name**: match the file name exactly, including case, and use a name without spaces. A line whose name matches no file beside `REVIEW.md` stays in `REVIEW.md` as plain text, and the check run doesn't report it as a skipped include.

124124* **One level**: list every file in the root `REVIEW.md`. An `@` line in an included file or in a subdirectory `REVIEW.md` stays as plain text, and a Markdown link to another file isn't an include.

125125* **Limits**: include at most eight different files, and keep `REVIEW.md` and the files it includes under 150,000 bytes combined. A file that would reach the byte limit is skipped whole, not cut short. The check run reports how many include lines it skipped for either limit.

126* **Links**: keep Markdown links at 64 or fewer across `REVIEW.md` and the files it includes. Links to `http`, `https`, or `mailto` addresses and to `#` anchors don't count. Past that limit, the review skips your whole root `REVIEW.md`, not only the included files. The check run then [says the instructions weren't applied](/docs/en/code-review-troubleshooting#the-check-run-mentions-review-md).

127127* **Merged copy**: merge the included file into the [branch `REVIEW.md` is read from](#which-branch-review-md-is-read-from). The review reads both from the same commit, never from the pull request's own changes.

128128

129129### Which branch REVIEW\.md is read from

from line 156

156156| The default branch isn't protected, and the base branch has no protection rule of either kind | Default branch | Root file |

157157| Code Review can't confirm the protection settings. This includes an unprotected default branch with a base branch that has only a classic rule | None | None |

158158

159If the check run mentions `REVIEW.md`, see [The check run mentions REVIEW.md](/docs/en/code-review-troubleshooting#the-check-run-mentions-review-md).

159If the check run mentions `REVIEW.md`, see [The check run mentions REVIEW.md](/docs/en/code-review-troubleshooting.md#the-check-run-mentions-review-md).

160160

161161## Related resources

162162

163* [Code Review](/docs/en/code-review): what the service is and how a review runs

164* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests#severity-levels): what each severity level means and how findings appear

165* [Set up Code Review](/docs/en/code-review-setup): the review level and when reviews run, which an Owner sets

163* [Code Review](/docs/en/code-review.md): what the service is and how a review runs

164* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests.md#severity-levels): what each severity level means and how findings appear

165* [Set up Code Review](/docs/en/code-review-setup.md): the review level and when reviews run, which an Owner sets

166166* [Review locally with `/code-review`](/docs/en/code-review-local): the `/code-review` command, its arguments, and effort levels

167* [Memory](/docs/en/memory): how `CLAUDE.md` files work across Claude Code

167* [Memory](/docs/en/memory.md): how `CLAUDE.md` files work across Claude Code

168168

code-review-local Changed · +26 / -26 lines

from line 8

99> [!NOTE]

1010>

11> To have every pull request in a repository reviewed automatically on GitHub, see [Code Review](/docs/en/code-review), a managed service that an Owner turns on for your organization.

11> To have every pull request in a repository reviewed automatically on GitHub, see [Code Review](/docs/en/code-review.md), a managed service that an Owner turns on for your organization.

1212

1313`/review` is an alias of `/code-review`. Before v2.1.223, `/review` was a separate command that ran a single-pass, read-only review of a GitHub pull request.

1414

from line 24

2424

2525You can also add flags:

2626

27* `--fix`: also asks Claude to apply the findings to your working tree after the review. Its edits go through your [permission mode](/docs/en/permission-modes).

27* `--fix`: also asks Claude to apply the findings to your working tree after the review. Its edits go through your [permission mode](/docs/en/permission-modes.md).

2828* `--comment`: posts the findings on a GitHub pull request as inline comments, or on a [GitLab merge request](#post-findings-to-a-gitlab-merge-request) as a single note

2929

3030**2. Keep working**

3131

32The review runs as a background [subagent](/docs/en/sub-agents) with its own context window, so it doesn't fill your conversation. The findings arrive in your conversation when the review completes.

32The review runs as a background [subagent](/docs/en/sub-agents.md) with its own context window, so it doesn't fill your conversation. The findings arrive in your conversation when the review completes.

3333

3434**3. Act on the findings**

3535

from line 57

5757Check these before you run a review, especially with `--fix`:

5858

5959* **Edits**: without `--fix`, the review's instructions ask Claude for a report only. With `--fix`, they also ask it to apply the findings to your working tree. Either way, any edit goes through your permission mode.

60* **Rewinding**: a background review applies its `--fix` edits outside your session's [checkpoints](/docs/en/checkpointing#subagent-edits-not-restored). After one, `/rewind` restores only the files Claude had already edited in your conversation. The review's edits to other files stay, so use git to revert them. When the review [runs in the foreground](#run-in-the-foreground), it edits your working tree during your own turn, so `/rewind` restores its edits as usual.

61* **Instructions**: the review follows your `CLAUDE.md`, including in a non-interactive `-p` run. It doesn't read `REVIEW.md`. That file configures the managed [Code Review service](/docs/en/code-review-customize#use-review-md-for-review-only-rules) on GitHub pull requests.

60* **Rewinding**: a background review applies its `--fix` edits outside your session's [checkpoints](/docs/en/checkpointing.md#subagent-edits-not-restored). After one, `/rewind` restores only the files Claude had already edited in your conversation. The review's edits to other files stay, so use git to revert them. When the review [runs in the foreground](#run-in-the-foreground), it edits your working tree during your own turn, so `/rewind` restores its edits as usual.

61* **Instructions**: the review follows your `CLAUDE.md`, including in a non-interactive `-p` run. It doesn't read `REVIEW.md`. That file configures the managed [Code Review service](/docs/en/code-review-customize.md#use-review-md-for-review-only-rules) on GitHub pull requests.

6262

6363## How findings are reported

6464

6565Claude reports the findings as text in the reply in both of these runs:

6666

67* In a terminal session, where `/code-review` runs the review as a [forked subagent](/docs/en/skills#run-skills-in-a-subagent)

67* In a terminal session, where `/code-review` runs the review as a [forked subagent](/docs/en/skills.md#run-skills-in-a-subagent)

6868* In a `-p` run with text or JSON output

6969

70In a host application that requests the findings list, such as the [desktop app](/docs/en/desktop#review-your-code), Claude reports the review's findings through the [`ReportFindings` tool](/docs/en/tools-reference) instead. The report appears as a findings list, and each entry shows the file location, a one-sentence summary, and a category tag such as `correctness` when the finding carries one. A host request applies at every effort level and requires Claude Code v2.1.218 or later.

70In a host application that requests the findings list, such as the [desktop app](/docs/en/desktop.md#review-your-code), Claude reports the review's findings through the [`ReportFindings` tool](/docs/en/tools-reference) instead. The report appears as a findings list, and each entry shows the file location, a one-sentence summary, and a category tag such as `correctness` when the finding carries one. A host request applies at every effort level and requires Claude Code v2.1.218 or later.

7171

7272When Claude fixes reported findings later in the session, it reports them again. Claude Code then marks each finding in the updated findings list as fixed, skipped, or no change needed.

7373

from line 75

7575

7676Beyond `--fix` and `--comment`, the command takes these flags:

7777

78* `--post`: on an `ultra` cloud review of a `github.com` pull request, preselects posting the finished findings to the PR in the launch dialog. See [Post findings to the pull request](/docs/en/ultrareview#post-findings-to-the-pull-request). Requires Claude Code v2.1.227 or later.

78* `--post`: on an `ultra` cloud review of a `github.com` pull request, preselects posting the finished findings to the PR in the launch dialog. See [Post findings to the pull request](/docs/en/ultrareview.md#post-findings-to-the-pull-request). Requires Claude Code v2.1.227 or later.

7979* `--max-findings <n>`, `--max-findings all`, or `--max-findings default`: reports up to `n` findings, or every finding with `all`, in place of the review's usual limit. Where the review reports through the findings tool, the limit is 32. Later reviews reuse the value you typed until you pass `--max-findings default`, but a value passed in a non-interactive `-p` run isn't remembered. Requires Claude Code v2.1.288 or later.

8080

81Pass an [effort level](/docs/en/model-config#adjust-effort-level) to trade coverage for confidence. At `low`, the review reports the findings it's most confident in, so you see fewer false positives. From `medium` through `max`, the review broadens coverage.

81Pass an [effort level](/docs/en/model-config.md#adjust-effort-level) to trade coverage for confidence. At `low`, the review reports the findings it's most confident in, so you see fewer false positives. From `medium` through `max`, the review broadens coverage.

8282

8383When you don't type a level, the review reuses the last level from `low` through `max` you typed, even in an earlier session. Claude Code shows a notice such as `Reusing high effort, the level you typed last time`. These rules decide which level a run uses:

8484

from line 99

9999

100100After the effort level and flags, Claude Code reads the rest of the line as the review target. The `ultra` argument changes that reading:

101101

102* **With `ultra`**: Claude Code reads a single word as a base branch or PR number. Longer text that doesn't name a branch or PR becomes [a note attached to the review](/docs/en/ultrareview#pass-a-request-in-plain-words). `/code-review ultra check my auth changes` reviews your current branch, and Claude relates the findings to your note.

103* **Without `ultra`**: everything left is the review target, even when it starts with another command name. `/code-review /fix-issue 123` reviews with `/fix-issue 123` as target text instead of loading `/fix-issue` as a second [stacked skill](/docs/en/skills#stack-several-skills-in-one-message). Before v2.1.218, a command stacked after `/code-review` expanded as its own skill.

102* **With `ultra`**: Claude Code reads a single word as a base branch or PR number. Longer text that doesn't name a branch or PR becomes [a note attached to the review](/docs/en/ultrareview.md#pass-a-request-in-plain-words). `/code-review ultra check my auth changes` reviews your current branch, and Claude relates the findings to your note.

103* **Without `ultra`**: everything left is the review target, even when it starts with another command name. `/code-review /fix-issue 123` reviews with `/fix-issue 123` as target text instead of loading `/fix-issue` as a second [stacked skill](/docs/en/skills.md#stack-several-skills-in-one-message). Before v2.1.218, a command stacked after `/code-review` expanded as its own skill.

104104

105105## Run in the foreground

106106

107107To make the review run in the foreground, do one of these:

108108

109* Run it in non-interactive mode, with the `-p` flag or the Agent SDK. Claude Code waits for the review and includes the findings in the response, except for `ultra`, which [doesn't wait for the cloud review](/docs/en/ultrareview#run-ultrareview-non-interactively).

110110* Set [`CLAUDE_CODE_DISABLE_BACKGROUND_TASKS`](/docs/en/env-vars) to `1`, which also turns off every other background task feature

111111* Run `/code-review` again while an earlier review is still in progress

112112

from line 117

117117Claude can start `/code-review` on its own, without you typing the command:

118118

119119* **When you ask in plain language**: ask Claude to review your changes and it can run the skill

120* **From a scheduled task**: a [session-scoped scheduled task](/docs/en/scheduled-tasks) with `/code-review` as its prompt runs the review

120* **From a scheduled task**: a [session-scoped scheduled task](/docs/en/scheduled-tasks.md) with `/code-review` as its prompt runs the review

121121

122122A session-scoped scheduled task never launches the [cloud review](#escalate-to-ultrareview), so schedule `/code-review` without the `ultra` argument.

123123

124To stop both Claude and scheduled tasks from starting the review while keeping `/code-review` available for you to type, add a [`skillOverrides`](/docs/en/skills#override-skill-visibility-from-settings) entry to a [settings file](/docs/en/settings#where-settings-live) such as `~/.claude/settings.json`:

124To stop both Claude and scheduled tasks from starting the review while keeping `/code-review` available for you to type, add a [`skillOverrides`](/docs/en/skills#override-skill-visibility-from-settings) entry to a [settings file](/docs/en/settings.md#where-settings-live) such as `~/.claude/settings.json`:

125125

126126```json theme={null}

127127{

from line 131

131131}

132132```

133133

134Before v2.1.246, Claude started `/code-review` on its own only where a feature flag fetched from Anthropic turned it on. In [sessions that don't fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), `/code-review` ran only when you typed it, and a scheduled `/code-review` reached Claude as plain text.

134Before v2.1.246, Claude started `/code-review` on its own only where a feature flag fetched from Anthropic turned it on. In [sessions that don't fetch feature flags](/docs/en/env-vars.md#features-that-need-feature-flag-fetching), `/code-review` ran only when you typed it, and a scheduled `/code-review` reached Claude as plain text.

135135

136136## Escalate to ultrareview

137137

138`/code-review ultra --fix` runs the deeper [ultrareview](/docs/en/ultrareview) in the cloud, then asks Claude to apply its findings to your working tree when they arrive back in your session.

138`/code-review ultra --fix` runs the deeper [ultrareview](/docs/en/ultrareview.md) in the cloud, then asks Claude to apply its findings to your working tree when they arrive back in your session.

139139

140140Ultrareview uses its own scope:

141141

142142* **What it compares**: your current branch against the repository's default branch, plus uncommitted and staged changes in the working tree

143* **Sensitive files**: for uncommitted changes to files named like credentials or keys, such as `.env` and `*.tfvars` files, Claude Code follows the rules for [uploading a local repository to a cloud session](/docs/en/claude-code-on-the-web#send-local-repositories-without-github)

144144* **A different base**: pass a branch name, such as `/code-review ultra develop`, to compare against a different base

145145

146When the target is a `github.com` pull request, you can have Claude [post the finished findings to the PR](/docs/en/ultrareview#post-findings-to-the-pull-request) as a comment from your GitHub account. Requires Claude Code v2.1.227 or later.

146When the target is a `github.com` pull request, you can have Claude [post the finished findings to the PR](/docs/en/ultrareview.md#post-findings-to-the-pull-request) as a comment from your GitHub account. Requires Claude Code v2.1.227 or later.

147147

148148> [!NOTE]

149149>

150> Ultrareview requires authentication with a claude.ai account. It isn't available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or to organizations with Zero Data Retention enabled or with the [HIPAA configuration](/docs/en/hipaa-setup) applied. In these cases, `/code-review ultra` runs a local review in your session instead. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) (CMEK) can't run ultrareview. To review your changes locally, run `/code-review`.

150> Ultrareview requires authentication with a claude.ai account. It isn't available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or to organizations with Zero Data Retention enabled or with the [HIPAA configuration](/docs/en/hipaa-setup.md) applied. In these cases, `/code-review ultra` runs a local review in your session instead. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) (CMEK) can't run ultrareview. To review your changes locally, run `/code-review`.

151151

152152To run a cloud review from a script or CI job, use the [`claude ultrareview` subcommand](/docs/en/ultrareview#run-ultrareview-non-interactively), which waits for the findings and prints them to stdout.

153153

154154## Change or build on the review

155155

156`/code-review` is a [bundled skill](/docs/en/skills#bundled-skills): its instructions are built into Claude Code, so there is no `SKILL.md` file on disk to open or edit. To give every review project rules to follow, add them to your `CLAUDE.md`. To go further, start from one of these pages:

156`/code-review` is a [bundled skill](/docs/en/skills.md#bundled-skills): its instructions are built into Claude Code, so there is no `SKILL.md` file on disk to open or edit. To give every review project rules to follow, add them to your `CLAUDE.md`. To go further, start from one of these pages:

157157

158* **Replace the command**: a project or personal skill named `code-review` runs in place of the bundled one, and the `/review` alias keeps running the bundled review. See [Resolve skills that share a name](/docs/en/skills#resolve-skills-that-share-a-name).

159* **Build your own reviewer**: write a reviewer [subagent](/docs/en/sub-agents) or a review [skill](/docs/en/skills)

159* **Build your own reviewer**: write a reviewer [subagent](/docs/en/sub-agents.md) or a review [skill](/docs/en/skills.md)

160160* **Use a neighboring command**: [`/simplify`](/docs/en/commands) reviews for cleanup only and applies its fixes, and [`/verify`](/docs/en/commands) runs your app to confirm a change works

161161

162162The command was named `/simplify` before v2.1.147, when it applied fixes by default. If you scripted `/simplify` for bug-finding, switch to `/code-review --fix`.

from line 163

163163

164164## Related resources

165165

166* [Code Review](/docs/en/code-review): the managed service that reviews every pull request on GitHub for your organization

167* [Ultrareview](/docs/en/ultrareview): setup, limits, and cost of the deeper cloud review

168* [Commands](/docs/en/commands): the one-line reference for `/code-review`, `/review`, `/simplify`, and `/verify`

169* [Skills](/docs/en/skills): how bundled skills work and how to write your own

166* [Code Review](/docs/en/code-review.md): the managed service that reviews every pull request on GitHub for your organization

167* [Ultrareview](/docs/en/ultrareview.md): setup, limits, and cost of the deeper cloud review

168* [Commands](/docs/en/commands.md): the one-line reference for `/code-review`, `/review`, `/simplify`, and `/verify`

169* [Skills](/docs/en/skills.md): how bundled skills work and how to write your own

170170

code-review-pull-requests Changed · +11 / -11 lines

from line 4

55Code Review is a managed service that an Owner in your Claude organization turns on for a set of GitHub repositories. Once it's on, Claude reviews pull requests in those repositories and posts its findings as inline comments, a summary in the review body, and a check run named **Claude Code Review**. A review never approves or blocks your pull request, and the check run never concludes as a failure.

7An Owner controls [when reviews run](/docs/en/code-review-setup#set-when-reviews-run) and [how thorough they are](/docs/en/code-review-setup#set-the-default-review-level) for each repository.

7An Owner controls [when reviews run](/docs/en/code-review-setup.md#set-when-reviews-run) and [how thorough they are](/docs/en/code-review-setup.md#set-the-default-review-level) for each repository.

99> [!NOTE]

1010>

from line 22

2222

2323When the review recorded its reasoning, the finding has a collapsed **Why this was flagged** section. Expand it to read why Claude flagged the issue and how it verified the problem.

2424

25To change what Claude flags in your repository or how it ranks severity, see [Customize Code Review](/docs/en/code-review-customize).

25To change what Claude flags in your repository or how it ranks severity, see [Customize Code Review](/docs/en/code-review-customize.md).

2626

2727## Respond to findings

2828

from line 47

4747

4848A finding that has a line but wasn't posted as an inline comment appears as an annotation in the **Files changed** tab, on the lines concerned. Important findings show in red, nits in yellow, and pre-existing bugs in gray.

4949

50The check run concludes as neutral, or as skipped when an automatic review didn't run because a push changed no files. It never concludes as a failure, so a finished review doesn't fail a required check. If you don't see findings, or a review didn't run, see [Troubleshoot Code Review](/docs/en/code-review-troubleshooting).

5151

5252### Read the result from a script

5353

from line 94

9494* **Open it or mark it ready**: in a repository set to **Once after PR creation** or **After every push**, a review starts when you open or reopen the pull request, or mark a draft ready for review.

9595* **Comment a command**: post [`@claude review`](#comment-commands) on the pull request.

9696* **Push a commit**: a push starts a review in a repository set to **After every push**, or on a pull request you subscribed with `@claude review always`.

97* **Click Re-run**: after a review fails or times out on a pull request that isn't from a fork, [run it again](/docs/en/code-review-troubleshooting#retrigger-a-failed-or-timed-out-review) from the check run.

98* **Wait for the automatic retry**: a review whose session was interrupted is retried once automatically. The [check run's summary](/docs/en/code-review-troubleshooting#retrigger-a-failed-or-timed-out-review) says when that's happening.

97* **Click Re-run**: after a review fails or times out on a pull request that isn't from a fork, [run it again](/docs/en/code-review-troubleshooting.md#retrigger-a-failed-or-timed-out-review) from the check run.

98* **Wait for the automatic retry**: a review whose session was interrupted is retried once automatically. The [check run's summary](/docs/en/code-review-troubleshooting.md#retrigger-a-failed-or-timed-out-review) says when that's happening.

9999

100100### Comment commands

101101

from line 143

143143

144144### Use Code Review alongside the Claude Code GitHub Action

145145

146If the repository also runs the [Claude Code GitHub Action](/docs/en/github-actions) in interactive mode with its default `@claude` trigger phrase, an `@claude review` comment starts the Action as well. To keep the two apart, set the Action's `trigger_phrase` input to a different phrase.

146If the repository also runs the [Claude Code GitHub Action](/docs/en/github-actions.md) in interactive mode with its default `@claude` trigger phrase, an `@claude review` comment starts the Action as well. To keep the two apart, set the Action's `trigger_phrase` input to a different phrase.

147147

148148## Related resources

149149

150* [Troubleshoot Code Review](/docs/en/code-review-troubleshooting): a review that didn't start, failed, or was skipped for budget

151* [Code Review](/docs/en/code-review): what the service is and how a review runs

152* [Set up Code Review](/docs/en/code-review-setup): for Owners, turn on Code Review and choose when reviews run and at what level

153* [Customize Code Review](/docs/en/code-review-customize): change what Claude flags with `REVIEW.md` and `CLAUDE.md`

154* [Code Review costs and usage](/docs/en/code-review-costs): how reviews are billed and where the spend limit is set

150* [Troubleshoot Code Review](/docs/en/code-review-troubleshooting.md): a review that didn't start, failed, or was skipped for budget

151* [Code Review](/docs/en/code-review.md): what the service is and how a review runs

152* [Set up Code Review](/docs/en/code-review-setup.md): for Owners, turn on Code Review and choose when reviews run and at what level

153* [Customize Code Review](/docs/en/code-review-customize.md): change what Claude flags with `REVIEW.md` and `CLAUDE.md`

154* [Code Review costs and usage](/docs/en/code-review-costs.md): how reviews are billed and where the spend limit is set

155155* [Review locally with `/code-review`](/docs/en/code-review-local): run a review of your branch from a Claude Code session

156156

code-review-setup Changed · +19 / -19 lines

from line 4

55As an Owner of your Claude organization, you turn on Code Review in [**Admin settings > Claude Code**](https://claude.ai/admin-settings/claude-code#code-review) on claude.ai. Reviews run on Anthropic infrastructure, so you don't add workflow files to your repositories.

7After setup, you choose how thorough reviews are and when they run in each repository. You spend more at a higher review level and when reviews run more often. See [Code Review costs](/docs/en/code-review-costs#pricing).

99## What you need to turn on Code Review

1010

11First check that your organization [qualifies for Code Review](/docs/en/code-review#availability). Then make sure you have this access, or someone who does:

11First check that your organization [qualifies for Code Review](/docs/en/code-review.md#availability). Then make sure you have this access, or someone who does:

1212

1313| Access | Needed for |

1414| :- | :- |

15| [Owner role](/docs/en/server-managed-settings#access-control) in your Claude organization | Every step on the admin page |

16| Owner of the GitHub organization | Installing the Claude GitHub App and [linking it to your Claude organization](/docs/en/admin-setup#connected-github-accounts). If you aren't an owner, have one install and link the app before you start |

15| [Owner role](/docs/en/server-managed-settings.md#access-control) in your Claude organization | Every step on the admin page |

16| Owner of the GitHub organization | Installing the Claude GitHub App and [linking it to your Claude organization](/docs/en/admin-setup.md#connected-github-accounts). If you aren't an owner, have one install and link the app before you start |

1717| Write access to each repository you add, from the GitHub account you connect to Claude | Adding the repository |

1818

1919## Turn on Code Review

from line 37

3737* Click **Install GitHub App**. When no repositories are listed, it's a button in the dialog. Otherwise, it's at the bottom of the dialog's GitHub organization filter menu. GitHub's install page opens in a new tab.

3838* Pick the GitHub organization that owns the repositories.

3939* Choose which repositories the app can access.

40* Approve the requested permissions. The set is broader than a review uses and is shared by other Claude features, such as [GitHub Actions](/docs/en/github-actions). See [what a review can access](/docs/en/code-review#what-a-review-can-access) and the [full permission list](/docs/en/github-actions#github-app-permissions).

40* Approve the requested permissions. The set is broader than a review uses and is shared by other Claude features, such as [GitHub Actions](/docs/en/github-actions.md). See [what a review can access](/docs/en/code-review.md#what-a-review-can-access) and the [full permission list](/docs/en/github-actions.md#github-app-permissions).

4141* When the install completes, the tab returns to Claude. If it shows a **Finish connecting GitHub** button, click it to link the installation to your Claude organization.

4242* Go back to the admin page's tab, where the list in the dialog refreshes.

4343

from line 55

5555

5656Open a test pull request in one of the repositories you added, and don't mark it as a draft. A check run named **Claude Code Review** appears within a few minutes. If you already set the repository to **Manual (@claude review)**, comment `@claude review` on the pull request to start the first review.

5757

58If no check run appears, see [No check run appears on the test pull request](/docs/en/code-review-troubleshooting#no-check-run-appears-on-the-test-pull-request).

58If no check run appears, see [No check run appears on the test pull request](/docs/en/code-review-troubleshooting.md#no-check-run-appears-on-the-test-pull-request).

5959

60Once the review arrives, send your developers [Read and request reviews on a pull request](/docs/en/code-review-pull-requests), which covers the severity levels, the comment commands, and how to respond to findings.

60Once the review arrives, send your developers [Read and request reviews on a pull request](/docs/en/code-review-pull-requests.md), which covers the severity levels, the comment commands, and how to respond to findings.

6161

6262## Set defaults for your organization

6363

from line 76

7676* **Organization default**: select a level under **Review level** and confirm with **Change level**. Every repository uses it unless you give that repository its own.

7777* **One repository**: click **Edit** on the repository's row, then select a **Review level** there. The first option, **Default**, follows the organization. The level saves as soon as you select it.

7878

79A new level applies to reviews that start after the change. For what else drives the cost of each review, see [Code Review costs and usage](/docs/en/code-review-costs).

79A new level applies to reviews that start after the change. For what else drives the cost of each review, see [Code Review costs and usage](/docs/en/code-review-costs.md).

8080

8181### Set when reviews run

8282

from line 86

8686* **After every push**: a review runs on pushes to the pull request branch, catching new issues as the pull request evolves and auto-resolving threads when you fix flagged issues

8787* **Manual (@claude review)**: opening or pushing to a pull request doesn't start a review. Comment [`@claude review`](/docs/en/code-review-pull-requests#comment-commands) to request one, or `@claude review always` to also subscribe the pull request to reviews on subsequent pushes.

8888

89Manual is useful for high-traffic repositories where you want to opt specific pull requests into review, or to start reviewing pull requests only once they're ready. To compare what each option does to spend, see [How often reviews run](/docs/en/code-review-costs#how-often-reviews-run).

9090

9191To change the setting, click **Edit** on the repository's row in the **Repositories** table and select a **Review runs** option. The choice saves as soon as you select it, and the table's **Review runs** column shows it shortened to Once per PR, Every push, or Manual.

9292

93* **Drafts and pull requests from forks**: whichever option you choose, [automatic reviews skip both](/docs/en/code-review-pull-requests#review-drafts-and-pull-requests-from-forks)

93* **Drafts and pull requests from forks**: whichever option you choose, [automatic reviews skip both](/docs/en/code-review-pull-requests.md#review-drafts-and-pull-requests-from-forks)

9494* **New repositories**: a repository you add from the **Add a repository** dialog starts at **After every push**. If its GitHub organization is [covered as a whole](#cover-a-whole-github-organization), it takes that organization row's setting instead.

9595

9696### Turn tip comments on or off

from line 108

108108

109109Developers come to you to change the review level, the **Review runs** setting, or which repositories get reviews. From GitHub, without the Owner role, they can do these:

110110

111* **Request a review**: comment [`@claude review`](/docs/en/code-review-pull-requests#comment-commands) on a pull request. This needs write access to the repository, and it works on [drafts and pull requests from forks](/docs/en/code-review-pull-requests#review-drafts-and-pull-requests-from-forks), which automatic reviews skip.

112* **Subscribe one pull request to a review on each push**: comment `@claude review always` on a pull request that isn't [a draft or from a fork](/docs/en/code-review-pull-requests#review-drafts-and-pull-requests-from-forks), such as in a repository set to Manual

111* **Request a review**: comment [`@claude review`](/docs/en/code-review-pull-requests#comment-commands) on a pull request. This needs write access to the repository, and it works on [drafts and pull requests from forks](/docs/en/code-review-pull-requests.md#review-drafts-and-pull-requests-from-forks), which automatic reviews skip.

112* **Subscribe one pull request to a review on each push**: comment `@claude review always` on a pull request that isn't [a draft or from a fork](/docs/en/code-review-pull-requests.md#review-drafts-and-pull-requests-from-forks), such as in a repository set to Manual

113113* **Change what reviews flag**: commit [`REVIEW.md` and `CLAUDE.md` files](/docs/en/code-review-customize) to the repository, for example to add a check

114114

115Reviews that developers request are [billed to your organization](/docs/en/code-review-costs#pricing). To limit what Code Review spends in a month, see [Limit your spend](/docs/en/code-review-costs#limit-your-spend).

115Reviews that developers request are [billed to your organization](/docs/en/code-review-costs.md#pricing). To limit what Code Review spends in a month, see [Limit your spend](/docs/en/code-review-costs.md#limit-your-spend).

116116

117117## Manage repositories

118118

from line 122

122122

123123To add repositories after setup, click **Add** above the **Repositories** table in the **Code review** section. The **Add a repository** dialog opens. Select repositories and click **Continue**.

124124

125* **A repository isn't listed**: see [A repository isn't listed in Add a repository](/docs/en/code-review-troubleshooting#a-repository-isn’t-listed-in-add-a-repository).

125* **A repository isn't listed**: see [A repository isn't listed in Add a repository](/docs/en/code-review-troubleshooting.md#a-repository-isn’t-listed-in-add-a-repository).

126126* **You want every repository in a GitHub organization**: [cover the organization](#cover-a-whole-github-organization) instead of selecting repositories one at a time

127127

128128### Cover a whole GitHub organization

from line 131

131131

132132* The GitHub account you connected to Claude is an owner of that GitHub organization.

133133* The organization is on github.com. GitHub Enterprise Server instances and personal GitHub accounts aren't eligible.

134* A [monthly spend limit](/docs/en/code-review-costs#limit-your-spend) is set, for your Claude organization or for Code Review.

134* A [monthly spend limit](/docs/en/code-review-costs.md#limit-your-spend) is set, for your Claude organization or for Code Review.

135135

136136To cover the organization, click **Edit** on its row, select a **Review runs** option, and confirm. The options are the three from [Set when reviews run](#set-when-reviews-run) plus **Off**.

137137

from line 153

153153

154154## Related resources

155155

156* [Code Review costs and usage](/docs/en/code-review-costs): how the review level and when reviews run affect spend, how to set a spend limit, and where to see usage

157* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests): what developers see on a pull request and the comment commands

158* [Customize Code Review](/docs/en/code-review-customize): tune what Claude flags with `REVIEW.md` and `CLAUDE.md`

159* [GitHub Enterprise Server](/docs/en/github-enterprise-server): connect a self-hosted GitHub instance before setup

156* [Code Review costs and usage](/docs/en/code-review-costs.md): how the review level and when reviews run affect spend, how to set a spend limit, and where to see usage

157* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests.md): what developers see on a pull request and the comment commands

158* [Customize Code Review](/docs/en/code-review-customize.md): tune what Claude flags with `REVIEW.md` and `CLAUDE.md`

159* [GitHub Enterprise Server](/docs/en/github-enterprise-server.md): connect a self-hosted GitHub instance before setup

160160

code-review-troubleshooting Changed · +15 / -15 lines

from line 2

33> Fix a Code Review that didn't start, failed, or was skipped for budget, find missing findings, and resolve setup and `REVIEW.md` problems.

5When [Code Review](/docs/en/code-review) doesn't do what you expect on a pull request, start with the **Claude Code Review** check run. Its title says how far the review got.

5When [Code Review](/docs/en/code-review.md) doesn't do what you expect on a pull request, start with the **Claude Code Review** check run. Its title says how far the review got.

77## Check how far the review got

from line 26

2626

2727After you comment `@claude review`, look for a **Claude Code Review** check run titled **Code review queued...** or **Code review in progress...** on the pull request. An 👀 reaction on your comment doesn't confirm a review is coming. If no check run appears, check for each of these causes:

2828

29* **Code Review isn't on for this repository**: Claude posts no comment and no check run in response to the command. Ask an Owner to [add the repository](/docs/en/code-review-setup#add-more-repositories).

30* **The comment doesn't meet a condition**: it was an inline comment or a review body rather than a new top-level comment, or the command wasn't at the start of the comment. Editing an earlier comment instead of posting a new one doesn't count either, and the pull request has to be open. See the [conditions for comment commands](/docs/en/code-review-pull-requests#comment-commands) and post a new comment that meets them.

31* **You don't have write access**: you need write, maintain, or admin permission on the repository. On a pull request from a fork, the permission that counts is on the base repository. Unless the pull request is yours, Claude can reply with a [tip](/docs/en/code-review-setup#turn-tip-comments-on-or-off): "No review was started: manual reviews can only be requested by someone with write access to this repository." Ask someone with write access to comment instead.

30* **The comment doesn't meet a condition**: it was an inline comment or a review body rather than a new top-level comment, or the command wasn't at the start of the comment. Editing an earlier comment instead of posting a new one doesn't count either, and the pull request has to be open. See the [conditions for comment commands](/docs/en/code-review-pull-requests.md#comment-commands) and post a new comment that meets them.

31* **You don't have write access**: you need write, maintain, or admin permission on the repository. On a pull request from a fork, the permission that counts is on the base repository. Unless the pull request is yours, Claude can reply with a [tip](/docs/en/code-review-setup.md#turn-tip-comments-on-or-off): "No review was started: manual reviews can only be requested by someone with write access to this repository." Ask someone with write access to comment instead.

3232* **The budget ran out**: Claude posts a comment that begins with "⚠️ Code review skipped". See [Review didn't run and the PR shows a budget message](#review-didn’t-run-and-the-pr-shows-a-budget-message).

3333

3434### Review didn't run and the PR shows a budget message

from line 37

3737

3838The comment links [claude.ai/admin-settings/usage](https://claude.ai/admin-settings/usage), where an admin restores the budget. Its wording tells you which limit was reached:

3939

40* **"has reached its monthly code review spending cap"**: the [monthly spend limit for Code Review](/docs/en/code-review-costs#limit-your-spend) was reached. Reviews resume at the start of the next billing period. To get them sooner, ask an admin to raise the limit.

40* **"has reached its monthly code review spending cap"**: the [monthly spend limit for Code Review](/docs/en/code-review-costs.md#limit-your-spend) was reached. Reviews resume at the start of the next billing period. To get them sooner, ask an admin to raise the limit.

4141* **"has no extra usage available to pay for this review"**: your organization's [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) balance is empty, or its overall monthly spend limit was reached. Ask an admin to add usage credits or raise that limit.

4242* **"is too low to start another review"**: what's left of the budget or balance is less than the expected cost of one review. Ask an admin to raise the limit or add usage credits.

4343

44After the budget is restored, comment `@claude review` on the pull request to get the review that was skipped. The [conditions for comment commands](/docs/en/code-review-pull-requests#comment-commands) apply, so the commenter needs write access.

44After the budget is restored, comment `@claude review` on the pull request to get the review that was skipped. The [conditions for comment commands](/docs/en/code-review-pull-requests.md#comment-commands) apply, so the commenter needs write access.

4545

4646## Retrigger a failed or timed-out review

4747

from line 50

5050Otherwise, when the check run's title is **Code review failed** or **Code review timed out**, run the review again with a comment or a re-run:

5151

5252* **Comment `@claude review`**: post it as a top-level comment on the pull request. This starts a fresh review without subscribing the pull request to future pushes.

53* **Click Re-run**: if the pull request isn't [from a fork](/docs/en/code-review-pull-requests#review-drafts-and-pull-requests-from-forks), click **Re-run** on the **Claude Code Review** check in GitHub's **Checks** tab. The re-run covers the pull request's current head commit and doesn't subscribe the pull request either.

53* **Click Re-run**: if the pull request isn't [from a fork](/docs/en/code-review-pull-requests.md#review-drafts-and-pull-requests-from-forks), click **Re-run** on the **Claude Code Review** check in GitHub's **Checks** tab. The re-run covers the pull request's current head commit and doesn't subscribe the pull request either.

5454

5555## Find issues that aren't showing as inline comments

5656

from line 64

6464

6565These are three of the messages a check run can carry about `REVIEW.md`:

6666

67* **"This review applied the repository's review instructions (REVIEW\.md) from its default branch, which is not protected against direct pushes."**: the review read the root file only. See [Which branch REVIEW.md is read from](/docs/en/code-review-customize#which-branch-review-md-is-read-from) for what protecting the branch changes.

67* **"This review applied the repository's review instructions (REVIEW\.md) from its default branch, which is not protected against direct pushes."**: the review read the root file only. See [Which branch REVIEW.md is read from](/docs/en/code-review-customize.md#which-branch-review-md-is-read-from) for what protecting the branch changes.

6868* **"were not applied to this review: branch protection could not be confirmed"**: the review read no `REVIEW.md`.

69* **"they link to a file this pull request modifies, or carry more links than the review checks"**: the review skipped the root `REVIEW.md`, or the number of subdirectory `REVIEW.md` files the message gives. Check the skipped file for each cause. For the root `REVIEW.md`, check the [files it includes](/docs/en/code-review-customize#include-other-files-in-review-md) too:

70 * **Too many links**: it carries more than 64 Markdown links. Cut links to [64 or fewer](/docs/en/code-review-customize#include-other-files-in-review-md).

70 * **Too many links**: it carries more than 64 Markdown links. Cut links to [64 or fewer](/docs/en/code-review-customize.md#include-other-files-in-review-md).

7171 * **A link the review can't parse**: it has a malformed Markdown link. Fix or remove the link.

7272 * **A link to a changed file**: it links to a file or folder this pull request changes, and the review couldn't leave out only the lines with that link. Write the rule in `REVIEW.md` itself.

7373

7474## Setup problems

7575

76These cases come up for an Owner while [setting up Code Review](/docs/en/code-review-setup).

76These cases come up for an Owner while [setting up Code Review](/docs/en/code-review-setup.md).

7777

7878### A repository isn't listed in Add a repository

7979

from line 85

8585

8686## Related resources

8787

88* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests): what the findings and the check run mean, and the comment commands

89* [Set up Code Review](/docs/en/code-review-setup): for Owners, turn on Code Review and manage repositories

90* [Code Review costs and usage](/docs/en/code-review-costs): the spend limits behind a budget message

91* [Customize Code Review](/docs/en/code-review-customize): which copy of `REVIEW.md` a review reads

88* [Read and request reviews on a pull request](/docs/en/code-review-pull-requests.md): what the findings and the check run mean, and the comment commands

89* [Set up Code Review](/docs/en/code-review-setup.md): for Owners, turn on Code Review and manage repositories

90* [Code Review costs and usage](/docs/en/code-review-costs.md): the spend limits behind a budget message

91* [Customize Code Review](/docs/en/code-review-customize.md): which copy of `REVIEW.md` a review reads

9292

common-workflows Changed · +19 / -19 lines

from line 2

33> Step-by-step guides for exploring codebases, fixing bugs, refactoring, testing, and other everyday tasks with Claude Code.

5This page collects short recipes for everyday development. For higher-level guidance on prompting and context management, see [Best practices](/docs/en/best-practices).

5This page collects short recipes for everyday development. For higher-level guidance on prompting and context management, see [Best practices](/docs/en/best-practices.md).

77This page covers:

from line 19

1919

2020### Understand new codebases

2121

22For configuring Claude Code in a monorepo or large codebase, see [Monorepos and large repos](/docs/en/large-codebases).

22For configuring Claude Code in a monorepo or large codebase, see [Monorepos and large repos](/docs/en/large-codebases.md).

2323

2424#### Get a quick codebase overview

2525

from line 95

9595>

9696> * Be specific about what you're looking for

9797> * Use domain language from the project

98> * Install a [code intelligence plugin](/docs/en/plugins/code-intelligence) for your language to give Claude precise "go to definition" and "find references" navigation

98> * Install a [code intelligence plugin](/docs/en/plugins/code-intelligence.md) for your language to give Claude precise "go to definition" and "find references" navigation

9999

100100***

101101

from line 227

227227enhance the PR description with more context about the security improvements

228228```

229229

230To find the session later, run `claude --from-pr 1234` with your own PR number, which opens the session picker filtered to sessions linked to that PR, or paste the PR URL into the [`/resume` picker](/docs/en/sessions#use-the-session-picker) search. Claude Code links the session to the PR when Claude creates it with `gh pr create` or `glab mr create`, and when Claude [works on an existing PR](/docs/en/agent-view#pull-request-status).

231231

232232> [!TIP]

233233>

from line 347

347347Explain the logic in @src/utils/auth.js

348348```

349349

350This includes the content of the file in the conversation when it fits the [Read tool](/docs/en/tools-reference#read-tool-behavior)'s token limit, 25,000 tokens by default. A text file larger than 256KB isn't included.

350This includes the content of the file in the conversation when it fits the [Read tool](/docs/en/tools-reference.md#read-tool-behavior)'s token limit, 25,000 tokens by default. A text file larger than 256KB isn't included.

351351

352352**2. Reference a directory**

353353

from line 361

361361Show me the data from @github:repos/owner/repo/issues

362362```

363363

364This fetches data from connected MCP servers using the format @server:resource. See [MCP resources](/docs/en/mcp#use-mcp-resources) for details.

364This fetches data from connected MCP servers using the format @server:resource. See [MCP resources](/docs/en/mcp.md#use-mcp-resources) for details.

365365

366366> [!TIP]

367367>

from line 373

373373> * Directory references show file listings, not contents

374374> * You can reference multiple files in a single message (for example, "@file1.js and @file2.js")

375375

376To stop `@` references from including file contents and directory listings, set [`CLAUDE_CODE_DISABLE_FILE_MENTIONS`](/docs/en/env-vars#variables) to `1` in your shell or in the [`env` block](/docs/en/env-vars#set-variables-in-settings-files) of user settings or [managed settings](/docs/en/managed-settings). Claude then receives the paths you referenced with a note to read them using its file tools. The variable requires Claude Code v2.1.299 or later, and Claude Code ignores it in project and local settings.

376To stop `@` references from including file contents and directory listings, set [`CLAUDE_CODE_DISABLE_FILE_MENTIONS`](/docs/en/env-vars#variables) to `1` in your shell or in the [`env` block](/docs/en/env-vars#set-variables-in-settings-files) of user settings or [managed settings](/docs/en/managed-settings.md). Claude then receives the paths you referenced with a note to read them using its file tools. The variable requires Claude Code v2.1.299 or later, and Claude Code ignores it in project and local settings.

377377

378378Your [`PreToolUse` hooks](/docs/en/hooks#pretooluse) don't run when Claude Code includes a file you reference with `@`, because it makes no tool call. If you rely on those hooks to control what Claude reads, block specific paths or stop `@` references from including files:

379379

from line 390

390390

391391| Option | Where it runs | Best for |

392392| :- | :- | :- |

393| [Cloud scheduled tasks](/docs/en/routines) | Cloud, Anthropic-managed by default | Tasks that should run even when your computer is off. Can also trigger on API calls or GitHub events in addition to a schedule. Configure at [claude.ai/code/routines](https://claude.ai/code/routines). |

394| [Desktop scheduled tasks](/docs/en/desktop-scheduled-tasks) | Your machine, via the desktop app | Tasks that need direct access to local files, tools, or uncommitted changes. |

395| [GitHub Actions](/docs/en/github-actions) | Your CI pipeline | Tasks tied to repo events like opened PRs, or cron schedules that should live alongside your workflow config. |

393| [Cloud scheduled tasks](/docs/en/routines.md) | Cloud, Anthropic-managed by default | Tasks that should run even when your computer is off. Can also trigger on API calls or GitHub events in addition to a schedule. Configure at [claude.ai/code/routines](https://claude.ai/code/routines). |

394| [Desktop scheduled tasks](/docs/en/desktop-scheduled-tasks.md) | Your machine, via the desktop app | Tasks that need direct access to local files, tools, or uncommitted changes. |

395| [GitHub Actions](/docs/en/github-actions.md) | Your CI pipeline | Tasks tied to repo events like opened PRs, or cron schedules that should live alongside your workflow config. |

396396| [`/loop`](/docs/en/scheduled-tasks) | The current CLI session | Quick polling while a session is open. `--resume` and `--continue` restore unexpired fixed-interval loops. |

397397

398398> [!TIP]

from line 452

452452claude --continue

453453```

454454

455This resumes the most recent session in the current directory; if there isn't one yet, it prints `No conversation found to continue` and exits. Use `claude --resume` to choose from a list, or `/resume` from inside a running session. See [Manage sessions](/docs/en/sessions) for naming, branching, and the full picker reference.

455This resumes the most recent session in the current directory; if there isn't one yet, it prints `No conversation found to continue` and exits. Use `claude --resume` to choose from a list, or `/resume` from inside a running session. See [Manage sessions](/docs/en/sessions.md) for naming, branching, and the full picker reference.

456456

457457## Run parallel sessions with worktrees

458458

from line 462

462462claude --worktree feature-auth

463463```

464464

465Run the same command with a different name in a second terminal to start an isolated parallel session. In a repository with no commits, the command fails with `Failed to resolve base branch "HEAD": git rev-parse failed`. See [Worktrees](/docs/en/worktrees) for cleanup, `.worktreeinclude`, and non-git VCS support. To monitor parallel sessions from one screen instead of separate terminals, see [background agents](/docs/en/agent-view).

465Run the same command with a different name in a second terminal to start an isolated parallel session. In a repository with no commits, the command fails with `Failed to resolve base branch "HEAD": git rev-parse failed`. See [Worktrees](/docs/en/worktrees.md) for cleanup, `.worktreeinclude`, and non-git VCS support. To monitor parallel sessions from one screen instead of separate terminals, see [background agents](/docs/en/agent-view.md).

466466

467467## Plan before editing

468468

from line 472

472472claude --permission-mode plan

473473```

474474

475You can also press `Shift+Tab` mid-session until the status bar shows `⏸ plan mode on`. See [Plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) for the approval flow and editing the plan in your text editor.

475You can also press `Shift+Tab` mid-session until the status bar shows `⏸ plan mode on`. See [Plan mode](/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode) for the approval flow and editing the plan in your text editor.

476476

477477## Delegate research to subagents

478478

from line 482

482482use a subagent to investigate how our auth system handles token refresh

483483```

484484

485The subagent reads files in its own context window and reports a summary. See [Subagents](/docs/en/sub-agents) for defining custom agents with their own tools and prompts.

485The subagent reads files in its own context window and reports a summary. See [Subagents](/docs/en/sub-agents.md) for defining custom agents with their own tools and prompts.

486486

487487## Pipe Claude into scripts

488488

from line 492

492492git log --oneline -20 | claude -p "summarize these recent commits"

493493```

494494

495See [Non-interactive mode](/docs/en/headless) for output formats, permission flags, and fan-out patterns.

495See [Non-interactive mode](/docs/en/headless.md) for output formats, permission flags, and fan-out patterns.

496496

497497## Next steps

498498

499> **[Best practices](/docs/en/best-practices)**

499> **[Best practices](/docs/en/best-practices.md)**

500500>

501501> Patterns for getting the most out of Claude Code

502502

503> **[Manage sessions](/docs/en/sessions)**

503> **[Manage sessions](/docs/en/sessions.md)**

504504>

505505> Resume, name, and branch conversations

506506

507> **[Worktrees](/docs/en/worktrees)**

507> **[Worktrees](/docs/en/worktrees.md)**

508508>

509509> Run isolated parallel sessions

510510

511> **[Extend Claude Code](/docs/en/features-overview)**

511> **[Extend Claude Code](/docs/en/features-overview.md)**

512512>

513513> Add skills, hooks, MCP, subagents, and plugins

514514

communications-kit Changed · +11 / -11 lines

from line 20

2020| - | - |

2121| `#claude-code` channel created and linked in the message | Gives questions one place to land |

2222| Install command tested on at least one machine in your environment | Catches proxy or firewall issues before everyone hits them at once |

23| Security and data-handling link ready ([Data usage](/docs/en/data-usage) or your internal equivalent) | "Where does my code go?" will be the first reply |

23| Security and data-handling link ready ([Data usage](/docs/en/data-usage.md) or your internal equivalent) | "Where does my code go?" will be the first reply |

2424| One concrete first task chosen, a real bug or file in your codebase | Generic examples don't convert; "fix the flaky test in `auth_test.go`" does |

2525| A named owner for the channel for the first 48 hours | Unanswered launch-day questions kill momentum |

2626| A C-suite sponsor lined up to send or co-sign the announcement | Exec-sent launches consistently see higher first-week adoption than admin-sent ones |

from line 219

219219

220220| Model | Best for |

221221| - | - |

222| Fable | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content triggers [automatic model fallback to Opus](/docs/en/model-config#automatic-model-fallback) |

223| Opus | Large-scale refactors, complex debugging, architecture decisions, high-stakes changes. On Opus 5.5 and Opus 5, cybersecurity or biology content triggers [automatic model fallback or a refusal](/docs/en/model-config#automatic-model-fallback) |

224| Sonnet | Everyday feature work, bug fixes, tests, documentation, code review. Recommended default. On Sonnet 5.5, cybersecurity or biology content triggers [automatic model fallback or a refusal](/docs/en/model-config#automatic-model-fallback) |

225225| Haiku | Quick questions, formatting, mechanical edits, rapid iteration |

226226

227227**Quick wins to try first**

from line 494

494494

495495| Question | Response |

496496| - | - |

497| "Does it work in VS Code?" | Yes. There is a VS Code extension and a JetBrains plugin with the same features, embedded in your editor. [VS Code →](/docs/en/vs-code) |

498| "Do I have to configure anything first?" | No. Install, then run `claude` in any repo. Run `/init` once and you're set. [Quickstart →](/docs/en/quickstart) |

499| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference. On a Team or Enterprise plan, your code and prompts are not used to train models. [Data usage →](/docs/en/data-usage) |

500| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt. [Permissions →](/docs/en/permissions) |

501| "How is this different from Copilot?" | Copilot autocompletes lines. Claude Code is an agent that reads files, runs commands, and makes multi-file edits. [Overview →](/docs/en/overview) |

502| "What should I try first?" | A bug you've been putting off because it's tedious. "The test in \[file] is flaky, figure out why." [Quickstart →](/docs/en/quickstart) |

497| "Does it work in VS Code?" | Yes. There is a VS Code extension and a JetBrains plugin with the same features, embedded in your editor. [VS Code →](/docs/en/vs-code.md) |

498| "Do I have to configure anything first?" | No. Install, then run `claude` in any repo. Run `/init` once and you're set. [Quickstart →](/docs/en/quickstart.md) |

500| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt. [Permissions →](/docs/en/permissions.md) |

501| "How is this different from Copilot?" | Copilot autocompletes lines. Claude Code is an agent that reads files, runs commands, and makes multi-file edits. [Overview →](/docs/en/overview.md) |

502| "What should I try first?" | A bug you've been putting off because it's tedious. "The test in \[file] is flaky, figure out why." [Quickstart →](/docs/en/quickstart.md) |

503503

504504### Prompt templates

505505

from line 518

518518

519519> [!TIP]

520520>

521> Claude Code ships frequently. Verify version-specific details against the [documentation home page](/docs/en/overview) before distributing internally.

521> Claude Code ships frequently. Verify version-specific details against the [documentation home page](/docs/en/overview.md) before distributing internally.

522522

computer-use Changed · +11 / -11 lines

from line 8

99Computer use lets Claude open apps, control your screen, and work on your machine the way you would. From the CLI, Claude can compile a Swift app, launch it, click through every button, and screenshot the result, all in the same conversation where it wrote the code.

1010

11This page covers how computer use works in the CLI. For the Desktop app on macOS or Windows, see [computer use in Desktop](/docs/en/desktop#let-claude-use-your-computer).

11This page covers how computer use works in the CLI. For the Desktop app on macOS or Windows, see [computer use in Desktop](/docs/en/desktop.md#let-claude-use-your-computer).

1212

1313## What you can do with computer use

1414

from line 23

2323

2424Claude has several ways to interact with an app or service. Computer use is the broadest and slowest, so Claude tries the most precise tool first:

2525

26* If you have an [MCP server](/docs/en/mcp) for the service, Claude uses that.

26* If you have an [MCP server](/docs/en/mcp.md) for the service, Claude uses that.

2727* If the task is a shell command, Claude uses Bash.

28* If the task is browser work and you have [Claude in Chrome](/docs/en/chrome) set up, Claude uses that.

28* If the task is browser work and you have [Claude in Chrome](/docs/en/chrome.md) set up, Claude uses that.

2929* If none of those apply, Claude uses computer use.

3030

3131Screen control is reserved for things nothing else can reach: native apps, simulators such as the iOS Simulator, and tools without an API.

from line 86

8686

8787Approve Finder to let Claude click the desktop, the Dock, or a Finder window.

8888

89Claude's level of control also varies by app category: browsers and trading platforms are view-only, terminals and IDEs are click-only, and everything else gets full control. See [app permissions in Desktop](/docs/en/desktop#app-permissions) for the complete tier breakdown.

9090

9191## How Claude works on your screen

9292

from line 118

118118

119119> [!WARNING]

120120>

121> Unlike the [sandboxed Bash tool](/docs/en/sandboxing), computer use runs on your actual desktop with access to the apps you approve. Claude checks each action and flags potential prompt injection from on-screen content, but the trust boundary is different. See the [computer use safety guide](https://support.claude.com/en/articles/14128542) for best practices.

121> Unlike the [sandboxed Bash tool](/docs/en/sandboxing.md), computer use runs on your actual desktop with access to the apps you approve. Claude checks each action and flags potential prompt injection from on-screen content, but the trust boundary is different. See the [computer use safety guide](https://support.claude.com/en/articles/14128542) for best practices.

122122

123123The built-in guardrails reduce risk without requiring configuration:

124124

from line 165

165165screens, and tell me if any screen takes more than a second to load.

166166```

167167

168Claude controls the simulator the same way you would with a mouse. This flow applies to the CLI; in the Desktop app, the same request opens the [iOS Simulator pane](/docs/en/desktop-ios-simulator) instead of screen control.

169169

170170## Differences from the Desktop app

171171

from line 193

193193

194194The server only appears on eligible setups. Check that:

195195

196* You're on macOS. Computer use in the CLI is not available on Linux or Windows. On Windows, use [computer use in Desktop](/docs/en/desktop#let-claude-use-your-computer) instead.

196* You're on macOS. Computer use in the CLI is not available on Linux or Windows. On Windows, use [computer use in Desktop](/docs/en/desktop.md#let-claude-use-your-computer) instead.

197197* You're on a Pro or Max plan. Run `/status` to confirm your subscription.

198198* You're authenticated through claude.ai. Computer use is not available with third-party providers like Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. If you access Claude exclusively through a third-party provider, you need a separate claude.ai account to use this feature.

199199* You're in an interactive session. Computer use is not available in non-interactive mode with the `-p` flag.

from line 200

200200

201201## See also

202202

203* [Computer use in Desktop](/docs/en/desktop#let-claude-use-your-computer): the same capability with a graphical settings page

204* [Claude in Chrome](/docs/en/chrome): browser automation for web-based tasks

205* [MCP](/docs/en/mcp): connect Claude to structured tools and APIs

206* [Sandboxing](/docs/en/sandboxing): how Claude's Bash tool isolates filesystem and network access

203* [Computer use in Desktop](/docs/en/desktop.md#let-claude-use-your-computer): the same capability with a graphical settings page

204* [Claude in Chrome](/docs/en/chrome.md): browser automation for web-based tasks

205* [MCP](/docs/en/mcp.md): connect Claude to structured tools and APIs

206* [Sandboxing](/docs/en/sandboxing.md): how Claude's Bash tool isolates filesystem and network access

207207* [Computer use safety guide](https://support.claude.com/en/articles/14128542): best practices for safe computer use

208208

corporate-launcher Changed · +14 / -14 lines

from line 4

55Some organizations require every process on a workstation to start through a mandatory launcher. The launcher applies the sandbox, network controls, or credential injection that the company's security posture depends on, and a binary that starts without it is a policy violation.

7`CLAUDE_CODE_PROCESS_WRAPPER` starts every process Claude Code launches from its own binary through your launcher: the [background service](/docs/en/agent-view#the-supervisor-process), every session it hosts in [agent view](/docs/en/agent-view), and Claude Code's relaunches after an update. Set it to your launcher's absolute path, and Claude Code runs the launcher with the Claude Code command as its arguments.

7`CLAUDE_CODE_PROCESS_WRAPPER` starts every process Claude Code launches from its own binary through your launcher: the [background service](/docs/en/agent-view.md#the-supervisor-process), every session it hosts in [agent view](/docs/en/agent-view.md), and Claude Code's relaunches after an update. Set it to your launcher's absolute path, and Claude Code runs the launcher with the Claude Code command as its arguments.

99A launcher that wraps the `claude` command on your `PATH` can't reach the background service or the sessions it hosts, because they start from the binary's direct path without looking up `claude`.

1010

from line 22

2222* The terminal host and the Claude Code session inside every agent view row, including the warm standby sessions the service keeps ready.

2323* Sessions the service respawns after an update or a crash.

2424* The relaunch Claude Code performs of itself to finish installing an update, including agent view's restart-for-update action.

25* The session processes that [Remote Control](/docs/en/remote-control) starts. Requires Claude Code v2.1.210 or later.

26* The split-pane teammate sessions that [agent teams](/docs/en/agent-teams) start in tmux or iTerm2. Teammate panes are interactive rather than background processes, but Claude Code starts them from its own binary, so the launcher covers them. Requires Claude Code v2.1.210 or later.

25* The session processes that [Remote Control](/docs/en/remote-control.md) starts. Requires Claude Code v2.1.210 or later.

26* The split-pane teammate sessions that [agent teams](/docs/en/agent-teams.md) start in tmux or iTerm2. Teammate panes are interactive rather than background processes, but Claude Code starts them from its own binary, so the launcher covers them. Requires Claude Code v2.1.210 or later.

2727

28On Windows, the variable is ignored: the launcher contract depends on `exec`, which Windows doesn't support. A Windows machine with the variable set runs every process unwrapped and keeps working, and the only signal is a warning in the [debug log](/docs/en/troubleshooting). If your launcher policy covers Windows, the variable doesn't satisfy it there: count Windows machines as unwrapped when you plan the rollout.

28On Windows, the variable is ignored: the launcher contract depends on `exec`, which Windows doesn't support. A Windows machine with the variable set runs every process unwrapped and keeps working, and the only signal is a warning in the [debug log](/docs/en/troubleshooting.md). If your launcher policy covers Windows, the variable doesn't satisfy it there: count Windows machines as unwrapped when you plan the rollout.

2929

3030### Processes that start outside the launcher

3131

from line 32

3232The following processes don't start through the launcher:

3333

3434* A session you start yourself in a terminal, which runs however you invoked it. To cover these sessions, put a script named `claude` in a directory earlier on `PATH` that runs your launcher with the real binary; don't replace the managed symlink. The background service and its sessions start without a `PATH` lookup, so the two launchers don't stack there.

35* The first process of a `claude-cli://` deep link, which the operating system's protocol handler starts directly. Everything that session starts in the background afterward runs through the launcher. To close this path entirely, [prevent handler registration](/docs/en/deep-links#registration-and-supported-platforms) with the `disableDeepLinkRegistration` setting.

35* The first process of a `claude-cli://` deep link, which the operating system's protocol handler starts directly. Everything that session starts in the background afterward runs through the launcher. To close this path entirely, [prevent handler registration](/docs/en/deep-links.md#registration-and-supported-platforms) with the `disableDeepLinkRegistration` setting.

3636* The relaunch that `--worktree` combined with `--tmux` performs: the terminal multiplexer starts that pane, not Claude Code's binary.

37* The native-messaging host that [Claude in Chrome](/docs/en/chrome) registers: the browser starts it, not Claude Code's binary.

37* The native-messaging host that [Claude in Chrome](/docs/en/chrome.md) registers: the browser starts it, not Claude Code's binary.

3838

3939### Helper process names in process monitors

4040

from line 63

6363

6464Set the variable in the `env` block of a settings file so the detached background service inherits it. A shell `export` isn't enough: the background service starts on demand, outlives your shell, and never re-reads shell profiles.

6565

66For one machine, add it to `~/.claude/settings.json`. To deploy it to every machine in your organization, put the same block in [managed settings](/docs/en/managed-settings):

66For one machine, add it to `~/.claude/settings.json`. To deploy it to every machine in your organization, put the same block in [managed settings](/docs/en/managed-settings.md):

6767

6868```json theme={null}

6969{

from line 85

8585

8686`CLAUDE_CODE_PROCESS_WRAPPER` takes precedence when both are set.

8787

88Because `processWrapper` is a named setting, an organization that delivers it through [remote managed settings](/docs/en/managed-settings#delivery-mechanisms) sees it listed on the [security approval dialog](/docs/en/server-managed-settings#security-approval-dialogs) alongside the other settings that run administrator-supplied executables.

88Because `processWrapper` is a named setting, an organization that delivers it through [remote managed settings](/docs/en/managed-settings.md#delivery-mechanisms) sees it listed on the [security approval dialog](/docs/en/server-managed-settings.md#security-approval-dialogs) alongside the other settings that run administrator-supplied executables.

8989

90Project and local settings can't configure the launcher. A file committed to a repository must not be able to put a binary in front of every Claude Code process on the machine, so Claude Code ignores `CLAUDE_CODE_PROCESS_WRAPPER` in `.claude/settings.json` or `.claude/settings.local.json` with a warning in the [debug log](/docs/en/troubleshooting), and never reads the `processWrapper` key from those files.

90Project and local settings can't configure the launcher. A file committed to a repository must not be able to put a binary in front of every Claude Code process on the machine, so Claude Code ignores `CLAUDE_CODE_PROCESS_WRAPPER` in `.claude/settings.json` or `.claude/settings.local.json` with a warning in the [debug log](/docs/en/troubleshooting.md), and never reads the `processWrapper` key from those files.

9191

9292**3. Restart the background service and your sessions**

9393

from line 126

126126* A value that starts with `[` is read as a JSON string array, such as `["/opt/corp/launcher", "--profile", "cc"]`.

127127* Shell syntax doesn't work: there is no variable expansion or globbing, and an unquoted operator such as `;`, `|`, `&`, or `$(` is rejected as a configuration error rather than reinterpreted.

128128

129When the value can't be used, Claude Code refuses to start the affected process and [reports the reason](/docs/en/errors#claude_code_process_wrapper-launcher-errors).

129When the value can't be used, Claude Code refuses to start the affected process and [reports the reason](/docs/en/errors.md#claude_code_process_wrapper-launcher-errors).

130130

131131In a settings file, write the array form inside a JSON string and escape its quotes: `"[\"/opt/corp/launcher\", \"--profile\", \"cc\"]"`.

132132

from line 152

152152

153153## Related resources

154154

155* [Agent view](/docs/en/agent-view): the background sessions and supervisor process the launcher covers

156* [Environment variables](/docs/en/env-vars): the `CLAUDE_CODE_PROCESS_WRAPPER` reference entry

157* [Managed settings](/docs/en/permissions#managed-settings): deliver the `env` block across a fleet

158* [Launcher error reference](/docs/en/errors#claude_code_process_wrapper-launcher-errors): the refusal messages and how to recover

155* [Agent view](/docs/en/agent-view.md): the background sessions and supervisor process the launcher covers

156* [Environment variables](/docs/en/env-vars.md): the `CLAUDE_CODE_PROCESS_WRAPPER` reference entry

157* [Managed settings](/docs/en/permissions.md#managed-settings): deliver the `env` block across a fleet

158* [Launcher error reference](/docs/en/errors.md#claude_code_process_wrapper-launcher-errors): the refusal messages and how to recover

159159

costs Changed · +60 / -60 lines

from line 29

2929

3030These totals reset when `/clear` starts a new session, so the next session's total cost starts at \$0. Before v2.1.211, they kept accumulating across `/clear` for the lifetime of the Claude Code process.

3131

32For a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies the list price of that response's tokens by 1.1 in the session cost figure. The same total appears in the [status line's cost field](/docs/en/statusline#cost-and-duration-tracking), and the multiplied figure also counts toward [`--max-budget-usd`](/docs/en/cli-reference#cli-flags).

32For a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies the list price of that response's tokens by 1.1 in the session cost figure. The same total appears in the [status line's cost field](/docs/en/statusline.md#cost-and-duration-tracking), and the multiplied figure also counts toward [`--max-budget-usd`](/docs/en/cli-reference#cli-flags).

3333

3434#### Prompt cache statistics

3535

36After the main conversation's first API response, Claude Code also adds a `Prompt cache (main)` line to the Session block, summarizing the session's [prompt cache](/docs/en/prompt-caching) use: the request count, the share of input tokens served from cache, cache misses, and whether the cache is warm right now. Requires Claude Code v2.1.251 or later.

36After the main conversation's first API response, Claude Code also adds a `Prompt cache (main)` line to the Session block, summarizing the session's [prompt cache](/docs/en/prompt-caching.md) use: the request count, the share of input tokens served from cache, cache misses, and whether the cache is warm right now. Requires Claude Code v2.1.251 or later.

3737

3838```text theme={null}

3939Prompt cache (main): 14 requests · 91% of input tokens from cache · 2 misses (last 6m 10s ago, 310.2k tokens re-cached) · 1 expected rebuild (compaction or tool-result clearing) · warm (1h TTL, last activity 40s ago)

from line 41

4141

4242The misses, expected rebuilds, and warm or cold parts of the line mean the following:

4343

44* **Misses**: requests that re-processed content the cache already held, with the time of the last miss and how many tokens those requests wrote back to the cache. [Actions that invalidate the cache](/docs/en/prompt-caching#actions-that-invalidate-the-cache) lists the usual causes. When Claude Code can identify a likely cause for the last miss, the line names it too, for example `likely cause: tool definitions changed`. The likely-cause text requires Claude Code v2.1.260 or later.

45* **Expected rebuilds**: when Claude Code has itself just rewritten the conversation, by [compaction](/docs/en/prompt-caching#compacting-the-conversation) or by clearing old tool results from context, it counts the same kind of miss as an expected rebuild instead. This part appears only after at least one expected rebuild has happened.

46* **Warm or cold**: whether the cached prefix is still within its [cache lifetime](/docs/en/prompt-caching#cache-lifetime), with the TTL in effect. When the cache is cold, the line shows how long the session has been idle. When no response has reported cache tokens, the line ends with `no prompt caching reported by the API` instead.

44* **Misses**: requests that re-processed content the cache already held, with the time of the last miss and how many tokens those requests wrote back to the cache. [Actions that invalidate the cache](/docs/en/prompt-caching.md#actions-that-invalidate-the-cache) lists the usual causes. When Claude Code can identify a likely cause for the last miss, the line names it too, for example `likely cause: tool definitions changed`. The likely-cause text requires Claude Code v2.1.260 or later.

45* **Expected rebuilds**: when Claude Code has itself just rewritten the conversation, by [compaction](/docs/en/prompt-caching.md#compacting-the-conversation) or by clearing old tool results from context, it counts the same kind of miss as an expected rebuild instead. This part appears only after at least one expected rebuild has happened.

46* **Warm or cold**: whether the cached prefix is still within its [cache lifetime](/docs/en/prompt-caching.md#cache-lifetime), with the TTL in effect. When the cache is cold, the line shows how long the session has been idle. When no response has reported cache tokens, the line ends with `no prompt caching reported by the API` instead.

4747

4848The counts come from the cache token fields in the API's responses, so the line works on every provider and gateway. It covers the main conversation only, not subagents. `/clear` resets it with the rest of the Session block.

4949

from line 61

6161

6262Press `d` or `w` to switch between the last 24 hours and the last 7 days. The figures are approximate and computed from local session history on this machine, so usage from other devices or claude.ai is not included.

6363

64In the [VS Code extension](/docs/en/vs-code#check-account-and-usage), the attribution shares and recommendations appear in the Account & usage dialog with a Day and Week toggle, without the Loops rows.

64In the [VS Code extension](/docs/en/vs-code.md#check-account-and-usage), the attribution shares and recommendations appear in the Account & usage dialog with a Day and Week toggle, without the Loops rows.

6565

6666#### Apply recommendations with the fix shortcut

6767

from line 80

8080

8181In `f to fix 2 of 3`, the first number counts the rows Claude Code acts on when you press `f`, and the second counts the rows shown. A hint with no `of` in it, such as `f to fix both`, means Claude Code acts on every row shown.

8282

83While [Remote Control](/docs/en/remote-control) is connected, the footer shows no `f` hint. If pressing `f` closes `/usage` with `Nothing was sent. Turn off Remote Control to use fixes.`, Remote Control connected while `/usage` was open. To use `f` again, [disconnect Remote Control](/docs/en/remote-control#check-connection-status), then run `/usage` at the Claude Code prompt and press `f` again.

83While [Remote Control](/docs/en/remote-control.md) is connected, the footer shows no `f` hint. If pressing `f` closes `/usage` with `Nothing was sent. Turn off Remote Control to use fixes.`, Remote Control connected while `/usage` was open. To use `f` again, [disconnect Remote Control](/docs/en/remote-control.md#check-connection-status), then run `/usage` at the Claude Code prompt and press `f` again.

8484

8585#### Check your usage-credits spend

8686

from line 101

101101

102102While Claude works in the main conversation, the line beside the spinner can end with an elapsed time and a token count, as in `Deciphering… (10m 27s · ↓ 5.5k tokens)`. It is a live, approximate count of the output the current turn has produced so far. The arrow beside the count points down while output arrives or tools run.

103103

104* **What it covers**: output the turn generates, such as the text and tool calls Claude streams back, its thinking, and the output of subagents that run in the [foreground](/docs/en/sub-agents#run-subagents-in-foreground-or-background)

105105* **What it leaves out**: what Claude Code sends to the model, so your prompt, the conversation history, and the rest of your context don't move it

106* **When it resets**: at the start of each turn, and when Claude Code [compacts the conversation](/docs/en/prompt-caching#compacting-the-conversation)

107* **When it stays hidden**: until output starts arriving, when the row is too narrow to fit it, and in [screen reader mode](/docs/en/accessibility)

106* **When it resets**: at the start of each turn, and when Claude Code [compacts the conversation](/docs/en/prompt-caching.md#compacting-the-conversation)

107* **When it stays hidden**: until output starts arriving, when the row is too narrow to fit it, and in [screen reader mode](/docs/en/accessibility.md)

108108

109It won't match the `Usage by model` output figures in the `/usage` Session block, which add up the whole session rather than one turn. It also differs from the token count [verbose mode adds](/docs/en/statusline#notifications-share-the-status-line-row), because that count measures the size of your context rather than one turn's output.

109It won't match the `Usage by model` output figures in the `/usage` Session block, which add up the whole session rather than one turn. It also differs from the token count [verbose mode adds](/docs/en/statusline.md#notifications-share-the-status-line-row), because that count measures the size of your context rather than one turn's output.

110110

111111### Analyze your usage patterns

112112

113113Run [`/insights`](/docs/en/commands#all-commands) for a report on how you work rather than how many tokens you've used. It analyzes your recent sessions on this machine and writes an HTML report covering what you work on, friction points such as misunderstood requests or buggy code, and suggestions for using Claude Code more effectively. A single run analyzes up to 200 sessions it hasn't seen before and skips very short ones. When sessions are left out, the report header shows the analyzed count with the total in parentheses, for example `200 sessions (412 total)`.

114114

115When [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) is available to the session and your recent sessions mostly ran without it, the report can also include an estimate of how many permission prompts auto mode could have handled across those sessions.

115When [auto mode](/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode) is available to the session and your recent sessions mostly ran without it, the report can also include an estimate of how many permission prompts auto mode could have handled across those sessions.

116116

117117Claude Code writes the latest report to `~/.claude/usage-data/report.html` and saves a timestamped copy of each run in the same directory, so earlier reports aren't overwritten. Claude Code deletes reports on the same schedule as the rest of your session data: at startup, it removes files older than [`cleanupPeriodDays`](/docs/en/claude-directory#cleaned-up-automatically), 30 days by default.

118118

from line 128

128128| Team or Enterprise member with billing access | Opens your organization's usage settings, [**Organization settings > Usage**](https://claude.ai/admin-settings/usage), in the browser |

129129| Team or Enterprise member without billing access | Asks you to confirm, then sends a request to your organization's admins. Before v2.1.211, Claude Code sent the request without a confirmation step |

130130

131For Team and Enterprise members without billing access, the confirmation appears only in interactive sessions: in non-interactive mode with the `-p` flag and from [Remote Control](/docs/en/remote-control), the command sends no request and tells you to run it in an interactive session instead.

131For Team and Enterprise members without billing access, the confirmation appears only in interactive sessions: in non-interactive mode with the `-p` flag and from [Remote Control](/docs/en/remote-control.md), the command sends no request and tells you to run it in an interactive session instead.

132132

133133If you run `/usage-credits` again while your earlier request is waiting on an admin, Claude Code tells you a request has already been sent rather than sending a duplicate. After an admin dismisses your request, running the command again sends a new one. Before v2.1.222, a dismissed request also blocked new requests.

134134

135On Pro and Max plans, when you reach your spend limit with usage credits still available, Claude Code prompts you to raise or remove the limit without leaving the CLI. If the server rejects the change, see [Could not update your spend limit](/docs/en/errors#could-not-update-your-spend-limit).

136136

137137## Manage costs for your organization

138138

139139Which controls you have depends on how your organization accesses Claude Code: a Claude for Teams or Enterprise plan, the Claude Console, or a cloud provider. On Teams and Enterprise plans, usage draws from each member's seat allowance. On the Console and on cloud providers, usage is billed per token to your organization. If your organization mixes sign-in methods, each developer is metered according to the one they authenticated with.

140140

141The table maps each setup to where you see spend, where you cap it, and how you pull per-user numbers. On an individual Pro or Max plan you have no organization to manage, so track your own usage-credit spend, including [fast mode](/docs/en/fast-mode#see-where-fast-mode-spend-appears), under [Add usage credits to your subscription](#add-usage-credits-to-your-subscription).

141The table maps each setup to where you see spend, where you cap it, and how you pull per-user numbers. On an individual Pro or Max plan you have no organization to manage, so track your own usage-credit spend, including [fast mode](/docs/en/fast-mode.md#see-where-fast-mode-spend-appears), under [Add usage credits to your subscription](#add-usage-credits-to-your-subscription).

142142

144144| :- | :- | :- | :- |

145145| [Claude for Teams or Enterprise](#claude-for-teams-and-enterprise) | [Spend report in org analytics](https://support.claude.com/en/articles/12883420-view-usage-analytics-for-team-and-enterprise-plans) | Spend limits in admin settings | [Spend report CSV](https://support.claude.com/en/articles/12883420-view-usage-analytics-for-team-and-enterprise-plans); [Enterprise Analytics API](https://platform.claude.com/docs/en/api/admin/analytics) on Enterprise |

146146| [Claude Console (API)](#claude-console) | [Console usage page](https://platform.claude.com/usage) | Workspace spend limits | [Console dashboard](https://platform.claude.com/claude-code), [Claude Code Analytics API](https://platform.claude.com/docs/en/build-with-claude/claude-code-analytics-api) |

147| [Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry](#cloud-providers) | Your cloud billing console | Your cloud's budget controls | [OpenTelemetry](/docs/en/monitoring-usage) or an [LLM gateway](/docs/en/llm-gateway) |

148148

149[OpenTelemetry export](/docs/en/monitoring-usage) works on every setup and is the only option that streams per-user token and cost metrics into your own observability stack in near real time.

149[OpenTelemetry export](/docs/en/monitoring-usage.md) works on every setup and is the only option that streams per-user token and cost metrics into your own observability stack in near real time.

150150

151151### Report spend at your contracted rates

152152

from line 162

162162

163163**3. Deploy it through managed settings**

164164

165Deliver it as [managed settings](/docs/en/managed-settings): server-managed settings, an MDM policy, `managed-settings.json`, or a [policy helper](/docs/en/managed-settings#compute-the-policy-with-a-helper-program). Claude Code ignores the key in user, project, and local settings and in `--settings`.

165Deliver it as [managed settings](/docs/en/managed-settings.md): server-managed settings, an MDM policy, `managed-settings.json`, or a [policy helper](/docs/en/managed-settings.md#compute-the-policy-with-a-helper-program). Claude Code ignores the key in user, project, and local settings and in `--settings`.

166166

167To confirm the rates are in effect, run `/usage` in a session that has [received the managed settings](/docs/en/managed-settings#read-the-source-in-%2Fstatus): the Session block's `Total cost` line carries the note `at your organization's configured rates`. The figures are still estimates, not an invoice. The per-million-token prices in the `/model` picker stay at list price.

167To confirm the rates are in effect, run `/usage` in a session that has [received the managed settings](/docs/en/managed-settings.md#read-the-source-in-%2Fstatus): the Session block's `Total cost` line carries the note `at your organization's configured rates`. The figures are still estimates, not an invoice. The per-million-token prices in the `/model` picker stay at list price.

168168

169169### Claude for Teams and Enterprise

170170

from line 171

171171On Claude for Teams and Enterprise plans, each member's Claude Code usage draws from a per-seat allowance that resets on a rolling five-hour window and a weekly window. The allowance is shared with Claude chat and Cowork, and its size depends on the member's [seat tier](https://support.claude.com/en/articles/11845131-use-claude-code-with-your-team-or-enterprise-plan) (Standard or Premium). Your controls live in the claude.ai admin console, not the Claude Console.

172172

173173* **See spend**: the [spend report in org analytics](https://support.claude.com/en/articles/12883420-view-usage-analytics-for-team-and-enterprise-plans) shows estimated spend per user and per model, with CSV export, updated daily. The report covers usage-credit spend and appears once usage credits are turned on. Usage inside the seat allowance isn't metered in dollars.

174* **See adoption**: the [analytics dashboard](https://claude.ai/analytics/claude-code) shows daily active users, sessions, and contribution metrics, with CSV export of contribution data. See [track team usage with analytics](/docs/en/analytics).

175175* **Cap spend**: the seat allowance is the default ceiling. To let members continue past it, turn on [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) and set spend limits at the organization, group, or individual member level.

176176* **Pull per-user numbers**: on the Enterprise plan, the [Enterprise Analytics API](https://platform.claude.com/docs/en/api/admin/analytics) returns per-user usage and cost reports across Claude surfaces, including Claude Code. A Primary Owner creates a key with the `read:analytics` scope at [claude.ai/analytics/api-keys](https://claude.ai/analytics/api-keys). On the Teams plan, export the [spend report CSV](https://support.claude.com/en/articles/12883420-view-usage-analytics-for-team-and-enterprise-plans), which lists token usage and estimated spend per user and per model.

177177

from line 187

187187>

188188> For organizations with custom rate limits, Claude Code traffic in this workspace counts toward your organization's overall API rate limits. You can set a [workspace rate limit](https://platform.claude.com/docs/en/api/rate-limits#setting-lower-limits-for-workspaces) on this workspace's Limits page in the Claude Console to cap Claude Code's share and protect other production workloads.

189189

190For per-user reporting, the [Console dashboard](https://platform.claude.com/claude-code) shows spend and accepted lines per member, and the [Claude Code Analytics API](https://platform.claude.com/docs/en/build-with-claude/claude-code-analytics-api) returns the same daily per-user metrics programmatically with an [Admin API key](https://platform.claude.com/settings/admin-keys). See [analytics for API customers](/docs/en/analytics#access-analytics-for-api-customers).

191191

192192#### Rate limit recommendations

193193

from line 212

212212

213213### Cloud providers

214214

215On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, Claude Code is billed per token to your cloud account, and spend controls live in your cloud provider's billing console. Claude Code does not send metrics from your cloud back to Anthropic, so the [analytics dashboards](/docs/en/analytics) and the Claude Code Analytics API do not cover this usage.

215On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, Claude Code is billed per token to your cloud account, and spend controls live in your cloud provider's billing console. Claude Code does not send metrics from your cloud back to Anthropic, so the [analytics dashboards](/docs/en/analytics.md) and the Claude Code Analytics API do not cover this usage.

216216

217217For per-user cost attribution, you have three options:

218218

219* **OpenTelemetry**: [export metrics](/docs/en/monitoring-usage) from each developer's machine to your own observability stack. This gives you per-user token counts, costs, and tool activity regardless of provider.

220* **A Claude apps gateway**: a self-hosted [Claude apps gateway](/docs/en/claude-apps-gateway) provides per-user usage attribution, OTLP metrics with token counts, and [per-user spend limits](/docs/en/claude-apps-gateway-spend-limits) on these providers.

219* **OpenTelemetry**: [export metrics](/docs/en/monitoring-usage.md) from each developer's machine to your own observability stack. This gives you per-user token counts, costs, and tool activity regardless of provider.

221221* **An LLM gateway**: route all Claude Code traffic through a proxy that tracks spend per key. Several large enterprises reported using [LiteLLM](/docs/en/llm-gateway), an open-source tool that [tracks spend by key](https://docs.litellm.ai/docs/proxy/virtual_keys#tracking-spend). This project is unaffiliated with Anthropic and has not been audited for security.

222222

223223### When a developer asks about a limit

from line 224

224224

225225Developers usually bring limit questions to their admin, so it helps to know which ceiling they hit. These situations mean different things:

226226

227* **"You've hit your session limit" or "You've hit your weekly limit"**: a seat-based usage window on a subscription plan, shared across all models, so the developer can't restore access by switching models with `/model`. The message shows when the window resets. After the model-specific "You've hit your Opus limit" or "You've hit your Sonnet limit" message, switching to a model outside that family with `/model` does keep the developer working. See [usage limit errors](/docs/en/errors#youve-hit-your-session-limit). What the developer can do in the meantime:

227* **"You've hit your session limit" or "You've hit your weekly limit"**: a seat-based usage window on a subscription plan, shared across all models, so the developer can't restore access by switching models with `/model`. The message shows when the window resets. After the model-specific "You've hit your Opus limit" or "You've hit your Sonnet limit" message, switching to a model outside that family with `/model` does keep the developer working. See [usage limit errors](/docs/en/errors.md#youve-hit-your-session-limit). What the developer can do in the meantime:

228228 * Run `/usage-credits` to request usage beyond the allowance, if you have [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) turned on.

229 * On Claude Code v2.1.234 or later, [wait and continue the interrupted task automatically after the reset](/docs/en/interactive-mode#wait-for-a-usage-limit-to-reset); that section lists when Claude Code starts the wait on its own and when the developer picks it from `/rate-limit-options`. To control for your fleet whether Claude Code starts that wait on its own, set [`autoContinueAtUsageLimit`](/docs/en/settings-reference#autocontinueatusagelimit) in [managed settings](/docs/en/settings#settings-precedence).

230* **"You've hit your individual spend limit", "org's monthly spend limit", or "team's shared budget"**: the developer's request would be billed to usage credits, and those credits have reached a spend limit you set. To let the developer continue, go to [**Organization settings > Usage**](https://claude.ai/admin-settings/usage) and increase the limit the message names. When the message also names a plan reset time, the developer can instead wait until then. See [the error reference](/docs/en/errors#youve-hit-your-monthly-spend-limit) for each variant.

231* **A spend limit message from a [Claude apps gateway](/docs/en/claude-apps-gateway)**: the developer passed a spend cap you set on your self-hosted gateway, and the gateway blocks their requests until the period resets or you raise the cap. See [gateway spend limits](/docs/en/claude-apps-gateway-spend-limits) for caps, reset schedules, and the message the developer sees.

232* **A context or auto-compact warning**: not a usage limit. The conversation has grown close to the session's [auto-compact window](/docs/en/model-config#set-the-auto-compact-window), the threshold where Claude Code summarizes older history to free space. Point the developer at [reduce token usage](#reduce-token-usage).

229 * On Claude Code v2.1.234 or later, [wait and continue the interrupted task automatically after the reset](/docs/en/interactive-mode.md#wait-for-a-usage-limit-to-reset); that section lists when Claude Code starts the wait on its own and when the developer picks it from `/rate-limit-options`. To control for your fleet whether Claude Code starts that wait on its own, set [`autoContinueAtUsageLimit`](/docs/en/settings-reference#autocontinueatusagelimit) in [managed settings](/docs/en/settings.md#settings-precedence).

230* **"You've hit your individual spend limit", "org's monthly spend limit", or "team's shared budget"**: the developer's request would be billed to usage credits, and those credits have reached a spend limit you set. To let the developer continue, go to [**Organization settings > Usage**](https://claude.ai/admin-settings/usage) and increase the limit the message names. When the message also names a plan reset time, the developer can instead wait until then. See [the error reference](/docs/en/errors.md#youve-hit-your-monthly-spend-limit) for each variant.

231* **A spend limit message from a [Claude apps gateway](/docs/en/claude-apps-gateway)**: the developer passed a spend cap you set on your self-hosted gateway, and the gateway blocks their requests until the period resets or you raise the cap. See [gateway spend limits](/docs/en/claude-apps-gateway-spend-limits.md) for caps, reset schedules, and the message the developer sees.

232* **A context or auto-compact warning**: not a usage limit. The conversation has grown close to the session's [auto-compact window](/docs/en/model-config.md#set-the-auto-compact-window), the threshold where Claude Code summarizes older history to free space. Point the developer at [reduce token usage](#reduce-token-usage).

233233* **Unexpectedly high spend on an API or cloud-provider plan**: usually traces back to long sessions that were never cleared or to Opus left as the default model. The highest-impact habits to share are clearing between unrelated tasks and matching the model to the job, both covered in [reduce token usage](#reduce-token-usage).

234234

235235### Agent team token costs

236236

237[Agent teams](/docs/en/agent-teams) spawn multiple Claude Code instances, each with its own context window. Token usage scales with the number of active teammates and how long each one runs.

237[Agent teams](/docs/en/agent-teams.md) spawn multiple Claude Code instances, each with its own context window. Token usage scales with the number of active teammates and how long each one runs.

238238

239239To keep agent team costs manageable:

240240

from line 242

242242* Keep teams small. Each teammate runs its own context window, so token usage is roughly proportional to team size.

243243* Keep spawn prompts focused. Teammates load CLAUDE.md, MCP servers, and skills automatically, but everything in the spawn prompt adds to their context from the start.

244244* Shut down teammates when their work is done. Each active teammate continues consuming tokens until it exits or the session ends.

245* Agent teams are disabled by default. Set `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in your [settings.json](/docs/en/settings) or environment to enable them. See [enable agent teams](/docs/en/agent-teams#enable-agent-teams).

245* Agent teams are disabled by default. Set `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in your [settings.json](/docs/en/settings.md) or environment to enable them. See [enable agent teams](/docs/en/agent-teams.md#enable-agent-teams).

246246

247247## Reduce token usage

248248

249Token costs scale with context size: the more context Claude processes, the more tokens you use. Claude Code automatically optimizes costs through [prompt caching](/docs/en/prompt-caching), which reduces costs for repeated content like system prompts, and auto-compaction, which summarizes conversation history when approaching context limits.

249Token costs scale with context size: the more context Claude processes, the more tokens you use. Claude Code automatically optimizes costs through [prompt caching](/docs/en/prompt-caching.md), which reduces costs for repeated content like system prompts, and auto-compaction, which summarizes conversation history when approaching context limits.

250250

251251The following strategies help you keep context small and reduce per-message costs.

252252

253253### Manage context proactively

254254

255Use `/usage` to check your current token usage, or [configure your status line](/docs/en/statusline#context-window-usage) to display it continuously.

255Use `/usage` to check your current token usage, or [configure your status line](/docs/en/statusline.md#context-window-usage) to display it continuously.

256256

257257* **Clear between tasks**: Use `/clear` to start fresh when switching to unrelated work. Stale context wastes tokens on every subsequent message. Use `/rename` before clearing so you can find the session later, then `/resume` to return to it.

258258* **Add custom compaction instructions**: `/compact Focus on code samples and API usage` tells Claude what to preserve during summarization.

from line 267

267267

268268### Choose the right model

269269

270Sonnet handles most coding tasks well and costs less than Opus. Reserve Opus for complex architectural decisions or multi-step reasoning. Use `/model` to switch models mid-session, or set a default in `/config`. A switch to Opus also applies to the [subagents that inherit your session's model](/docs/en/model-config#setting-your-model). For simple subagent tasks, specify `model: haiku` in your [subagent configuration](/docs/en/sub-agents#choose-a-model).

270Sonnet handles most coding tasks well and costs less than Opus. Reserve Opus for complex architectural decisions or multi-step reasoning. Use `/model` to switch models mid-session, or set a default in `/config`. A switch to Opus also applies to the [subagents that inherit your session's model](/docs/en/model-config.md#setting-your-model). For simple subagent tasks, specify `model: haiku` in your [subagent configuration](/docs/en/sub-agents.md#choose-a-model).

271271

272272### Reduce MCP server overhead

273273

274MCP tool definitions are [deferred by default](/docs/en/mcp#scale-with-mcp-tool-search), so only tool names and server instructions enter context until Claude uses a specific tool. Run `/context` to see what's consuming space.

274MCP tool definitions are [deferred by default](/docs/en/mcp.md#scale-with-mcp-tool-search), so only tool names and server instructions enter context until Claude uses a specific tool. Run `/context` to see what's consuming space.

275275

276276* **Prefer CLI tools when available**: Tools like `gh`, `aws`, `gcloud`, and `sentry-cli` are still more context-efficient than MCP servers because they don't add any per-tool listing. Claude can run CLI commands directly.

277277* **Disable unused servers**: Run `/mcp` to see configured servers and disable any you're not actively using.

from line 278

278278

279279### Install code intelligence plugins for typed languages

280280

281[Code intelligence plugins](/docs/en/plugins/code-intelligence) give Claude precise symbol navigation instead of text-based search, reducing unnecessary file reads when exploring unfamiliar code. A single "go to definition" call replaces what might otherwise be a grep followed by reading multiple candidate files. Installed language servers also report type errors automatically after edits, so Claude catches mistakes without running a compiler.

281[Code intelligence plugins](/docs/en/plugins/code-intelligence.md) give Claude precise symbol navigation instead of text-based search, reducing unnecessary file reads when exploring unfamiliar code. A single "go to definition" call replaces what might otherwise be a grep followed by reading multiple candidate files. Installed language servers also report type errors automatically after edits, so Claude catches mistakes without running a compiler.

282282

283283### Offload processing to hooks and skills

284284

285Custom [hooks](/docs/en/hooks) can preprocess data before Claude sees it. Instead of Claude reading a 10,000-line log file to find errors, a hook can grep for `ERROR` and return only matching lines, reducing context from tens of thousands of tokens to hundreds.

285Custom [hooks](/docs/en/hooks.md) can preprocess data before Claude sees it. Instead of Claude reading a 10,000-line log file to find errors, a hook can grep for `ERROR` and return only matching lines, reducing context from tens of thousands of tokens to hundreds.

286286

287A [skill](/docs/en/skills) can give Claude domain knowledge so it doesn't have to explore. For example, a "codebase-overview" skill could describe your project's architecture, key directories, and naming conventions. When Claude invokes the skill, it gets this context immediately instead of spending tokens reading multiple files to understand the structure.

287A [skill](/docs/en/skills.md) can give Claude domain knowledge so it doesn't have to explore. For example, a "codebase-overview" skill could describe your project's architecture, key directories, and naming conventions. When Claude invokes the skill, it gets this context immediately instead of spending tokens reading multiple files to understand the structure.

288288

289289For example, this PreToolUse hook filters test output to show only failures:

290290

291291**settings.json**

292292

293Add this to your [settings.json](/docs/en/settings#where-settings-live) to run the hook before every Bash command:

293Add this to your [settings.json](/docs/en/settings.md#where-settings-live) to run the hook before every Bash command:

294294

295295```json theme={null}

296296{

from line 334

334334

335335### Move instructions from CLAUDE.md to skills

336336

337Your [CLAUDE.md](/docs/en/memory) file is loaded into context at session start. If it contains detailed instructions for specific workflows (like PR reviews or database migrations), those tokens are present even when you're doing unrelated work. [Skills](/docs/en/skills) load on-demand only when invoked, so moving specialized instructions into skills keeps your base context smaller. Aim to keep CLAUDE.md under 200 lines by including only essentials.

337Your [CLAUDE.md](/docs/en/memory.md) file is loaded into context at session start. If it contains detailed instructions for specific workflows (like PR reviews or database migrations), those tokens are present even when you're doing unrelated work. [Skills](/docs/en/skills.md) load on-demand only when invoked, so moving specialized instructions into skills keeps your base context smaller. Aim to keep CLAUDE.md under 200 lines by including only essentials.

338338

339339### Adjust extended thinking

340340

341341Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the default budget can be tens of thousands of tokens per request depending on the model.

342342

343For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, or by disabling thinking in `/config`. You can't turn off thinking on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fable models, which always use extended thinking.

343For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config.md#adjust-effort-level) with `/effort` or in `/model`, or by disabling thinking in `/config`. You can't turn off thinking on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fable models, which always use extended thinking.

344344

345On models with a [fixed thinking budget](/docs/en/model-config#adaptive-reasoning-and-fixed-thinking-budgets), you can also lower the budget by setting the `MAX_THINKING_TOKENS` [environment variable](/docs/en/env-vars), for example `MAX_THINKING_TOKENS=8000`. Adaptive-reasoning models ignore nonzero budgets, so use effort levels there instead.

345On models with a [fixed thinking budget](/docs/en/model-config.md#adaptive-reasoning-and-fixed-thinking-budgets), you can also lower the budget by setting the `MAX_THINKING_TOKENS` [environment variable](/docs/en/env-vars.md), for example `MAX_THINKING_TOKENS=8000`. Adaptive-reasoning models ignore nonzero budgets, so use effort levels there instead.

346346

347347### Delegate verbose operations to subagents

348348

349Running tests, fetching documentation, or processing log files can consume significant context. Delegate these to [subagents](/docs/en/sub-agents#isolate-high-volume-operations) so the verbose output stays in the subagent's context while only a summary returns to your main conversation.

349Running tests, fetching documentation, or processing log files can consume significant context. Delegate these to [subagents](/docs/en/sub-agents.md#isolate-high-volume-operations) so the verbose output stays in the subagent's context while only a summary returns to your main conversation.

350350

351The subagent's own requests still draw on your usage. To spend less on them, [choose a smaller model for a subagent](/docs/en/sub-agents#choose-a-model) or [run every subagent on one model](/docs/en/sub-agents#run-every-subagent-on-one-model).

351The subagent's own requests still draw on your usage. To spend less on them, [choose a smaller model for a subagent](/docs/en/sub-agents.md#choose-a-model) or [run every subagent on one model](/docs/en/sub-agents.md#run-every-subagent-on-one-model).

352352

353353### Manage agent team costs

354354

355Agent teams use approximately 7x more tokens than standard sessions when teammates run in plan mode, because each teammate maintains its own context window and runs as a separate Claude instance. Keep team tasks small and self-contained to limit per-teammate token usage. See [agent teams](/docs/en/agent-teams) for details.

356356

357357### Write specific prompts

358358

from line 362

362362

363363For longer or more complex work, these habits help avoid wasted tokens from going down the wrong path:

364364

365* **Use plan mode for complex tasks**: Press Shift+Tab to cycle to [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) before implementation. Claude explores the codebase and proposes an approach for your approval, preventing expensive re-work when the initial direction is wrong.

365* **Use plan mode for complex tasks**: Press Shift+Tab to cycle to [plan mode](/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode) before implementation. Claude explores the codebase and proposes an approach for your approval, preventing expensive re-work when the initial direction is wrong.

366366* **Course-correct early**: If Claude starts heading the wrong direction, press Escape to stop immediately. Use `/rewind` or double-tap Escape to restore conversation and code to a previous checkpoint.

367367* **Give verification targets**: Include test cases, paste screenshots, or define expected output in your prompt. When Claude can verify its own work, it catches issues before you need to request fixes.

368368* **Test incrementally**: Write one file, test it, then continue. This catches issues early.

from line 376

376376

377377These background processes consume a small amount of tokens (typically under \$0.04 per session) even without active interaction.

378378

379When prompt suggestions are on, Claude Code also sends a short request to the model your session is using after Claude responds, to [suggest your next prompt](/docs/en/interactive-mode#prompt-suggestions). That request reuses the conversation's prompt cache, so it is mostly cache reads plus a few output tokens. Claude Code [skips it while your account is close to or at its usage limit](/docs/en/interactive-mode#when-claude-code-skips-suggestions). To stop these requests, [turn prompt suggestions off](/docs/en/interactive-mode#turn-prompt-suggestions-off).

379When prompt suggestions are on, Claude Code also sends a short request to the model your session is using after Claude responds, to [suggest your next prompt](/docs/en/interactive-mode.md#prompt-suggestions). That request reuses the conversation's prompt cache, so it is mostly cache reads plus a few output tokens. Claude Code [skips it while your account is close to or at its usage limit](/docs/en/interactive-mode.md#when-claude-code-skips-suggestions). To stop these requests, [turn prompt suggestions off](/docs/en/interactive-mode.md#turn-prompt-suggestions-off).

380380

381381## Why usage climbs in a long session

382382

383383A session that has been open for hours can use far more of your plan limits than your activity suggests, usually for one of these reasons:

384384

385* **Long context**: Claude Code sends your full conversation with every request, and each time Claude uses tools it sends another request carrying that batch of tool results. With [prompt caching](/docs/en/prompt-caching), Claude Code re-reads that history at the [cached token rate](https://platform.claude.com/docs/en/about-claude/pricing), so a one-line question in a session that has been open all day still draws usage for the whole conversation. See [Manage context proactively](#manage-context-proactively) for ways to keep your context small

386* **Cache misses**: your first message after a break longer than the [cache lifetime](/docs/en/prompt-caching#cache-lifetime) misses the cache and reprocesses your full context. See [which lifetime your requests get](/docs/en/prompt-caching#which-ttl-each-request-gets) and [the controls for setting it](/docs/en/prompt-caching#choose-the-ttl-yourself)

387* **Scheduled tasks**: a [session-scoped scheduled task](/docs/en/scheduled-tasks) fires on its interval even while the session is idle, sending your full context each time

388* **Cross-session messages**: Claude Code delivers a [message from another of your sessions](/docs/en/cross-session-messaging) as a new turn when this session sits idle, sending your full context each time. To hold inbound messages instead of delivering them, set [`crossSessionInbound`](/docs/en/settings-reference#crosssessioninbound) to `hold`

389* **Goal check-ins**: while background work keeps an active [goal](/docs/en/goal) waiting, Claude Code [asks Claude to check on that work](/docs/en/goal#background-work-defers-evaluation) even when the session sits idle, starting a new turn that sends your full context. Claude Code starts at most three idle check-ins per goal between your prompts. Before v2.1.246, idle check-ins were uncapped. To turn check-ins off, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars) to `0`. Idle check-ins require Claude Code v2.1.236 or later

390* **Subagents and workflows**: every subagent, and every agent a [dynamic workflow](/docs/en/workflows#cost) spawns, sends its own requests on top of the main conversation's. The [attribution breakdown](#plan-usage-breakdown) shows the subagent share

385* **Long context**: Claude Code sends your full conversation with every request, and each time Claude uses tools it sends another request carrying that batch of tool results. With [prompt caching](/docs/en/prompt-caching.md), Claude Code re-reads that history at the [cached token rate](https://platform.claude.com/docs/en/about-claude/pricing), so a one-line question in a session that has been open all day still draws usage for the whole conversation. See [Manage context proactively](#manage-context-proactively) for ways to keep your context small

386* **Cache misses**: your first message after a break longer than the [cache lifetime](/docs/en/prompt-caching.md#cache-lifetime) misses the cache and reprocesses your full context. See [which lifetime your requests get](/docs/en/prompt-caching.md#which-ttl-each-request-gets) and [the controls for setting it](/docs/en/prompt-caching.md#choose-the-ttl-yourself)

387* **Scheduled tasks**: a [session-scoped scheduled task](/docs/en/scheduled-tasks.md) fires on its interval even while the session is idle, sending your full context each time

388* **Cross-session messages**: Claude Code delivers a [message from another of your sessions](/docs/en/cross-session-messaging.md) as a new turn when this session sits idle, sending your full context each time. To hold inbound messages instead of delivering them, set [`crossSessionInbound`](/docs/en/settings-reference#crosssessioninbound) to `hold`

389* **Goal check-ins**: while background work keeps an active [goal](/docs/en/goal.md) waiting, Claude Code [asks Claude to check on that work](/docs/en/goal.md#background-work-defers-evaluation) even when the session sits idle, starting a new turn that sends your full context. Claude Code starts at most three idle check-ins per goal between your prompts. Before v2.1.246, idle check-ins were uncapped. To turn check-ins off, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars) to `0`. Idle check-ins require Claude Code v2.1.236 or later

390* **Subagents and workflows**: every subagent, and every agent a [dynamic workflow](/docs/en/workflows.md#cost) spawns, sends its own requests on top of the main conversation's. The [attribution breakdown](#plan-usage-breakdown) shows the subagent share

391391* **Agent teammates**: each active [teammate](#agent-team-token-costs) keeps consuming tokens until it exits

392* **Compaction**: `/compact` reads the conversation it summarizes, so [compacting a large context](/docs/en/prompt-caching#compacting-the-conversation) is itself a large request. When you want a fresh start instead of continuity, `/clear` costs nothing

392* **Compaction**: `/compact` reads the conversation it summarizes, so [compacting a large context](/docs/en/prompt-caching.md#compacting-the-conversation) is itself a large request. When you want a fresh start instead of continuity, `/clear` costs nothing

393393

394394On a Pro, Max, Team, or Enterprise plan, the [`/usage` breakdown](#plan-usage-breakdown) recommends a change for behaviors behind 10% or more of your recent usage, such as long context or cache misses.

395395

cross-session-messaging Changed · +44 / -44 lines

from line 8

99Cross-session messaging lets Claude deliver a message from one of your Claude Code sessions to another. When a change in one session breaks what another is building on, Claude can warn that session before you notice. When one session settles a question another is blocked on, Claude can send the answer across.

1010

11A message is a piece of text one Claude writes to another, never the sender's conversation history or files. To move a whole conversation or its context, [resume the session](/docs/en/sessions#resume-a-session) instead.

1212

1313## When to use cross-session messaging

1414

from line 15

1515Use messaging when one of your sessions has something another session needs mid-task. Claude can send a message on its own when it sees the need, for example after making a change that affects work another session is doing, or you can ask it to send one. The common cases:

1616

1717* **Hand over a finding**: when one session discovers a breaking change or makes a decision, Claude summarizes it for the session working on the affected area, instead of you re-explaining it there.

18* **Coordinate parallel worktrees**: when sessions work the same repository in separate [worktrees](/docs/en/worktrees), Claude can tell the other sessions what landed.

18* **Coordinate parallel worktrees**: when sessions work the same repository in separate [worktrees](/docs/en/worktrees.md), Claude can tell the other sessions what landed.

1919* **Get status from long-running work**: have a migration or test run report back to the session you're watching, or ask it yourself from there. If that session is on this machine, Claude can also [ask it for one notice when it next goes idle or exits](#get-a-notice-when-another-session-goes-idle).

2020* **Message across machines**: reach one of your sessions on another machine or in the cloud.

2121

from line 35

3535Explain what we just did to the session working on the payments API

3636```

3737

38To name the target yourself, mention the session in your prompt: type `@` followed by the first letters of the session's name and pick the session from the typeahead, the same way you [@-mention a subagent](/docs/en/sub-agents#invoke-subagents-explicitly). Requires Claude Code v2.1.232 or later. Claude Code inserts the mention, such as `@api-worker`, and tells Claude which session it names, so Claude can message that session without listing your sessions first. This prompt names the target with a mention:

38To name the target yourself, mention the session in your prompt: type `@` followed by the first letters of the session's name and pick the session from the typeahead, the same way you [@-mention a subagent](/docs/en/sub-agents.md#invoke-subagents-explicitly). Requires Claude Code v2.1.232 or later. Claude Code inserts the mention, such as `@api-worker`, and tells Claude which session it names, so Claude can message that session without listing your sessions first. This prompt names the target with a mention:

3939

4040```text wrap theme={null}

4141Let @api-worker know the schema migration finished

from line 54

5454

5555The receiving Claude reads the message between tool calls during an active turn, so a running tool is never interrupted. When the receiving session is idle, Claude Code starts a new turn with the message.

5656

57A message from another session arrives as plain text. If it mentions a file or an [MCP resource](/docs/en/mcp#use-mcp-resources) with `@`, Claude sees the mention as written and Claude Code attaches nothing, whether the message starts a new turn or arrives during one. Claude can still open a mentioned path on the receiving machine with its own tools, subject to that session's permissions.

57A message from another session arrives as plain text. If it mentions a file or an [MCP resource](/docs/en/mcp.md#use-mcp-resources) with `@`, Claude sees the mention as written and Claude Code attaches nothing, whether the message starts a new turn or arrives during one. Claude can still open a mentioned path on the receiving machine with its own tools, subject to that session's permissions.

5858

5959Claude Code refuses a message in the following cases:

6060

from line 61

6161* The message is [over the size cap](#limitations). Claude Code refuses it in the sending session, before it leaves.

6262* A rapid burst to a session on this machine has reached [what that session's inbox accepts](#limitations). Claude Code refuses further messages to that session.

6363* A session beyond this machine is [listed as unable to receive cross-session messages](#message-sessions-on-other-machines). Claude Code refuses the message in the sending session, before it leaves this machine.

64* The reply target on this machine fails a safety check, such as a symlinked target. [Refusing to send a cross-session message](/docs/en/errors#refusing-to-send-a-cross-session-message) lists these checks.

64* The reply target on this machine fails a safety check, such as a symlinked target. [Refusing to send a cross-session message](/docs/en/errors.md#refusing-to-send-a-cross-session-message) lists these checks.

6565

6666The receiving session checks each arriving message against its own [inbound controls](#control-inbound-messages), and the check ends in one of three outcomes:

6767

from line 69

6969* **Held**: Claude Code sets the message aside undelivered. A held message reaches Claude only when you approve it or a later mode or settings change allows it.

7070* **Refused**: Claude Code drops the message without delivering it.

7171

72Once delivered, the message counts toward [usage](/docs/en/costs) like a prompt you type. The receiving Claude can reply to the sender with `SendMessage`, except in the cases under [Replies from other machines and cloud sessions](#replies-from-other-machines-and-cloud-sessions) and [Turn off cross-session messaging](#turn-off-cross-session-messaging).

72Once delivered, the message counts toward [usage](/docs/en/costs.md) like a prompt you type. The receiving Claude can reply to the sender with `SendMessage`, except in the cases under [Replies from other machines and cloud sessions](#replies-from-other-machines-and-cloud-sessions) and [Turn off cross-session messaging](#turn-off-cross-session-messaging).

7373

7474Permission boundaries stay per-session. Claude is instructed never to ask another session for an action that was denied or blocked in its own session, or that its own permission settings would block, and to route that work back to you instead. On the receiving side, the [receiving session's own permission prompts and rules still apply](#how-a-session-treats-an-incoming-message) to anything the message asks for.

7575

from line 107

107107Claude finds a message's target on its own, so you don't need to run anything before asking it to send. To see for yourself which sessions Claude can reach, run the `/list-agents` command. The first line, when present, is this session's own name, the one your other sessions use to message it. The rows below it are the sessions Claude can reach:

108108

109109* **Subagents**: agents running inside the current session.

110* **Teammates**: this session's own [agent team](/docs/en/agent-teams) teammates.

111* **Your other local sessions**: Claude Code sessions running on the same machine, including [background sessions](/docs/en/agent-view). A session appears only when it binds an [inbox socket](#the-sessions-inbox-socket).

112* **Your [cloud sessions](/docs/en/claude-code-on-the-web)**: shown while this session is connected to [Remote Control](/docs/en/remote-control).

113* **Your Remote Control sessions on other machines**: shown while this session is connected to [Remote Control](/docs/en/remote-control), and labeled `Remote Control`. Claude Code shows `offline` as the status of a session whose Remote Control connection has dropped.

110* **Teammates**: this session's own [agent team](/docs/en/agent-teams.md) teammates.

111* **Your other local sessions**: Claude Code sessions running on the same machine, including [background sessions](/docs/en/agent-view.md). A session appears only when it binds an [inbox socket](#the-sessions-inbox-socket).

112* **Your [cloud sessions](/docs/en/claude-code-on-the-web.md)**: shown while this session is connected to [Remote Control](/docs/en/remote-control.md).

113* **Your Remote Control sessions on other machines**: shown while this session is connected to [Remote Control](/docs/en/remote-control.md), and labeled `Remote Control`. Claude Code shows `offline` as the status of a session whose Remote Control connection has dropped.

114114

115While this session is connected to [Remote Control](/docs/en/remote-control), Claude Code withholds some details of your local sessions from the `/list-agents` output, without changing what Claude itself sees when it looks for a session to message:

115While this session is connected to [Remote Control](/docs/en/remote-control.md), Claude Code withholds some details of your local sessions from the `/list-agents` output, without changing what Claude itself sees when it looks for a session to message:

116116

117117* **Working directories**: it leaves out each local session's working directory.

118118* **Session names**: it leaves out any session name it can't attribute to a person, so a row left with no name reads `(unnamed session)`.

from line 120

120120

121121When the output lists anything, it ends with a note saying details were withheld. Running `/rename` followed by an unused name at a session's own keyboard gives that session a name that appears in the output.

122122

123A session answers to the name you set with the [`/rename`](/docs/en/commands) command or the [`--name`](/docs/en/cli-reference#cli-flags) flag. When you don't set one, Claude Code names the session itself. For an interactive session, that is the name shown in [listings of running sessions](/docs/en/sessions#name-your-sessions).

124124

125125Unless this session is connected to Remote Control, Claude Code shows each local session's working directory in the `/list-agents` output, so you can tell same-named sessions apart when they run in different directories. Claude addresses the message in one of two ways, depending on how many live sessions answer to the name:

126126

from line 134

134134| Where the other session runs | How the message travels |

135135| :- | :- |

136136| On this machine | Over a per-session socket on macOS and Linux, or a per-session named pipe on native Windows, never through Anthropic servers |

137| On another of your machines | Through Anthropic servers, arriving over that machine's [Remote Control](/docs/en/remote-control) connection |

138| In the [cloud](/docs/en/claude-code-on-the-web) | Through Anthropic servers, straight to the cloud session |

137| On another of your machines | Through Anthropic servers, arriving over that machine's [Remote Control](/docs/en/remote-control.md) connection |

138| In the [cloud](/docs/en/claude-code-on-the-web.md) | Through Anthropic servers, straight to the cloud session |

139139

140140Starting a conversation with a session on another of your machines requires Claude Code v2.1.225 or later and a target that [appears in the listing](#see-which-sessions-claude-can-reach).

141141

from line 150

150150

151151#### Replies from other machines and cloud sessions

152152

153A [cloud session](/docs/en/claude-code-on-the-web), including one on a [self-hosted runner](/docs/en/self-hosted-environments), can't use `SendMessage` to answer a message from another machine, even when the message carries a [reply address](#what-a-message-looks-like). The message still arrives. Read the cloud session's response in its transcript at [claude.ai/code](https://claude.ai/code).

153A [cloud session](/docs/en/claude-code-on-the-web.md), including one on a [self-hosted runner](/docs/en/self-hosted-environments), can't use `SendMessage` to answer a message from another machine, even when the message carries a [reply address](#what-a-message-looks-like). The message still arrives. Read the cloud session's response in its transcript at [claude.ai/code](https://claude.ai/code).

154154

155155If this session isn't connected to Remote Control when Claude sends to a session beyond this machine, the message still goes through, but without a [reply address](#what-a-message-looks-like). The receiving Claude can't answer it.

156156

from line 169

169169

170170Any of these shows you the full text:

171171

172* Press `Ctrl+O` to open the [transcript viewer](/docs/en/interactive-mode#transcript-viewer) and read the full text under the sender's session name.

173* In [fullscreen rendering](/docs/en/fullscreen#use-the-mouse), click a preview line that leaves part of the message out to expand it in place.

172* Press `Ctrl+O` to open the [transcript viewer](/docs/en/interactive-mode.md#transcript-viewer) and read the full text under the sender's session name.

173* In [fullscreen rendering](/docs/en/fullscreen.md#use-the-mouse), click a preview line that leaves part of the message out to expand it in place.

174174* In a session started with [`--verbose`](/docs/en/cli-reference#cli-flags), Claude Code shows the full text instead of the preview.

175175

176176The preview shortens only what you see. Whether or not you expand it, Claude reads the full message.

from line 191

191191| Value | Behavior |

192192| :- | :- |

193193| `accept` | Claude Code delivers each message to Claude |

194| `hold` | Claude Code shows a notice for each message and doesn't deliver it. If an `accept` later applies, per the [precedence rules](/docs/en/settings-reference#crosssessioninbound), Claude Code releases the held messages |

194| `hold` | Claude Code shows a notice for each message and doesn't deliver it. If an `accept` later applies, per the [precedence rules](/docs/en/settings-reference.md#crosssessioninbound), Claude Code releases the held messages |

195195| `refuse` | Claude Code drops each message without delivering it |

196196

197197Beyond editing a settings file, you can select the value in the `/config` row **Messages from your other sessions**. Claude Code writes the value you select to your user settings. The row requires Claude Code v2.1.232 or later and doesn't appear while managed settings or the `--settings` flag sets the key, since a user-settings value wouldn't apply then. Claude Code rejects the `/config crossSessionInbound=value` shorthand for this key.

198198

199To see which value applies, follow the `crossSessionInbound` precedence rules in the [settings reference](/docs/en/settings-reference#crosssessioninbound).

199To see which value applies, follow the `crossSessionInbound` precedence rules in the [settings reference](/docs/en/settings-reference.md#crosssessioninbound).

200200

201When no value applies, Claude Code decides per message from the two sessions' permission modes. It groups sessions that [bypass permission prompts](/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode) into one class, and every other session into the other. Plan mode counts as bypassing in interactive terminal sessions with bypass permissions available, and [auto](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), `acceptEdits`, and `dontAsk` count as prompting:

201When no value applies, Claude Code decides per message from the two sessions' permission modes. It groups sessions that [bypass permission prompts](/docs/en/permission-modes.md#skip-all-checks-with-bypasspermissions-mode) into one class, and every other session into the other. Plan mode counts as bypassing in interactive terminal sessions with bypass permissions available, and [auto](/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode), `acceptEdits`, and `dontAsk` count as prompting:

202202

203203* **The receiving session prompts for permissions**: Claude Code delivers each message. It holds one for your approval only when the sending session identifies itself as bypassing permission prompts.

204204* **The receiving session bypasses permission prompts**: Claude Code holds each message for your approval. It delivers one only when the sending session identifies itself as also bypassing.

from line 208

208208* **Approve** delivers that one message to Claude.

209209* **Deny**, or dismissing the dialog, drops it.

210210* When the dialog stays unanswered past the [`dialogExpiry`](/docs/en/settings-reference#dialogexpiry) deadline, Claude Code closes it and drops the message. The deadline defaults to five minutes.

211* While no terminal is attached to a [background session](/docs/en/agent-view), Claude Code leaves the dialog open past the deadline. After you attach, if the dialog stays unanswered for a full deadline period, Claude Code closes it and drops the message.

211* While no terminal is attached to a [background session](/docs/en/agent-view.md), Claude Code leaves the dialog open past the deadline. After you attach, if the dialog stays unanswered for a full deadline period, Claude Code closes it and drops the message.

212212* If this session's permission-mode class changes while messages are held, Claude Code re-applies the inbound rules, delivers the messages they now accept, and shows a notice.

213213

214214A session in the VS Code extension or the Desktop app can't show the dialog. Claude Code keeps a held message there until the same deadline, as [Non-interactive sessions](#non-interactive-sessions) describes.

from line 217

217217

218218### Non-interactive sessions

219219

220Claude Code binds an inbox socket for a [`claude -p`](/docs/en/headless) session like an interactive one, so a long-running `-p` worker can receive messages and appears in the listing. When you start a session in [bare mode](/docs/en/headless#start-faster-with-bare-mode), Claude Code doesn't bind the socket, so that session can't receive messages and doesn't appear in the agent list.

220Claude Code binds an inbox socket for a [`claude -p`](/docs/en/headless) session like an interactive one, so a long-running `-p` worker can receive messages and appears in the listing. When you start a session in [bare mode](/docs/en/headless.md#start-faster-with-bare-mode), Claude Code doesn't bind the socket, so that session can't receive messages and doesn't appear in the agent list.

221221

222222A `-p` session can't show the approval dialog. When the [inbound default](#control-inbound-messages) holds a message there, Claude Code keeps it for the same [`dialogExpiry`](/docs/en/settings-reference#dialogexpiry) deadline the dialog uses, five minutes by default:

223223

from line 237

237237You can find the socket's path in two places:

238238

239239* `/status` shows it in the `Peer address` row. The path is prefixed with `uds:`.

240* Claude Code exports it to [hooks](/docs/en/hooks) and Bash commands as the [`CLAUDE_CODE_MESSAGING_SOCKET`](/docs/en/env-vars#variables) environment variable:

240* Claude Code exports it to [hooks](/docs/en/hooks.md) and Bash commands as the [`CLAUDE_CODE_MESSAGING_SOCKET`](/docs/en/env-vars#variables) environment variable:

241241 * In a session that starts with messaging on, Claude Code exports the variable before any hook runs, including `SessionStart`.

242242

243243On macOS and Linux, Claude Code restricts the socket to your operating-system user. On native Windows, it instead requires each connection to authenticate first with a key that only your operating-system user can read. Either way, on a shared machine another user's sessions can't deliver to it.

from line 257

257257 * On Linux, including inside WSL 2, Claude Code can verify by process evidence even for a child that has already exited. On macOS it can verify that way only while the posting process is still running, and in a container where Claude Code runs as process ID 1 it has no process evidence at all. On native Windows it also has none.

258258 * On macOS after the posting process has exited and in containers where Claude Code runs as process ID 1, that process evidence is missing, and Claude Code instead verifies a child that sent the session's exported [`CLAUDE_CODE_MESSAGING_TOKEN`](/docs/en/env-vars#variables) in the auth line that opened its connection. On native Windows, that token is the only way Claude Code verifies an own-child message.

259259 * When Claude Code can verify neither way, it treats the message like any other that asserts no permission class, so a session that bypasses permission prompts holds it for your approval.

260* **Sandboxed sessions**: control whether a Bash command can reach the socket from inside the [sandbox](/docs/en/sandboxing) with the sandbox's Unix-socket settings, [`sandbox.network.allowAllUnixSockets` and `sandbox.network.allowUnixSockets`](/docs/en/settings-reference#sandbox-settings).

260* **Sandboxed sessions**: control whether a Bash command can reach the socket from inside the [sandbox](/docs/en/sandboxing.md) with the sandbox's Unix-socket settings, [`sandbox.network.allowAllUnixSockets` and `sandbox.network.allowUnixSockets`](/docs/en/settings-reference#sandbox-settings).

261261

262262## Restrict cross-session messaging

263263

from line 280

280280Receiving and sending are separate controls, so turn off whichever direction you need, or both. Use `crossSessionInbound` for messages that arrive, and permission rules for what Claude here can send or list:

281281

282282* **Stop receiving**: set `crossSessionInbound` to `refuse`, and Claude Code drops inbound peer messages without delivering them. From project or local settings, `refuse` applies over every other source, and from your user settings it applies unless managed settings or the `--settings` flag set a value.

283* **Stop sending and listing**: add [permission deny rules](/docs/en/permissions#tool-specific-permission-rules) naming `SendMessage` and `ListAgents`. Both take the bare tool name with no specifier.

283* **Stop sending and listing**: add [permission deny rules](/docs/en/permissions.md#tool-specific-permission-rules) naming `SendMessage` and `ListAgents`. Both take the bare tool name with no specifier.

284284

285Administrators can turn both sides off for an organization in [managed settings](/docs/en/managed-settings), combining the deny rules with the `refuse`:

285Administrators can turn both sides off for an organization in [managed settings](/docs/en/managed-settings.md), combining the deny rules with the `refuse`:

286286

287287```json theme={null}

288288{

from line 301

301301

302302* **Operating system**: available on macOS, Windows, and Linux, including Linux inside WSL 2.

303303

304* **Sessions on this machine**: available on every provider, including Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry, and in sessions that run with [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) off. On those providers, and with flag fetching off, same-machine messaging requires Claude Code v2.1.248 or later. Claude Code delivers these messages over a [per-session socket on your machine](#the-sessions-inbox-socket), never through Anthropic servers.

304* **Sessions on this machine**: available on every provider, including Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry, and in sessions that run with [feature-flag fetching](/docs/en/env-vars.md#features-that-need-feature-flag-fetching) off. On those providers, and with flag fetching off, same-machine messaging requires Claude Code v2.1.248 or later. Claude Code delivers these messages over a [per-session socket on your machine](#the-sessions-inbox-socket), never through Anthropic servers.

305305

306306 To stop a session from receiving them, set [`crossSessionInbound`](#turn-off-cross-session-messaging) to `refuse`.

307307

308* **Sessions beyond this machine**: Claude finds your [cloud sessions](/docs/en/claude-code-on-the-web) and your sessions on other machines from a session that is connected to Remote Control, which needs a claude.ai sign-in as this session's active authentication and the other [Remote Control requirements](/docs/en/remote-control#requirements). Claude can't find those sessions with an API key or on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry.

308* **Sessions beyond this machine**: Claude finds your [cloud sessions](/docs/en/claude-code-on-the-web.md) and your sessions on other machines from a session that is connected to Remote Control, which needs a claude.ai sign-in as this session's active authentication and the other [Remote Control requirements](/docs/en/remote-control.md#requirements). Claude can't find those sessions with an API key or on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry.

309309

310310To check a session, type `/list-agents`, also available as `/peers`. The result separates a session that doesn't have the feature from a session where something narrower blocked a message, such as a missing `SendMessage` tool or a refused send:

311311

from line 313

313313* **`/list-agents` works but a send didn't arrive**: messaging is on, and something narrower applies:

314314 * **Deny rules**: a [permission deny rule](#turn-off-cross-session-messaging) removes the `SendMessage` and `ListAgents` tools.

315315 * **Inbound controls**: the [receiving session's inbound controls](#control-inbound-messages) can hold or drop what you send it.

316 * **Cloud session missing**: a cloud session appears only while this session is connected to [Remote Control](/docs/en/remote-control).

317 * **Other-machine session missing**: a session on another of your machines appears only when it runs with [Remote Control](/docs/en/remote-control) and this session is connected as well.

316 * **Cloud session missing**: a cloud session appears only while this session is connected to [Remote Control](/docs/en/remote-control.md).

317 * **Other-machine session missing**: a session on another of your machines appears only when it runs with [Remote Control](/docs/en/remote-control.md) and this session is connected as well.

318318 * **Other-machine session `offline`**: a message to a session listed as `offline` goes through, but [arrives only after that session's machine reconnects](#message-sessions-on-other-machines).

319319 * **Cloud or other-machine session `can't receive cross-session messages`**: a message to a session listed with this condition [doesn't leave this machine](#message-sessions-on-other-machines), and the result under `SendMessage` begins `Not sent`.

320320 * **Older cloud or other-machine session missing**: Claude Code reads those session lists newest first and stops after a bounded number of pages, so Claude can't message a session that fell past them by name.

from line 325

325325

326326The limits here are properties of the messaging channel itself and apply wherever the feature runs. For platform and provider gaps, see [Availability](#availability) instead.

327327

328* **Plain text only**: Claude sends only plain text across sessions. Structured [agent team](/docs/en/agent-teams) protocol messages stay within a team.

329* **Same-machine message size is capped**: Claude Code refuses a message to a session on this machine once its serialized form passes about a million characters. The refusal [names the exact sizes](/docs/en/errors#message-too-large-for-cross-session-delivery). Nothing reaches the receiving session.

330* **Rapid bursts to one session are refused at the sender**: once a rapid burst of messages to a session on this machine reaches what that session's inbox accepts, Claude Code refuses further sends in the sending session. The [refusal names the burst](/docs/en/errors#too-many-messages-to-this-session-just-now) and tells Claude to batch the rest into one message or wait.

328* **Plain text only**: Claude sends only plain text across sessions. Structured [agent team](/docs/en/agent-teams.md) protocol messages stay within a team.

329* **Same-machine message size is capped**: Claude Code refuses a message to a session on this machine once its serialized form passes about a million characters. The refusal [names the exact sizes](/docs/en/errors.md#message-too-large-for-cross-session-delivery). Nothing reaches the receiving session.

330* **Rapid bursts to one session are refused at the sender**: once a rapid burst of messages to a session on this machine reaches what that session's inbox accepts, Claude Code refuses further sends in the sending session. The [refusal names the burst](/docs/en/errors.md#too-many-messages-to-this-session-just-now) and tells Claude to batch the rest into one message or wait.

331331* **Message loops are throttled**: in the receiving session, Claude Code rate-limits repeated messages per sender, drops identical repeats arriving within a short window, and queues at most 50 accepted messages for Claude to read. A message loop between two sessions therefore stops on its own.

332332

333333## Related resources

334334

335* [Subagents](/docs/en/sub-agents#resume-subagents) and [agent teams](/docs/en/agent-teams#messages-between-agents): messaging within a single session or team

336* [Background agents](/docs/en/agent-view): dispatch and monitor the parallel sessions you might message

337* [Remote Control](/docs/en/remote-control): connect this session to reach your sessions on other machines

338* [Channels](/docs/en/channels): push external events, such as CI results or chat messages, into a session

339* [Settings](/docs/en/settings-reference#all-settings): `crossSessionInbound`, `isolatePeerMachines`, and `dialogExpiry`

340* [Permission modes](/docs/en/permission-modes): the modes behind the inbound default's two classes

341* [Tools reference](/docs/en/tools-reference): the `ListAgents` and `SendMessage` rows in the tools table

342* [Run agents in parallel](/docs/en/agents): compare the ways Claude Code runs multiple agents

335* [Subagents](/docs/en/sub-agents.md#resume-subagents) and [agent teams](/docs/en/agent-teams.md#messages-between-agents): messaging within a single session or team

336* [Background agents](/docs/en/agent-view.md): dispatch and monitor the parallel sessions you might message

337* [Remote Control](/docs/en/remote-control.md): connect this session to reach your sessions on other machines

338* [Channels](/docs/en/channels.md): push external events, such as CI results or chat messages, into a session

339* [Settings](/docs/en/settings-reference.md#all-settings): `crossSessionInbound`, `isolatePeerMachines`, and `dialogExpiry`

340* [Permission modes](/docs/en/permission-modes.md): the modes behind the inbound default's two classes

341* [Tools reference](/docs/en/tools-reference.md): the `ListAgents` and `SendMessage` rows in the tools table

342* [Run agents in parallel](/docs/en/agents.md): compare the ways Claude Code runs multiple agents

343343

data-usage Changed · +17 / -17 lines

from line 19

1919

2020If you choose to send us feedback about Claude Code using the `/feedback` command, we may use your feedback to improve our products and services. Transcripts shared via `/feedback`, or via `/bug` and `/share`, which report through the same path, are retained for 5 years.

2121

22With [Claude-drafted feedback](/docs/en/tools-reference#sendfeedback-tool-behavior), Claude can also draft a feedback report and queue it on your machine for you to review. Claude Code sends nothing until you choose to send the draft, and a sent draft goes through the same submission path and retention as other `/feedback` reports.

22With [Claude-drafted feedback](/docs/en/tools-reference.md#sendfeedback-tool-behavior), Claude can also draft a feedback report and queue it on your machine for you to review. Claude Code sends nothing until you choose to send the draft, and a sent draft goes through the same submission path and retention as other `/feedback` reports.

2323

2424### Session quality surveys

2525

from line 31

3131* **No**: declines without sending anything

3232* **Don't ask again**: declines and stops this follow-up from appearing in future sessions

3333

34Nothing is uploaded unless you explicitly select **Yes**. Organizations with [zero data retention](/docs/en/zero-data-retention), or where product feedback is disabled by organization policy, or where `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` is set, never see this follow-up. Your responses to this survey, including session transcripts submitted after the rating prompt, do not impact your data training preferences and cannot be used to train our AI models.

34Nothing is uploaded unless you explicitly select **Yes**. Organizations with [zero data retention](/docs/en/zero-data-retention.md), or where product feedback is disabled by organization policy, or where `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` is set, never see this follow-up. Your responses to this survey, including session transcripts submitted after the rating prompt, do not impact your data training preferences and cannot be used to train our AI models.

3535

36To disable these surveys, set `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY=1`. The survey is also disabled when `DISABLE_TELEMETRY`, `DO_NOT_TRACK`, or `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` is set. Organizations that block nonessential traffic but capture survey responses through their own [OpenTelemetry collector](/docs/en/monitoring-usage) can opt the survey back in by setting `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL=1`. The survey then logs ratings to the configured collector only. The transcript-share follow-up and all other Anthropic-bound feedback traffic stay disabled. To control frequency instead of disabling, set [`feedbackSurveyRate`](/docs/en/settings-reference#feedbacksurveyrate) in your settings file to a probability between `0` and `1`.

36To disable these surveys, set `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY=1`. The survey is also disabled when `DISABLE_TELEMETRY`, `DO_NOT_TRACK`, or `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` is set. Organizations that block nonessential traffic but capture survey responses through their own [OpenTelemetry collector](/docs/en/monitoring-usage.md) can opt the survey back in by setting `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL=1`. The survey then logs ratings to the configured collector only. The transcript-share follow-up and all other Anthropic-bound feedback traffic stay disabled. To control frequency instead of disabling, set [`feedbackSurveyRate`](/docs/en/settings-reference#feedbacksurveyrate) in your settings file to a probability between `0` and `1`.

3737

3838### Data retention

3939

from line 48

4848**Commercial users (Team, Enterprise, and API)**:

4949

5050* Standard: 30-day retention period

51* [Zero data retention](/docs/en/zero-data-retention): available to qualified accounts for Claude Code on Claude for Enterprise. ZDR is not included in the standard Enterprise plan; it is enabled on a per-organization basis by your account team after confirming eligibility

52* Local caching: Claude Code clients store session transcripts locally in plaintext under `~/.claude/projects/` for 30 days by default to enable session resumption. Adjust the period with `cleanupPeriodDays`. See [application data](/docs/en/claude-directory#application-data) for what's stored and how to clear it.

51* [Zero data retention](/docs/en/zero-data-retention.md): available to qualified accounts for Claude Code on Claude for Enterprise. ZDR is not included in the standard Enterprise plan; it is enabled on a per-organization basis by your account team after confirming eligibility

52* Local caching: Claude Code clients store session transcripts locally in plaintext under `~/.claude/projects/` for 30 days by default to enable session resumption. Adjust the period with `cleanupPeriodDays`. See [application data](/docs/en/claude-directory.md#application-data) for what's stored and how to clear it.

5353

54 Transcripts of sessions started or most recently continued in Claude Desktop or Cowork are [exempt from that limit by default](/docs/en/claude-directory#cleaned-up-automatically).

54 Transcripts of sessions started or most recently continued in Claude Desktop or Cowork are [exempt from that limit by default](/docs/en/claude-directory.md#cleaned-up-automatically).

5555

56You can delete individual cloud sessions at any time. Deleting a session permanently removes the session's event data. For instructions on how to delete sessions, see [Delete sessions](/docs/en/claude-code-on-the-web#delete-sessions).

5757

5858Learn more about data retention practices in our [Privacy Center](https://privacy.anthropic.com/).

5959

from line 61

6161

6262## Data access

6363

64For all first party users, you can learn more about what data is logged for [local Claude Code](#local-claude-code-data-flow-and-dependencies) and [remote Claude Code](#cloud-execution-data-flow-and-dependencies). [Remote Control](/docs/en/remote-control) sessions follow the local data flow since all execution happens on your machine; while connected, the session transcript is also stored on Anthropic servers to sync the conversation across devices, as described in [Connection and security](/docs/en/remote-control#connection-and-security). Note for remote Claude Code, Claude accesses the repository where you initiate your Claude Code session. Claude does not access repositories that you have connected but have not started a session in.

64For all first party users, you can learn more about what data is logged for [local Claude Code](#local-claude-code-data-flow-and-dependencies) and [remote Claude Code](#cloud-execution-data-flow-and-dependencies). [Remote Control](/docs/en/remote-control.md) sessions follow the local data flow since all execution happens on your machine; while connected, the session transcript is also stored on Anthropic servers to sync the conversation across devices, as described in [Connection and security](/docs/en/remote-control.md#connection-and-security). Note for remote Claude Code, Claude accesses the repository where you initiate your Claude Code session. Claude does not access repositories that you have connected but have not started a session in.

6565

6666## Local Claude Code: Data flow and dependencies

6767

from line 75

7575

7676| Provider | Encryption at rest |

7777| - | - |

78| Anthropic API | Infrastructure-level disk encryption (AES-256). Enable [Zero Data Retention](/docs/en/zero-data-retention) for no server-side persistence. |

78| Anthropic API | Infrastructure-level disk encryption (AES-256). Enable [Zero Data Retention](/docs/en/zero-data-retention.md) for no server-side persistence. |

7979| Amazon Bedrock | AES-256 with AWS-managed keys. Customer-managed keys available via AWS KMS. |

8080| Google Cloud's Agent Platform | Google-managed encryption keys. CMEK available. |

8181| Microsoft Foundry | Depends on the deployment's [hosting option](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options). For Hosted on Azure deployments, prompts and completions remain within Azure; only usage metadata and content flagged by Anthropic's safety systems egress to Anthropic. For Hosted on Anthropic deployments, requests route to Anthropic infrastructure with AES-256 disk encryption. |

from line 84

8484

8585### Cloud execution: Data flow and dependencies

8686

87[Cloud sessions](/docs/en/claude-code-on-the-web) run in Anthropic-managed virtual machines by default instead of locally. Sessions your organization routes to a [self-hosted environment](/docs/en/self-hosted-environments) run on infrastructure you control; for what stays on your machines and what still goes to Anthropic, see [What stays on your infrastructure](/docs/en/self-hosted-environments#what-stays-on-your-infrastructure). In Anthropic-hosted cloud sessions:

87[Cloud sessions](/docs/en/claude-code-on-the-web.md) run in Anthropic-managed virtual machines by default instead of locally. Sessions your organization routes to a [self-hosted environment](/docs/en/self-hosted-environments) run on infrastructure you control; for what stays on your machines and what still goes to Anthropic, see [What stays on your infrastructure](/docs/en/self-hosted-environments#what-stays-on-your-infrastructure). In Anthropic-hosted cloud sessions:

8888

8989* **Code and data storage:** Your repository is cloned into the session's isolated VM. Anthropic stores the session transcript so you can return to the session later. Code and session data are subject to the [retention and usage policies](#data-retention) for your account type

9090* **Credentials:** GitHub credentials are stored encrypted on Anthropic's servers and never enter the VM. GitHub traffic from the VM goes through an Anthropic proxy that attaches them on the server side

from line 91

9191* **Network traffic:** All outbound traffic goes through a security proxy for audit logging and abuse prevention

9292* **Session data:** Prompts, code changes, and outputs follow the same data policies as local Claude Code usage

9393

94For security details about cloud execution, see [Security](/docs/en/security#cloud-execution-security).

94For security details about cloud execution, see [Security](/docs/en/security.md#cloud-execution-security).

9595

9696## Telemetry services

9797

98Claude Code sends two kinds of operational telemetry: usage metrics and error reports. You can turn each off individually with the environment variables below, or disable all non-essential traffic at once by setting `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`. Setting `DISABLE_TELEMETRY` or `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` also disables feature-flag evaluation, which can make [Remote Control](/docs/en/remote-control#requirements) unavailable; `DISABLE_ERROR_REPORTING` doesn't.

98Claude Code sends two kinds of operational telemetry: usage metrics and error reports. You can turn each off individually with the environment variables below, or disable all non-essential traffic at once by setting `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`. Setting `DISABLE_TELEMETRY` or `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` also disables feature-flag evaluation, which can make [Remote Control](/docs/en/remote-control.md#requirements) unavailable; `DISABLE_ERROR_REPORTING` doesn't.

9999

100100**Metrics**: latency, reliability, and usage patterns, sent to Anthropic and to third-party logging infrastructure over TLS. Metrics never include your code, prompts, or file paths. Set `DISABLE_TELEMETRY=1` to opt out.

101101

from line 108

108108* you're connecting directly to the Claude API

109109* your organization doesn't have a zero data retention or HIPAA agreement

110110

111When you run the `/feedback` command, a copy of your conversation history including code is sent to Anthropic. The `/bug` and `/share` commands submit through the same path. Before submitting a report from the feedback dialog, you choose how much history to include: the current session only, which is the default, or also other sessions from the same project over the last 24 hours or 7 days. Claude Code submits [Claude-drafted feedback](/docs/en/tools-reference#sendfeedback-tool-behavior) through the same path, including the transcript when you chose to include it on the draft's review screen. The data is encrypted in transit via TLS and stored in Google Cloud Storage, which encrypts stored data at rest by default. Optionally, a GitHub issue is created in the public repository. To opt out, set the `DISABLE_FEEDBACK_COMMAND` environment variable to `1`.

111When you run the `/feedback` command, a copy of your conversation history including code is sent to Anthropic. The `/bug` and `/share` commands submit through the same path. Before submitting a report from the feedback dialog, you choose how much history to include: the current session only, which is the default, or also other sessions from the same project over the last 24 hours or 7 days. Claude Code submits [Claude-drafted feedback](/docs/en/tools-reference.md#sendfeedback-tool-behavior) through the same path, including the transcript when you chose to include it on the draft's review screen. The data is encrypted in transit via TLS and stored in Google Cloud Storage, which encrypts stored data at rest by default. Optionally, a GitHub issue is created in the public repository. To opt out, set the `DISABLE_FEEDBACK_COMMAND` environment variable to `1`.

112112

113113When you use a third-party provider such as Amazon Bedrock or Google Cloud's Agent Platform, or have no Anthropic credentials configured, `/feedback` writes the report to a local archive under `~/.claude/feedback-bundles/` instead of sending it to Anthropic. Known API key and token patterns are redacted before the archive is written. Nothing leaves your machine until you send that file to your Anthropic account representative or attach it to a support request.

114114

115115## Default behaviors by API provider

116116

117By default, error reporting, telemetry, and bug reporting are disabled when using Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS. Session quality surveys and the WebFetch domain safety check are exceptions and run regardless of provider. On a signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) session, usage analytics, error reporting, and survey ratings to Anthropic are disabled by the gateway credential itself, with no setting to re-enable them. You can opt out of all non-essential traffic, including surveys, at once by setting `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`. This variable doesn't affect the WebFetch check or official plugin marketplace auto-install; each has its own opt-out: `skipWebFetchPreflight` in [settings](/docs/en/settings) for WebFetch, and `CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL` for the marketplace. Here are the full default behaviors:

117By default, error reporting, telemetry, and bug reporting are disabled when using Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS. Session quality surveys and the WebFetch domain safety check are exceptions and run regardless of provider. On a signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) session, usage analytics, error reporting, and survey ratings to Anthropic are disabled by the gateway credential itself, with no setting to re-enable them. You can opt out of all non-essential traffic, including surveys, at once by setting `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`. This variable doesn't affect the WebFetch check or official plugin marketplace auto-install; each has its own opt-out: `skipWebFetchPreflight` in [settings](/docs/en/settings.md) for WebFetch, and `CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL` for the marketplace. Here are the full default behaviors:

118118

120120| - | - | - | - | - | - |

from line 122

122122| **Error reports** | On for Pro and Max sign-ins on v2.1.198+, otherwise off. `DISABLE_ERROR_REPORTING=1` to disable. | Default off. `CLAUDE_CODE_USE_VERTEX` must be 1. | Default off. `CLAUDE_CODE_USE_BEDROCK` must be 1. | Default off. `CLAUDE_CODE_USE_FOUNDRY` must be 1. | Default off. `CLAUDE_CODE_USE_ANTHROPIC_AWS` must be 1. |

123123| **Claude API (`/feedback` reports)** | Default on. `DISABLE_FEEDBACK_COMMAND=1` to disable. | Default off. `CLAUDE_CODE_USE_VERTEX` must be 1. | Default off. `CLAUDE_CODE_USE_BEDROCK` must be 1. | Default off. `CLAUDE_CODE_USE_FOUNDRY` must be 1. | Default off. `CLAUDE_CODE_USE_ANTHROPIC_AWS` must be 1. |

124124| **Session quality surveys** | Default on. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY=1` to disable. | Default on. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY=1` to disable. | Default on. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY=1` to disable. | Default on. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY=1` to disable. | Default on. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY=1` to disable. |

125| **WebFetch domain safety check** | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings) to disable. |

125| **WebFetch domain safety check** | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings.md) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings.md) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings.md) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings.md) to disable. | Default on. `skipWebFetchPreflight: true` in [settings](/docs/en/settings.md) to disable. |

126126

127All environment variables can be checked into `settings.json` (see [settings reference](/docs/en/settings-reference)).

127All environment variables can be checked into `settings.json` (see [settings reference](/docs/en/settings-reference.md)).

128128

129129When a host platform sets `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`, metrics default to on for Google Cloud's Agent Platform, Amazon Bedrock, Microsoft Foundry, and Claude Platform on AWS, and follow the standard `DISABLE_TELEMETRY` opt-out. Error reporting and `/feedback` reports remain off by default on those providers.

130130

from line 132

132132

133133Before fetching a URL, the WebFetch tool sends the requested hostname to `api.anthropic.com` to check it against a safety blocklist maintained by Anthropic. Only the hostname is sent, not the full URL, path, or page contents. Claude Code caches a hostname that passes the check for five minutes, and re-checks a blocked or failed hostname on the next request.

134134

135This check runs regardless of which model provider you use and is not affected by `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`. If your network blocks `api.anthropic.com`, WebFetch requests fail until you either allowlist the domain or set `skipWebFetchPreflight: true` in [settings](/docs/en/settings). Disabling the check means WebFetch attempts to retrieve any URL without consulting the blocklist, so combine it with [`WebFetch` permission rules](/docs/en/permissions#webfetch) if you need to restrict which domains Claude can reach.

135This check runs regardless of which model provider you use and is not affected by `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`. If your network blocks `api.anthropic.com`, WebFetch requests fail until you either allowlist the domain or set `skipWebFetchPreflight: true` in [settings](/docs/en/settings.md). Disabling the check means WebFetch attempts to retrieve any URL without consulting the blocklist, so combine it with [`WebFetch` permission rules](/docs/en/permissions#webfetch) if you need to restrict which domains Claude can reach.

136136

debug-your-config Changed · +30 / -30 lines

from line 4

55When Claude ignores an instruction or a feature you configured doesn't appear, the cause is usually that the file didn't load, it loaded from a different location than you expected, or another file overrode it. This guide shows how to inspect what Claude Code actually loaded so you can narrow down which applies.

7For installation, authentication, and connectivity problems, see [Troubleshoot installation and login](/docs/en/troubleshoot-install) instead.

7For installation, authentication, and connectivity problems, see [Troubleshoot installation and login](/docs/en/troubleshoot-install.md) instead.

99## See what loaded into context

1010

11The `/context` command shows everything occupying the context window for the current session, broken down by category: system prompt, system tools, MCP tools, custom subagents with the source each loaded from, memory files, skills, and conversation messages. Run it first to confirm whether your `CLAUDE.md`, rules, or skill descriptions are present at all. The skills section in `/context` also includes [bundled skills](/docs/en/skills#bundled-skills), which `/skills` doesn't list.

1212

1313For detail on a specific category, follow up with the dedicated command:

1414

from line 19

1919| `/hooks` | Active hook configurations |

2020| `/mcp` | Connected MCP servers and their status |

2121| `/permissions` | Resolved allow and deny rules currently in effect |

22| `/doctor` | Setup checkup: installation health, invalid settings files, unused extensions, duplicate [subagent](/docs/en/sub-agents) names in the same directory, and checked-in `CLAUDE.md` content Claude can derive from the codebase, with proposed fixes |

22| `/doctor` | Setup checkup: installation health, invalid settings files, unused extensions, duplicate [subagent](/docs/en/sub-agents.md) names in the same directory, and checked-in `CLAUDE.md` content Claude can derive from the codebase, with proposed fixes |

2323| `/debug [issue]` | Enables debug logging for the session and prompts Claude to diagnose using the log output and settings paths |

2424| `/status` | Active settings sources, including whether managed settings are in effect |

2525

26If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md` files load on demand rather than at session start, so they don't appear in that breakdown.

26If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory.md#how-claude-md-files-load). Subdirectory `CLAUDE.md` files load on demand rather than at session start, so they don't appear in that breakdown.

2727

2828If `/context` confirms the file loaded but Claude still isn't following a particular instruction, the issue is likely how the instruction is written rather than whether it loaded. CLAUDE.md works well for the kinds of guidance you'd give a new teammate, such as project conventions, build commands, and where files belong.

2929

30Adherence drops when an instruction is vague enough to interpret multiple ways, when two files give conflicting direction, or when the file has grown long enough that individual rules get less attention. [Write effective instructions](/docs/en/memory#write-effective-instructions) covers the specificity, size, and structure patterns that keep adherence high.

30Adherence drops when an instruction is vague enough to interpret multiple ways, when two files give conflicting direction, or when the file has grown long enough that individual rules get less attention. [Write effective instructions](/docs/en/memory.md#write-effective-instructions) covers the specificity, size, and structure patterns that keep adherence high.

3131

3232> [!NOTE]

3333>

34> CLAUDE.md and permissions solve different problems. CLAUDE.md tells Claude how your project works so it makes good decisions. [Permissions](/docs/en/permissions) and [hooks](/docs/en/hooks) enforce limits regardless of what Claude decides. Use CLAUDE.md for "we do it this way here." Use permissions or hooks for security boundaries and anything that must never happen, where you need a guarantee instead of guidance.

34> CLAUDE.md and permissions solve different problems. CLAUDE.md tells Claude how your project works so it makes good decisions. [Permissions](/docs/en/permissions.md) and [hooks](/docs/en/hooks.md) enforce limits regardless of what Claude decides. Use CLAUDE.md for "we do it this way here." Use permissions or hooks for security boundaries and anything that must never happen, where you need a guarantee instead of guidance.

3535

3636## Check resolved settings

3737

38Settings merge across managed, user, project, and local scopes. Managed settings apply first when present. Among the rest, the closer scope overrides the broader one in the order local, then project, then user. Some settings can also be set by command-line flags or [environment variables](/docs/en/env-vars), which act as another override layer. When a setting doesn't seem to apply, the value you set is usually being overridden by another scope or an environment variable.

38Settings merge across managed, user, project, and local scopes. Managed settings apply first when present. Among the rest, the closer scope overrides the broader one in the order local, then project, then user. Some settings can also be set by command-line flags or [environment variables](/docs/en/env-vars.md), which act as another override layer. When a setting doesn't seem to apply, the value you set is usually being overridden by another scope or an environment variable.

3939

4040To find invalid settings files, run `claude doctor` from your terminal. It prints read-only installation and settings diagnostics without starting a session. For a full checkup that also proposes fixes and asks before applying them, run [`/doctor`](/docs/en/commands#all-commands) inside a session.

4141

42Run `/status` to see which settings sources are active, including whether managed settings are in effect. To understand which scope Claude Code uses for a given key, see [Settings precedence](/docs/en/settings#settings-precedence).

4343

4444## Check MCP servers

4545

from line 49

4949* A server that fails to start shows as failed in `/mcp`. Relative file paths in `command` or `args` are a frequent cause, since they resolve against the directory you launched Claude Code from rather than the location of `.mcp.json`.

5050* A server that shows as connected but lists zero tools has started successfully but isn't returning a tool list. Select **Reconnect** from `/mcp`. If the count stays at zero, run `claude --debug=mcp` and read the server's stderr in the debug log at `~/.claude/debug/<session-id>.txt`.

5151

52For configuration locations and scope rules, see [MCP](/docs/en/mcp).

52For configuration locations and scope rules, see [MCP](/docs/en/mcp.md).

5353

5454## Check hooks

5555

5656Run `/hooks` to list every hook registered for the current session, grouped by event. If a hook you defined doesn't appear, Claude Code didn't load it. Check for these causes:

5757

58* The hook is defined in a standalone file. Hooks go under the `"hooks"` key in a [settings file](/docs/en/settings#settings-files).

58* The hook is defined in a standalone file. Hooks go under the `"hooks"` key in a [settings file](/docs/en/settings.md#settings-files).

5959* The `matcher` value is an array instead of a single string. Claude Code lists the entry as an invalid setting when you start an interactive session and in `claude doctor`. If the array is under `PreToolUse` or `PermissionRequest`, none of that file's other hooks load either.

60* The hook is in a skill's frontmatter, and neither you nor Claude has invoked the skill yet in this session. Invoke it or ask Claude to, then run `/hooks` again. If the hook still doesn't appear, check for other causes, such as [frontmatter that didn't parse](/docs/en/skills#skill-not-triggering) or one of the [limits on skill hooks](/docs/en/hooks#limits-on-skill-hooks).

60* The hook is in a skill's frontmatter, and neither you nor Claude has invoked the skill yet in this session. Invoke it or ask Claude to, then run `/hooks` again. If the hook still doesn't appear, check for other causes, such as [frontmatter that didn't parse](/docs/en/skills.md#skill-not-triggering) or one of the [limits on skill hooks](/docs/en/hooks.md#limits-on-skill-hooks).

6161

6262If the hook appears but doesn't fire, the matcher is the usual cause. Check it for these mistakes:

6363

from line 68

6868

6969If `/hooks` still shows the old definition a few seconds after you save, run `/hooks` again to refresh the view.

7070

71If `/hooks` shows the hook but it still does not fire, the next step is to watch hook evaluation live. Start a session with `claude --debug` and trigger the tool call. The debug log records each event, which matchers were checked, and the hook's exit code and output. See [Debug hooks](/docs/en/hooks#debug-hooks) for the log format and [hooks troubleshooting](/docs/en/hooks-guide#limitations-and-troubleshooting) for common failure patterns.

71If `/hooks` shows the hook but it still does not fire, the next step is to watch hook evaluation live. Start a session with `claude --debug` and trigger the tool call. The debug log records each event, which matchers were checked, and the hook's exit code and output. See [Debug hooks](/docs/en/hooks.md#debug-hooks) for the log format and [hooks troubleshooting](/docs/en/hooks-guide.md#limitations-and-troubleshooting) for common failure patterns.

7272

7373## Test against a clean configuration

7474

from line 125

125125claude --setting-sources user

126126```

127127

128On the first launch, you go through the first-run setup screens again, a sign that the clean configuration directory is in effect. Managed settings still apply, and [connectors](/docs/en/mcp#use-mcp-servers-from-claude-ai) still load if you log in with a claude.ai account.

128On the first launch, you go through the first-run setup screens again, a sign that the clean configuration directory is in effect. Managed settings still apply, and [connectors](/docs/en/mcp.md#use-mcp-servers-from-claude-ai) still load if you log in with a claude.ai account.

129129

130130**3. Reproduce the problem**

131131

from line 132

132132Repeat what triggered the problem in the clean session:

133133

134134* **Problem gone**: the cause is in your user or project configuration. Copy `~/.claude.json` and the files in `~/.claude` into `~/claude-clean/config` one at a time. If none brings the problem back, go to your project directory in the same shell and start Claude Code without `--setting-sources user`. In Bash or Zsh, run `CLAUDE_CONFIG_DIR=~/claude-clean/config claude`. In PowerShell, the variable is still set, so run `claude`.

135* **Problem persists**: the cause is outside your user and project configuration. Run `/status` in the session to check for managed settings, check your shell for [environment variables](/docs/en/env-vars), then see [Troubleshooting](/docs/en/troubleshooting).

135* **Problem persists**: the cause is outside your user and project configuration. Run `/status` in the session to check for managed settings, check your shell for [environment variables](/docs/en/env-vars.md), then see [Troubleshooting](/docs/en/troubleshooting.md).

136136

137137## Check common causes

138138

from line 140

140140

141141| Symptom | Cause | Fix |

142142| :- | :- | :- |

144144| Hook never fires | `matcher` uses `,` as a separator on a version before v2.1.191 | Claude Code v2.1.191 or later treats `,` as a list separator like `\|`. Earlier versions evaluate a comma as a literal character, so `"Edit,Write"` matches nothing. Use `\|` instead, or upgrade Claude Code. |

145145| Hook never fires | `matcher` value is lowercase, for example `"bash"` | Matching is case-sensitive. Tool names are capitalized: `Bash`, `Edit`, `Write`, `Read`. |

146| Hook never fires | Hooks are defined in a standalone file instead of `settings.json` | There is no standalone hooks file for project or user config. Define hooks under the `"hooks"` key in `settings.json`. Only [plugins](/docs/en/plugins/components#hooks) load a separate `hooks/hooks.json`. See [hook configuration](/docs/en/hooks). |

146| Hook never fires | Hooks are defined in a standalone file instead of `settings.json` | There is no standalone hooks file for project or user config. Define hooks under the `"hooks"` key in `settings.json`. Only [plugins](/docs/en/plugins/components.md#hooks) load a separate `hooks/hooks.json`. See [hook configuration](/docs/en/hooks.md). |

147147| Permissions or hooks set globally are ignored | Configuration was added to `~/.claude.json` | `~/.claude.json` holds app state and UI toggles. `permissions`, `hooks`, and `env` belong in `~/.claude/settings.json`. These are two different files. |

148| A `settings.json` value seems ignored | The same key is set in `settings.local.json` | `settings.local.json` overrides `settings.json`, and both override `~/.claude/settings.json`. See [settings precedence](/docs/en/settings#settings-precedence). |

149149| Skill doesn't appear in `/skills` | Skill file is at `.claude/skills/name.md` instead of in a folder | Use a folder with `SKILL.md` inside: `.claude/skills/name/SKILL.md`. |

150| Skill appears in `/skills` but Claude never invokes it | Skill has `disable-model-invocation: true` in its frontmatter, or its description doesn't match how you phrase the request | Check the badge in `/skills`: a "user-only" label means Claude won't trigger it on its own. See [skill invocation](/docs/en/skills). |

151| Subdirectory `CLAUDE.md` instructions seem ignored | Subdirectory files load on demand, not at session start | To load a subdirectory's `CLAUDE.md`, ask Claude to read another file in that subdirectory. See [when subdirectory files load](/docs/en/memory#how-claude-md-files-load). |

152| Subagent ignores `CLAUDE.md` instructions | The built-in Explore and Plan agents skip `CLAUDE.md` at startup. A custom subagent loads it the same way the main conversation does, unless it has [`omitClaudeMd`](/docs/en/sub-agents#supported-frontmatter-fields) set in its definition | For Explore or Plan, restate the instruction in your delegating prompt. For a subagent that sets `omitClaudeMd`, remove the field. For any other custom subagent, put critical instructions in the agent file body, which becomes the agent's system prompt. See [what loads at startup](/docs/en/sub-agents#what-loads-at-startup). |

153| Cleanup logic never runs at session end | No `SessionEnd` hook configured | Add a `SessionEnd` hook in `settings.json`. See the [hook events list](/docs/en/hooks#hook-events). |

154| MCP servers in `.mcp.json` never load | File is under `.claude/`, or its servers sit under a top-level `servers` key, as in VS Code's `mcp.json`, instead of `mcpServers` | Project MCP config goes at the repository root as `.mcp.json`, not inside `.claude/`, with servers under the `mcpServers` key. See [MCP configuration](/docs/en/mcp). |

155| MCP servers added under `mcpServers` in `settings.json` never appear | `settings.json` does not read an `mcpServers` key | Define project servers in `.mcp.json` at the repository root, or run `claude mcp add --scope user` for user-scoped servers. See [MCP configuration](/docs/en/mcp). |

153| Cleanup logic never runs at session end | No `SessionEnd` hook configured | Add a `SessionEnd` hook in `settings.json`. See the [hook events list](/docs/en/hooks.md#hook-events). |

156156| Project MCP server added but doesn't appear | The one-time approval prompt was dismissed | Project-scoped servers require approval. Run `/mcp` to see status and approve. |

157157| MCP server fails to start from some directories | `command` or `args` uses a relative file path | Use absolute paths for local scripts. Executables on your `PATH` like `npx` or `uvx` work as-is. |

158| MCP server starts without expected environment variables | The server's config entry doesn't set them, and they aren't in the environment Claude Code passes to stdio servers: its own environment, minus the [variables it strips from subprocesses](/docs/en/monitoring-usage#administrator-configuration) | Set per-server `env` inside the server's `.mcp.json` entry, which doesn't depend on the launch environment or workspace trust. |

159| `Bash(rm *)` deny rule doesn't block `/bin/rm` or `find -delete` | Bash rules match the literal command string, not the underlying executable; see [what a Bash rule doesn't match](/docs/en/permissions#bash-rule-limits) | Use a [PreToolUse hook](/docs/en/hooks-guide) or the [sandbox](/docs/en/sandboxing) for a hard guarantee. |

158| MCP server starts without expected environment variables | The server's config entry doesn't set them, and they aren't in the environment Claude Code passes to stdio servers: its own environment, minus the [variables it strips from subprocesses](/docs/en/monitoring-usage.md#administrator-configuration) | Set per-server `env` inside the server's `.mcp.json` entry, which doesn't depend on the launch environment or workspace trust. |

159| `Bash(rm *)` deny rule doesn't block `/bin/rm` or `find -delete` | Bash rules match the literal command string, not the underlying executable; see [what a Bash rule doesn't match](/docs/en/permissions.md#bash-rule-limits) | Use a [PreToolUse hook](/docs/en/hooks-guide.md) or the [sandbox](/docs/en/sandboxing.md) for a hard guarantee. |

160160

161161## Related resources

162162

from line 163

163163For full reference on each configuration surface, see the dedicated page:

164164

165165* **[`.claude` directory reference](/docs/en/claude-directory)**: every config file location and what reads it

166* **[Settings](/docs/en/settings)**: which file to use and which value Claude Code uses; the [settings reference](/docs/en/settings-reference) has the full key list

167* **[Hooks reference](/docs/en/hooks)**: event names, payloads, and `--debug` output format

168* **[MCP](/docs/en/mcp)**: server configuration, approval, and `/mcp` output

169* **[Troubleshoot installation and login](/docs/en/troubleshoot-install)**: `command not found`, PATH, and authentication problems

170* **[Troubleshooting](/docs/en/troubleshooting)**: performance, hangs, and search issues

166* **[Settings](/docs/en/settings.md)**: which file to use and which value Claude Code uses; the [settings reference](/docs/en/settings-reference.md) has the full key list

167* **[Hooks reference](/docs/en/hooks.md)**: event names, payloads, and `--debug` output format

168* **[MCP](/docs/en/mcp.md)**: server configuration, approval, and `/mcp` output

169* **[Troubleshoot installation and login](/docs/en/troubleshoot-install.md)**: `command not found`, PATH, and authentication problems

170* **[Troubleshooting](/docs/en/troubleshooting.md)**: performance, hangs, and search issues

171171