1,040 pages for comm.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
inference-hooks
Claude Developer Platform · in the page
manage-claude/inference-hooks
…ll in Slack, so the edit or deletion comes first. See the [`!restart` command](https://claude.com/docs/claude-tag/users/commands#restart-a-stuck-or-wrong-context-session). *** ## Use cases * **Data…
inference-hooks-configuration
Claude Developer Platform · in the page
manage-claude/inference-hooks-configuration
…handshake. Click **Save** to store any headers you entered. Common failure results: | Result | What to check…
inference-hooks-endpoint
Claude Developer Platform · in the page
manage-claude/inference-hooks-endpoint
…dies under about 10 MB, but the protocol allows up to 64 MiB. Several common defaults are much smaller, including nginx `client_max_body_size` at 1 MB and Express `express.json()` at 100 kB, and a rej…
ip-allowlist
Claude Developer Platform · in the page
manage-claude/ip-allowlist
…s available in beta under your agreement with Anthropic, such as the [Commercial Terms of Service](https://www.anthropic.com/legal/commercial-terms) and the [Service Specific Terms](https://www.anthro…
plugins-api
Claude Developer Platform · in the page
manage-claude/plugins-api
…ds when a task calls for it. | | Command | A saved prompt a member runs by typing `/` followed by the command’s name. | | Agent…
rate-limits-api
Claude Developer Platform · in the page
manage-claude/rate-limits-api
…Limits()`; php: `$client->organization->workspaces->rateLimits`). The comments in each list example say whether it fetches more pages or reads only the first. ## Quick start List the rate limits con…
usage-cost-analytics-api
Claude Developer Platform · in the page
manage-claude/usage-cost-analytics-api
…ull` on every row. <Warning> Requests served under a Priority Tier commitment appear on the usage endpoint with `service_tier: "priority"` but contribute zero token cost to `amount` and `list_amoun…
First request
Claude Developer Platform · in the page
manage-claude/usage-cost-api
…latform.claude.com/docs/en/manage-claude/usage-cost-analytics-api) (recommended), or the legacy Usage and Cost Admin API described on this page…
user-management
Claude Developer Platform · in the page
manage-claude/user-management
…ook up a specific member; the match is case-insensitive and tolerates common variants of the same address (for example, `[email protected]` matches `[email protected]`). Requires the `read:member…
user-profiles
Claude Developer Platform · in the page
manage-claude/user-profiles
…who can manage IAM in the AWS account or Google Cloud project runs a command that the portal provides. 3. The admin or owner completes the verification in the portal. Programs that apply to a profil…
wif-admin-api
Claude Developer Platform · in the page
manage-claude/wif-admin-api
…are short-lived. If requests start returning 401, rerun the `export` command to refresh the token. The SDK and the `ant` CLI read `ANTHROPIC_AUTH_TOKEN` automatically. Leave `ANTHROPIC_API_KEY` unse…
aws
Claude Developer Platform · in the page
manage-claude/wif-providers/aws
…tatic API keys by exchanging an AWS-signed OIDC identity token. The recommended path calls the AWS STS [`GetWebIdentityToken`](https://docs.aws.amazon.com/STS/latest/APIReference/API_GetWebIdentityTok…
Create the app registration that represents the Claude API audience.
Claude Developer Platform · in the page
manage-claude/wif-providers/azure
…_id=<IDENTITY_CLIENT_ID>` to the token request to select one. Azure recommends always specifying it. Without it, the outcome depends on whether the resource also has a system-assigned identity enabled…
gcp
Claude Developer Platform · in the page
manage-claude/wif-providers/gcp
…reference these claims in a federation rule’s `condition` matcher, a Common Expression Language (CEL) expression such as `claims.google.compute_engine.project_id == "my-project"`. <Note> Y…
github-actions
Claude Developer Platform · in the page
manage-claude/wif-providers/github-actions
…eshoot-a-failed-exchange) walks through the checks in order. The most common GitHub Actions-side cause is a `sub` claim format that doesn’t match, because its trailing segment varies among `ref:...`,…
kubernetes
Claude Developer Platform · in the page
manage-claude/wif-providers/kubernetes
…the [`--service-account-issuer`](https://kubernetes.io/docs/reference/command-line-tools-reference/kube-apiserver/) flag configured on the API server. Most distributions set this by default, and kubea…
okta
Claude Developer Platform · in the page
manage-claude/wif-providers/okta
…admin console version. The following numbered steps walk through one common path: 1. **Create a service app integration.** In the Okta Admin Console, create a new app integration of type **API Servi…
Replace NODE_UID with the node's UID:
Claude Developer Platform · in the page
manage-claude/wif-providers/spiffe
…pire-about/) is its open-source reference implementation, and several commercial products also issue SPIFFE-conformant identities. Anthropic federates with any SPIFFE implementation that emits OIDC-co…
wif-reference
Claude Developer Platform · in the page
manage-claude/wif-reference
…ion_id`, `workspace_id`, and `base_url`. | Non-secret. Safe to commit or build into an image. | | `<config_dir>/credentials/<profile>.json` | `version`, the cached `access_token`, `expires_at`,…
workload-identity-federation
Claude Developer Platform · in the page
manage-claude/workload-identity-federation
…subject_prefix`, an exact `audience`, a map of exact claim values, a [Common Expression Language (CEL)](https://cel.dev/) `condition` expression for complex logic, or any combination. A `subject_prefi…
workspaces
Claude Developer Platform · in the page
manage-claude/workspaces
…ault Workspace are reported under the Default Workspace’s own ID. ## Common use cases ### Environment separation Create separate workspaces for development, staging, and production: | Workspace…
agent-setup
Claude Developer Platform · in the page
managed-agents/agent-setup
…g-assistant.md`, prints its ID, and records it in `claude-lock.json`. Commit `claude-lock.json` so the next `ant apply` updates this agent instead of creating a second one. </CodeGroupItem> ```py…
choosing-an-environment
Claude Developer Platform · in the page
managed-agents/choosing-an-environment
…x is an isolated workspace, such as a container, where the agent runs commands and works on files. You have two options: * **Cloud environment:** Anthropic runs the sandbox for you. Each session gets…
cloud-sandboxes-reference
Claude Developer Platform · in the page
managed-agents/cloud-sandboxes-reference
…| | C/C++ | GCC 13 and Clang | make, cmake, ninja | Common Python data and document libraries, including NumPy, pandas, Matplotlib, openpyxl, python-docx, python-pptx, and pypdf, are…
environments
Claude Developer Platform · in the page
managed-agents/environments
…vironment.yaml`, prints its ID, and records it in `claude-lock.json`. Commit `claude-lock.json` so the next `ant apply` updates this environment instead of attempting to create it again. </CodeGroup…
event-deltas
Claude Developer Platform · in the page
managed-agents/event-deltas
…nguage="cURL"> This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it. </CodeGroupItem>…
events-and-streaming
Claude Developer Platform · in the page
managed-agents/events-and-streaming
…beta Claude Models on Google Cloud (Anthropic managed): beta --- Communication with Claude Managed Agents is event-based. You open a stream to follow a session, send events to direct it, and answ…
github
Claude Developer Platform · in the page
managed-agents/github
…reated. A public repository clones without a token, and the agent can commit in its clone, but `git push` fails. It is not echoed in API responses. See [Token permissions](https://platform.claude.com/…
mcp-connector
Claude Developer Platform · in the page
managed-agents/mcp-connector
…{ "name": "list_issues", "enabled": true }, { "name": "add_issue_comment", "enabled": true } ] } ``` This pattern is useful when a server exposes many tools but the agent only needs a few, or…
memory
Claude Developer Platform · in the page
managed-agents/memory
…when different parts of memory have different owners or access rules. Common reasons: * **Shared reference material:** one read-only store attached to many sessions (standards, conventions, domain kn…
migration
Claude Developer Platform · in the page
managed-agents/migration
…nguage="cURL"> This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it. </CodeGroupItem>…
multiagent-orchestration
Claude Developer Platform · in the page
managed-agents/multiagent-orchestration
…ally from one agent to another, freeing up the main session thread to communicate with the user and check in on one or several running workflows to report on progress. The agent can’t send follow-up m…
overview
Claude Developer Platform · in the page
managed-agents/overview
…you get a fully managed environment where Claude can read files, run commands, browse the web, and run code securely. The harness supports built-in prompt caching, compaction, and other performance o…
permission-policies
Claude Developer Platform · in the page
managed-agents/permission-policies
…ll agent toolset by default but requires confirmation before any bash command runs: <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -fsSL https://api.anthropic.com/v1/agents \ -H "x-api-k…
quickstart
Claude Developer Platform · in the page
managed-agents/quickstart
…title="Choose how to authenticate"> Signing in with the CLI is recommended for local development. Follow the steps for one of the following options. </Step> </Steps> **CLI** <Steps conti…
scheduled-deployments
Claude Developer Platform · in the page
managed-agents/scheduled-deployments
…_context.type: "manual"`. This allows you to test a deployment before committing to the schedule. <CodeGroup> ```bash cURL curl --fail-with-body -sS -X POST "https://api.anthropic.com/v1/deployme…
secure-deployment
Claude Developer Platform · in the page
managed-agents/secure-deployment
…ecision | Recommended…
secure-deployment-risks
Claude Developer Platform · in the page
managed-agents/secure-deployment-risks
…| | An open network lets data out | A bash command posts a file to an outside host | [Limit…
spawn.sh: called once per claimed work item
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes
…boxEnv { args = append(args, "-e", name) } launcher := exec.CommandContext(ctx, "docker", append(args, "your-sdk-worker-image")...) launcher.Env = append(os.Environ(), "ANTHROPIC_WORK…
self-hosted-sandboxes-custom-tools
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-custom-tools
…put_schema` | Accepts the JSON Schema keywords MCP servers commonly emit, such as `additionalProperties` and `title`. Rejects reference keywords such as `$ref` anywhere, and top-level `oneO…
self-hosted-sandboxes-memory
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-memory
…OFOLLOW` when it opens memory files. A case-sensitive filesystem is recommended, so that memory paths that differ only in case do not collide. macOS volumes are case-insensitive by default, so such pa…
self-hosted-sandboxes-operations
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-operations
…d queue depth, stop sessions and workers without losing work, and fix common self-hosted sandbox failures. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs…
self-hosted-sandboxes-reference
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-reference
…de.com/docs/en/managed-agents/self-hosted-sandboxes-workers). ## CLI commands and flags | Command | Description…
self-hosted-sandboxes-security
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-security
…et`). Other processes in the sandbox can still change the local copy: commands the agent runs through the `bash` tool, and [custom tools](https://platform.claude.com/docs/en/managed-agents/self-hosted…
self-hosted-sandboxes-workers
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-workers
…ching a sandbox for each session needs more logic than a single shell command. From the shell, run `ant beta:worker poll --on-work` with a spawn script, as in [Run one sandbox per session](https://pla…
session-threads
Claude Developer Platform · in the page
managed-agents/session-threads
…nguage="cURL"> This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it. </CodeGroupItem>…
skills
Claude Developer Platform · in the page
managed-agents/skills
…hen they are relevant to the task. * **Pre-built Anthropic skills:** Common document tasks such as PowerPoint, Excel, Word, and PDF handling (`pptx`, `xlsx`, `docx`, `pdf`). * **Custom skills:** Skil…
tools
Claude Developer Platform · in the page
managed-agents/tools
…---------------------------- | | Bash | `bash` | Run bash commands in a shell session | | Read | `read` | Read a file from the sandbox filesystem…
tools-web-restrictions
Claude Developer Platform · in the page
managed-agents/tools-web-restrictions
…llowedDomains`; csharp, go: `AllowedDomains`) lists have no domain in common, the tool stays available to that agent, but every call fails. Each call returns a `url_not_allowed` error whose text inclu…
vaults
Claude Developer Platform · in the page
managed-agents/vaults
…s you can’t enumerate in advance. Limiting domains is strongly recommended for security purposes, and prevents your key from ever being shared with unauthorized hosts. <Note> `allowed_…