HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
812pages tracked
765 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
5,591 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
1 Oct 2026
90 pages
+5398 −858 lines
claude-code
third-party-integrations
±changed
+2−0
claude-codechanged
third-party-integrations
To limit which of these deployment options a managed machine may use, set [`allowedProviders`](/docs/en/settings-reference#allowedproviders) in managed settings. For example, `["be
+2 −0 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
settings-reference
±changed
+44−1
claude-codechanged
settings-reference
| [`allowedProviders`](#allowedproviders) | Limit which [API providers](/docs/en/third-party-integrations) a machine may use | Authentication and providers | Managed |
### `allowedProviders`
List the services a machine may reach Claude through, such as the Anthropic API, Amazon Bedrock, or an LLM gateway. A session on a provider that isn't listed is refused at startup,
+44 −1 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
server-managed-settings
±changed
+2−1
claude-codechanged
server-managed-settings
Three kinds of keys are exceptions to the no-merge rule:
These keys are exceptions to the no-merge rule:
* **`allowedProviders`**: a list set on the machine and a server-managed list combine as [its entry's Scope note](/docs/en/settings-reference#allowedproviders) states. Requires Cla
+2 −1 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
monitoring-usage
±changed
+2−1
claude-codechanged
monitoring-usage
* `"policy_invalid"`: the managed settings contain an error that stops Claude Code from starting, or an admin source failed to load, so Claude Code can't check organization login
* `"policy_invalid"`: the managed settings contain an error that stops Claude Code from starting, or an admin source failed to load for a reason other than a denied read, so Clau
* `"provider_not_allowed"`: the session would use an API provider, or send a provider's traffic to a host, that the managed [`allowedProviders`](/docs/en/settings-reference#allow
+2 −1 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
managed-settings
±changed
+8−2
claude-codechanged
managed-settings
[`allowedProviders`](/docs/en/settings-reference#allowedproviders) has its own rule: its entry's Scope note says how a list set on the machine combines with a server-managed one. R
If a managed settings file, drop-in file, or `managed-settings.d/` directory can't be read and no admin source supplies a policy, sessions signed in with claude.ai or Claude Consol
When a managed settings file, drop-in file, `managed-settings.d/` directory, MDM profile, or HKLM registry value exists but can't be read, and no admin source supplies a policy, wh
+8 −2 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
llm-gateway
±changed
+2−0
claude-codechanged
llm-gateway
To make a gateway reached through `ANTHROPIC_BASE_URL` the only destination a managed machine may use, set [`allowedProviders`](/docs/en/settings-reference#allowedproviders) to `["
+2 −0 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
errors
±changed
+65−12
claude-codechanged
errors
| `Your organization's managed settings allow Claude Code to use: <providers>` | [Configuration warnings](#managed-settings-dont-allow-this-api-provider) |
| `Your organization's managed settings allow Claude Code to use no API provider at all` | [Configuration warnings](#managed-settings-dont-allow-this-api-provider) |
| `Unable to read managed policy settings` | [Configuration warnings](#unable-to-read-managed-policy-settings) |
You ran [`/desktop`](/docs/en/desktop#coming-from-the-cli), or its alias `/app`, and the system command Claude Code uses to open Claude Desktop failed. The session stays in the ter
+65 −12 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
claude-apps-gateway-config
±changed
+2−0
claude-codechanged
claude-apps-gateway-config
To 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
+2 −0 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
authentication
±changed
+18−0
claude-codechanged
authentication
### Restrict which API providers a machine may use
[`allowedProviders`](/docs/en/settings-reference#allowedproviders) in [managed settings](/docs/en/managed-settings) lists which services a managed machine may reach Claude through,
+18 −0 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
agent-sdk/typescript
±changed
+4−2
claude-codechanged
agent-sdk/typescript
| "provider_not_allowed"
| `provider_not_allowed` | Managed settings [list the API providers this machine may use](/docs/en/settings-reference#allowedproviders), and the session is set up for a provider th
Executes Bash commands with optional timeout and background execution. The working directory persists between commands, including commands run in later turns of a multi-turn sessio
Executes Bash commands with optional timeout and background execution. The working directory persists between commands, including commands run in later turns of a multi-turn sessio
When a subagent running in the foreground owns a backgrounded command, the command [ends when that subagent's run ends](/docs/en/tools-reference#background-commands). Claude Code s
+4 −2 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
admin-setup
±changed
+1−0
claude-codechanged
admin-setup
| [Provider restrictions](/docs/en/settings-reference#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at start
+1 −0 lines
Upstream edited 1 Oct 2026 01:04 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
tools-reference
±changed
+13−5
claude-codechanged
tools-reference
For a command that Claude starts in the background, `timeout` instead sets how long the command may run there, with the separate default and maximum described under [Background com
For a command that Claude starts in the background, `timeout` instead sets how long the command may run there, with the separate default and maximum described under [Time limit for
A command that a [foreground subagent](/docs/en/sub-agents#run-subagents-in-foreground-or-background) started stops when that subagent's run ends, whether it finished, failed, or w
#### When a background command stops
+13 −5 lines
Upstream edited 1 Oct 2026 00:55 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
* **Timeout**: each command runs under the Bash tool's default 2-minute [timeout](/docs/en/tools-reference#timeout-and-output-limits). When the Bash tool [moves a timed-out command
* **Timeout**: each command runs under the Bash tool's default 2-minute [timeout](/docs/en/tools-reference#timeout-and-output-limits). When the Bash tool [moves a timed-out command
+1 −1 lines
Upstream edited 1 Oct 2026 00:55 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
interactive-mode
±changed
+3−5
claude-codechanged
interactive-mode
When a command reaches its timeout before it finishes, Claude Code automatically [moves it to the background](/docs/en/tools-reference#background-commands) instead of stopping it,
When a command reaches its timeout before it finishes, Claude Code automatically [moves it to the background](/docs/en/tools-reference#foreground-commands-that-move-to-the-backgrou
* Background Bash and PowerShell commands have a time limit, counted from the moment the command enters the background: 30 minutes, or the `timeout` Claude asks for when it starts
* Set [`BASH_DEFAULT_TIMEOUT_MS`](/docs/en/env-vars) above `1800000` to replace the 30-minute default with that value, for moved commands as well
* Set [`BASH_MAX_TIMEOUT_MS`](/docs/en/env-vars) above `7200000` to raise the 2-hour maximum. Setting `BASH_DEFAULT_TIMEOUT_MS` above `7200000` raises it the same way
+3 −5 lines
Upstream edited 1 Oct 2026 00:55 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
| `updatedInput` | Modifies the tool's input parameters before execution. Replaces the entire input object, so include unchanged fields alongside modified ones. Claude Code evaluat
| `updatedInput` | Modifies the tool's input parameters before execution. Replaces the entire input object, so include unchanged fields alongside modified ones. Claude Code evaluat
+1 −1 lines
Upstream edited 1 Oct 2026 00:55 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
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#background-commands) i
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-th
+1 −1 lines
Upstream edited 1 Oct 2026 00:55 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
For what sets the foreground ceiling, see [Timeout and output limits](/docs/en/tools-reference#timeout-and-output-limits). For the background time limit, see [Background commands](
For what sets the foreground ceiling, see [Timeout and output limits](/docs/en/tools-reference#timeout-and-output-limits). For the background time limit, see [Time limit for backgr
+1 −1 lines
Upstream edited 1 Oct 2026 00:55 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
sessions
±changed
+20−2
claude-codechanged
sessions
<span id="resume-a-running-background-session" />
When the conversation you resume with `claude --resume` or `/resume` belongs to a [background session](/docs/en/agent-view) that is still running, Claude Code opens the running ses
* **From your shell**: `claude --resume <session>` runs [`claude attach`](/docs/en/agent-view#attach-to-a-session) on that session in the same terminal instead of loading the trans
+20 −2 lines
Upstream edited 1 Oct 2026 00:38 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
desktop
±changed
+8−0
claude-codechanged
desktop
From your shell, [`claude --desktop`](/docs/en/cli-reference#cli-flags) opens Desktop directly without starting a terminal session. It requires Claude Code v2.1.285 or later and ha
```bash theme={null}
claude --desktop --resume <session-id>
```
+8 −0 lines
Upstream edited 1 Oct 2026 00:38 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 1 Oct 2026 00:37 UTC
claude-code
vs-code
±changed
+22−4
claude-codechanged
vs-code
* **Installed plugins** appear at the top with toggle switches to enable or disable them
* **Installed plugins** appear at the top with toggle switches to enable or disable them.
* If you turn off a plugin that your project's shared `.claude/settings.json` turns on, the extension asks first: **Disable for me** turns it off only for you, while **Disable fo
Once the install finishes, a form asks for any of the plugin's [configuration options](/docs/en/plugins/components#user-configuration) that aren't set yet. To review or change the
+22 −4 lines
Upstream edited 1 Oct 2026 00:29 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
plugins/troubleshooting
±changed
+38−2
claude-codechanged
plugins/troubleshooting
<h3 id="invalid-git-url">
`Invalid git URL`
</h3>
You added a marketplace, installed a plugin, or ran an update from a git address, and the command failed with `Invalid git URL` in its message.
+38 −2 lines
Upstream edited 1 Oct 2026 00:29 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
plugins/install
±changed
+8−2
claude-codechanged
plugins/install
* **Active, but a server needs setup**: `Plugin is now active.` is followed by `Its bundled MCP server needs configuration before it can start`. The plugin's [bundled MCP s
* **SSH**: the host must already be in your `known_hosts` file and the key must work without a passphrase prompt, because the host-fingerprint and passphrase prompts are suppressed
* **SSH**: the host must already be in your `known_hosts` file and the key must work without a passphrase prompt. If your git setup names an SSH program in `GIT_SSH_COMMAND`, `GIT_
* Press **Enter** to open a plugin's details. The menu there offers **Disable plugin** or **Enable plugin**, **Update now**, and **Uninstall**. Plugins that take settings also offe
* Press **Enter** to open a plugin's details.
+8 −2 lines
Upstream edited 1 Oct 2026 00:29 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
plugins/components
±changed
+13−2
claude-codechanged
plugins/components
A bundle's own manifest can declare settings the server needs from the user in a `user_config` block. A bundled server with a required setting that has no saved value doesn't start
Users supply the values in one of two ways:
* **In `/plugin`**: select the plugin on the **Installed** tab and choose **Configure**
+13 −2 lines
Upstream edited 1 Oct 2026 00:29 UTC Recorded here 1 Oct 2026 01:07 UTC
claude-code
plugins/cli-reference
±changed
+34−2
claude-codechanged
plugins/cli-reference
* **Plugin arguments**: a `<plugin>` argument is a plugin `name` or `name@marketplace`. When two marketplaces offer the same name, use the qualified form.
* **Plugin arguments**: a `<plugin>` argument is a plugin `name` or `name@marketplace`. When two marketplaces offer the same name, use the qualified form. `configure` takes only th
| `--config <key=value>` | Set a [`userConfig`](/docs/en/plugins/manifest-reference) option the plugin's manifest declares. Repeat the flag for each option. Requires Claude Code v2
| `--config <key=value>` | Set a [`userConfig`](/docs/en/plugins/manifest-reference) option the plugin's manifest declares. Repeat the flag for each option. Requires Claude Code v2
| `--data-size [plugin]` | Measure each installed plugin's [saved data directory](#what-an-uninstall-deletes-and-keeps), or only the named plugin's, given as `name@marketplace`. Ha
+34 −2 lines
Upstream edited 1 Oct 2026 00:29 UTC Recorded here 1 Oct 2026 01:07 UTC
30 Sep 2026
63 pages
+3919 −261 lines
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 30 Sep 2026 21:07 UTC
claude-code
claude-apps-gateway-spend-limits
±changed
+1−1
claude-codechanged
claude-apps-gateway-spend-limits
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.
By 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
+1 −1 lines
Upstream edited 30 Sep 2026 20:43 UTC Recorded here 30 Sep 2026 21:07 UTC
claude-code
claude-apps-gateway-on-aws
±changed
+64−1
claude-codechanged
claude-apps-gateway-on-aws
Telemetry shows usage after the fact; [spend limits](/docs/en/claude-apps-gateway-spend-limits) are the gateway's live per-developer view and enforcement on top of the shared upstr
Telemetry shows usage after the fact; [spend limits](/docs/en/claude-apps-gateway-spend-limits) are the gateway's live per-developer view and enforcement.
## Cost attribution
+64 −1 lines
Upstream edited 30 Sep 2026 20:43 UTC Recorded here 30 Sep 2026 21:07 UTC
claude-code
claude-apps-gateway-config
±changed
+85−4
claude-codechanged
claude-apps-gateway-config
On `5xx`, `429`, `401`, `403`, `404`, or timeout the gateway fails over to the next upstream; other `4xx` doesn't, because those errors are attributable to the request rather than
On `5xx`, `429`, `401`, `403`, `404`, or timeout the gateway fails over to the next upstream; other `4xx` doesn't, because those errors are attributable to the request rather than
Also grant the gateway's AWS principal `bedrock:ApplyGuardrail` on the guardrail.
Also grant `bedrock:ApplyGuardrail` on the guardrail to the principal that signs this upstream's requests: the gateway's AWS principal, or with [`assume_role`](#bedrock-in-another-
+85 −4 lines
Upstream edited 30 Sep 2026 20:43 UTC Recorded here 30 Sep 2026 21:07 UTC
claude-code
claude-tag
±changed
+7−7
claude-codechanged
claude-tag
No line of the body moved in this read.
+7 −7 lines
Recorded here 30 Sep 2026 19:37 UTC
claude-code
glossary
±changed
+6−0
claude-codechanged
glossary
### Transcript
The stored record of a [session](#session). The conversation is what you and Claude exchange; the transcript is that conversation kept as a file, by default at `~/.claude/projects/
Learn more: [Where transcripts are stored](/docs/en/sessions#where-transcripts-are-stored)
+6 −0 lines
Upstream edited 30 Sep 2026 19:24 UTC Recorded here 30 Sep 2026 19:37 UTC
claude-code
skills
±changed
+9−1
claude-codechanged
skills
If a skill seems to stop influencing behavior after the first response, the content is usually still present and the model is choosing other tools or approaches. Strengthen the ski
If Claude stops following a skill partway through a session, see [Claude stops following a skill](#claude-stops-following-a-skill).
### Claude stops following a skill
If Claude follows a skill in its first response and stops following it later, start with whichever of these cases matches:
+9 −1 lines
Upstream edited 30 Sep 2026 19:23 UTC Recorded here 30 Sep 2026 19:37 UTC
claude-code
changelog
±changed
+91−0
claude-codechanged
changelog
<Update label="2.1.286" description="September 30, 2026">
* Added a count such as "2 of 5" to the permission prompt when several permission requests stack up
* Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states
* Fixed several Claude Code processes and IDE extensions each opening a login browser when gcpAuthRefresh or awsAuthRefresh credentials expire
+91 −0 lines
Upstream edited 30 Sep 2026 19:19 UTC Recorded here 30 Sep 2026 19:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
Schedules a prompt to run on a 5-field cron schedule in local time. Set `recurring` to `false` to fire once at the next match. Jobs are session-scoped by default: starting a fresh
Schedules a prompt to run on a 5-field cron schedule in local time. Set `recurring` to `false` to fire once at the next match. Jobs are session-scoped by default, and resuming with
+1 −1 lines
Upstream edited 30 Sep 2026 19:18 UTC Recorded here 30 Sep 2026 19:37 UTC
claude-code
scheduled-tasks
±changed
+2−2
claude-codechanged
scheduled-tasks
Tasks are session-scoped: they live in the current conversation and stop when you start a new one. When you resume with `--resume` or `--continue`, Claude Code restores tasks that
Tasks are session-scoped. When you resume with `--resume` or `--continue`, Claude Code restores tasks that haven't [expired](#seven-day-expiry), except those listed under [Limitati
* Starting a fresh conversation clears all session-scoped tasks. When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled w
* When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired](#s
+2 −2 lines
Upstream edited 30 Sep 2026 19:12 UTC Recorded here 30 Sep 2026 19:37 UTC
claude-code
claude-tag
±changed
+6−6
claude-codechanged
claude-tag
No line of the body moved in this read.
+6 −6 lines
Recorded here 30 Sep 2026 18:07 UTC
claude-code
remote-control
±changed
+4−5
claude-codechanged
remote-control
Available flags:
Pass any of these flags after `remote-control`:
| `--sandbox` / `--no-sandbox` | Enable or disable [sandboxing](/docs/en/sandboxing) for filesystem and network isolation. Off by default. |
Give these flags after `remote-control`.
+4 −5 lines
Upstream edited 30 Sep 2026 17:57 UTC Recorded here 30 Sep 2026 18:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 30 Sep 2026 17:37 UTC
claude-code
tools-reference
±changed
+22−4
claude-codechanged
tools-reference
Each command runs under a timeout, and Claude manages it: when it wants longer than the default for a command, it passes the `timeout` parameter with that call — you never set a pe
Each command runs under a timeout, and Claude manages it: when it wants longer than the default for a command, it passes the `timeout` parameter with that call. You never set a per
Two [environment variables](/docs/en/env-vars) control what Claude gets for a command that runs in the foreground:
+22 −4 lines
Upstream edited 30 Sep 2026 17:31 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
interactive-mode
±changed
+4−1
claude-codechanged
interactive-mode
* Background commands owned by a [subagent](/docs/en/sub-agents) have no time limit, except that a command owned by a subagent running in the foreground ends when that subagent giv
* Background Bash and PowerShell commands have a time limit, counted from the moment the command enters the background: 30 minutes, or the `timeout` Claude asks for when it starts
* Set [`BASH_DEFAULT_TIMEOUT_MS`](/docs/en/env-vars) above `1800000` to replace the 30-minute default with that value, for moved commands as well
* Set [`BASH_MAX_TIMEOUT_MS`](/docs/en/env-vars) above `7200000` to raise the 2-hour maximum. Setting `BASH_DEFAULT_TIMEOUT_MS` above `7200000` raises it the same way
* A background command that a foreground [subagent](/docs/en/sub-agents#run-subagents-in-foreground-or-background) started ends when that subagent's run ends, whether it finished,
+4 −1 lines
Upstream edited 30 Sep 2026 17:31 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
cloud-environments
±changed
+15−4
claude-codechanged
cloud-environments
Each session copies the environment's values once, at startup, into ordinary environment variables that any command Claude runs can read, except `OTEL_*` variables. Claude Code use
A 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 [t
In 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
+15 −4 lines
Upstream edited 30 Sep 2026 17:31 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
agent-sdk/typescript
±changed
+3−3
claude-codechanged
agent-sdk/typescript
timeout?: number; // milliseconds, max 600000; higher values are clamped to the max
timeout?: number; // milliseconds. Foreground: capped at 600000 by default, higher values are clamped. With run_in_background (Claude Code v2.1.285 or later): the background time
Executes Bash commands with optional timeout and background execution. The working directory persists between commands, including commands run in later turns of a multi-turn sessio
Executes Bash commands with optional timeout and background execution. The working directory persists between commands, including commands run in later turns of a multi-turn sessio
When a subagent running in the foreground owns a backgrounded command, Claude Code terminates the command when that subagent gives its final response. Claude Code sets `backgroundE
+3 −3 lines
Upstream edited 30 Sep 2026 17:31 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
agent-sdk/python
±changed
+3−1
claude-codechanged
agent-sdk/python
For what sets the foreground ceiling, see [Timeout and output limits](/docs/en/tools-reference#timeout-and-output-limits). For the background time limit, see [Background commands](
"timeout": int | None, # Optional timeout in milliseconds (max 600000; higher values are clamped to the max)
"timeout": int | None, # Milliseconds. Foreground: capped at 600000 by default, higher values are clamped. With run_in_background (Claude Code v2.1.285 or later): the backgrou
+3 −1 lines
Upstream edited 30 Sep 2026 17:31 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
advisor
±changed
+3−2
claude-codechanged
advisor
The advisor must be at least as capable as the main model. The accepted advisors for each main model are:
Both Claude Code and the API require an advisor at least as capable as the main model, and the two rank some models differently. The accepted advisors for each main model are:
| Sonnet 5.5 or Sonnet 5 | Fable, Opus 4.7 or later, Sonnet 5 or later | A Sonnet 4.6 advisor is rejected, and the API refuses an Opus 4.6 advisor |
| Sonnet 5 | Fable, Opus 4.7 or later, Sonnet 5 or later | A Sonnet 4.6 advisor is rejected, and the API refuses an Opus 4.6 advisor |
| Sonnet 5.5 | Fable, Opus 5 or later, Sonnet 5.5 | A Sonnet 4.6 advisor is rejected, and the API refuses a Sonnet 5, Opus 4.6, Opus 4.7, or Opus 4.8 advisor |
+3 −2 lines
Upstream edited 30 Sep 2026 17:31 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
errors
±changed
+53−1
claude-codechanged
errors
| `This server's URL is missing or not a valid URL, so sign-in can't start` | [Authentication](#mcp-server-url-is-missing-or-not-a-valid-url) |
| `MCP server "<name>" was not saved to` / `was not removed from` | [Command-line errors](#mcp-server-was-not-saved-or-removed) |
| `MCP server "<name>" may not have been saved` / `may not have been removed` | [Command-line errors](#mcp-server-may-not-have-been-saved-or-removed) |
### MCP server URL is missing or not a valid URL
+53 −1 lines
Upstream edited 30 Sep 2026 17:30 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
skills
±changed
+19−7
claude-codechanged
skills
Permission syntax: `Skill(name)` for exact match, `Skill(name *)` for prefix match with any arguments. In an `allow` rule, a prefix outside the [namespace reserved for synced skill
If your `deny` rule names an alias or an unqualified name rather than the skill's own name, Claude Code still blocks the skill: with `Skill(review)` it blocks the bundled `/code-re
Claude Code matches an `allow` rule only against the skill's own name and the name in Claude's invocation.
+19 −7 lines
Upstream edited 30 Sep 2026 17:28 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
permissions
±changed
+3−1
claude-codechanged
permissions
* The value is compared against the literal input Claude sends, before any normalization. `Agent(model:opus)` matches the alias `opus` but not a full model ID. Run with [`--verbose
* The value is compared against the literal input Claude sends, before any normalization. `Agent(model:opus)` matches the alias `opus` but not a full model ID
* A `Skill(skill:<name>)` deny rule instead [matches the skill under any of its names](/docs/en/skills#restrict-claude’s-skill-access), such as its alias or display name
* Run with [`--verbose`](/docs/en/cli-reference) to see the exact parameter names and values in each tool call
+3 −1 lines
Upstream edited 30 Sep 2026 17:28 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
mcp
±changed
+10−4
claude-codechanged
mcp
Each `claude mcp add` and `claude mcp add-json` command prints an `Added ...` line. To check that Claude Code connected, run `claude mcp get <name>`; [Server status](#server-status
Each `claude mcp add` and `claude mcp add-json` command prints an `Added ...` line on success. To check that Claude Code connected, run `claude mcp get <name>`; [Server status](#se
`claude mcp add` confirms a successful add by printing an `Added ...` line, which means the configuration was written. `claude mcp list` then shows a health status next to each ser
`claude mcp add` confirms a successful add by printing an `Added ...` line, which means the configuration was written. If the command prints a `was not saved` message instead, see
+10 −4 lines
Upstream edited 30 Sep 2026 17:27 UTC Recorded here 30 Sep 2026 17:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 30 Sep 2026 17:07 UTC
claude-code
permissions
±changed
+1−1
claude-codechanged
permissions
| `auto` | Auto-approves tool calls with background safety checks that verify actions align with your request |
| `auto` | Runs without routine prompts; before actions such as shell commands and network requests run, a background [classifier](/docs/en/permission-modes#eliminate-prompts-with-
+1 −1 lines
Upstream edited 30 Sep 2026 17:02 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
2. While the subagent runs, each of its actions goes through the classifier with the same rules as the parent session, and any `permissionMode` in the subagent's frontmatter is
2. While the subagent runs, each of its actions goes through the same [decision order](#how-the-classifier-evaluates-actions) as in the parent session, with the same block and
+1 −1 lines
Upstream edited 30 Sep 2026 17:02 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
hooks
±changed
+5−1
claude-codechanged
hooks
| `session_title` | The current session title if one is already set, for example via `--name` or `/rename`. A hook that emits `sessionTitle` can check `session_title` first to avoi
| `session_title` | The session's custom title, present when one is set, for example with `--name`, `/rename`, a hook's `sessionTitle` output, or the Agent SDK's `renameSession()`.
A session you haven't named can still have a [generated title](/docs/en/sessions#name-your-sessions). That title isn't a custom title and doesn't appear in `session_title`.
+5 −1 lines
Upstream edited 30 Sep 2026 17:02 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
desktop
±changed
+3−3
claude-codechanged
desktop
| **Auto** | `auto` | Claude executes all actions with background safety checks that verify alignment with your request. Reduces permission prompts while maintaining oversight. App
| **Auto** | `auto` | Claude runs without routine prompts; before actions such as shell commands and network requests run, a background classifier checks that they align with your
Local and cloud sessions also load the skills enabled for your claude.ai account. Cloud sessions load them instead of `~/.claude/skills/`, as [Skills in Cowork and cloud sessions](
Local and cloud sessions also load the skills enabled for your claude.ai account, except local sessions when your organization sets [`disableSideloadFlags`](/docs/en/settings-refer
You can scope plugins to your user account, a specific project, or local-only. If your organization manages plugins centrally, those plugins are available in desktop sessions the s
+3 −3 lines
Upstream edited 30 Sep 2026 17:02 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
agent-sdk/typescript
±changed
+2−2
claude-codechanged
agent-sdk/typescript
| `customTitle` | `string \| undefined` | User-set session title (via `/rename`) |
| `customTitle` | `string \| undefined` | The session's custom title when one is set, for example with `--name`, `/rename`, a hook's `sessionTitle` output, or [`renameSession()`](#
| "auto"; // Model classifier approves or denies permission prompts
| "auto"; // A model classifier reviews actions such as shell commands and network requests
+2 −2 lines
Upstream edited 30 Sep 2026 17:02 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
agent-sdk/permissions
±changed
+1−1
claude-codechanged
agent-sdk/permissions
| `auto` | Model-classified approvals | A model classifier approves or denies permission prompts. See [Auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for av
| `auto` | Model-classified approvals | A model classifier reviews actions such as shell commands and network requests, allowing or blocking each one it reviews. See [Auto mode](/d
+1 −1 lines
Upstream edited 30 Sep 2026 17:02 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
agent-sdk/agent-loop
±changed
+1−1
claude-codechanged
agent-sdk/agent-loop
| `"auto"` | Uses a model classifier to approve or deny permission prompts. See [Auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for availability and behavio
| `"auto"` | Uses a model classifier to review actions such as shell commands and network requests, allowing or blocking each one it reviews. See [Auto mode](/docs/en/permission-mo
+1 −1 lines
Upstream edited 30 Sep 2026 17:02 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
mcp
±changed
+1−0
claude-codechanged
mcp
* Sends [MCP OAuth](#authenticate-with-remote-mcp-servers) credentials only to a token endpoint served over HTTPS or at `localhost`, `127.0.0.1`, or `::1`. Sign-in fails for a serv
+1 −0 lines
Upstream edited 30 Sep 2026 17:00 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
errors
±changed
+18−0
claude-codechanged
errors
| `Refusing to send credentials to non-https token endpoint` / `<short-name> from the MCP SDK for <server-url>` | [Authentication](#refusing-to-send-credentials-to-non-https-token-
### Refusing to send credentials to non-https token endpoint
On the [v2 runtime](/docs/en/mcp#mcp-client-runtimes), Claude Code sends an [MCP OAuth](/docs/en/mcp#authenticate-with-remote-mcp-servers) token request only to a token endpoint se
+18 −0 lines
Upstream edited 30 Sep 2026 17:00 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
settings-reference
±changed
+6−1
claude-codechanged
settings-reference
Reject the `--plugin-dir`, `--plugin-url`, `--agents`, and `--mcp-config` CLI flags at startup, which users could otherwise pass to bypass [`strictKnownMarketplaces`](#strictknownm
Reject the `--plugin-dir`, `--plugin-url`, `--agents`, and `--mcp-config` CLI flags at startup, which users could otherwise pass to bypass [`strictKnownMarketplaces`](#strictknownm
The desktop app manages some plugins itself, including plugins synced from claude.ai and plugins your organization deploys through the app. If you deploy this key to a device throu
+6 −1 lines
Upstream edited 30 Sep 2026 16:58 UTC Recorded here 30 Sep 2026 17:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 30 Sep 2026 08:07 UTC
claude-code
authentication
±changed
+4−2
claude-codechanged
authentication
If you're having trouble logging in, see [authentication troubleshooting](/docs/en/troubleshoot-install#login-and-authentication).
### Log in with multiple accounts
+4 −2 lines
Upstream edited 30 Sep 2026 07:44 UTC Recorded here 30 Sep 2026 08:07 UTC
claude-code
plugins/components
±changed
+2−0
claude-codechanged
plugins/components
If a rule must hold every time, such as [blocking edits to protected files](/docs/en/hooks-guide#block-edits-to-protected-files), add it to the plugin as a [hook](#hooks) rather th
+2 −0 lines
Upstream edited 30 Sep 2026 07:40 UTC Recorded here 30 Sep 2026 08:07 UTC
claude-code
plugins/cli-reference
±changed
+2−0
claude-codechanged
plugins/cli-reference
Run `claude plugin install --help` in your shell to see every option your version supports.
+2 −0 lines
Upstream edited 30 Sep 2026 07:39 UTC Recorded here 30 Sep 2026 08:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 30 Sep 2026 07:37 UTC
claude-code
memory
±changed
+14−12
claude-codechanged
memory
CLAUDE.md files are loaded into the context window at the start of every session, consuming tokens alongside your conversation. The [context window visualization](/docs/en/context-
**Size**: target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence. If your instructions are growing large, use [path-scoped rules](#path-s
**Structure**: use markdown headers and bullets to group related instructions. Claude scans structure the same way readers do: organized sections are easier to follow than dense pa
+14 −12 lines
Upstream edited 30 Sep 2026 07:11 UTC Recorded here 30 Sep 2026 07:37 UTC
claude-code
sandbox-environments
±changed
+2−2
claude-codechanged
sandbox-environments
* Without a valid `~/.srt-settings.json`, the runtime starts anyway, blocks network access, and confines writes to built-in runtime paths such as `/tmp/claude`, `~/.npm/_logs`, and
* When you pass `--settings`, the runtime refuses to start if the file fails to load.
* If `~/.srt-settings.json` doesn't exist and you don't pass `--settings`, the runtime starts anyway. It blocks network access and confines writes to built-in runtime paths such as
* If the settings file exists but is empty, unreadable, or invalid, the runtime refuses to start, whether it's `~/.srt-settings.json` or a file you pass with `--settings`. It also
+2 −2 lines
Upstream edited 30 Sep 2026 07:07 UTC Recorded here 30 Sep 2026 07:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 30 Sep 2026 07:07 UTC
claude-code
skills
±changed
+8−3
claude-codechanged
skills
The check for both is a baseline comparison. Collect a few realistic prompts, run each one in a fresh session with the skill available and again with it [disabled](#override-skill-
Two tools automate that comparison. For a skill that ships in a [plugin](/docs/en/plugins/overview), [`claude plugin eval`](/docs/en/plugin-evals) runs each prompt in an isolated s
The check for both is a baseline comparison. Collect a few realistic prompts, run each one in a fresh session with the skill available and again with it turned off, and compare the
+8 −3 lines
Upstream edited 30 Sep 2026 07:05 UTC Recorded here 30 Sep 2026 07:07 UTC
claude-code
troubleshoot-install
±changed
+1−1
claude-codechanged
troubleshoot-install
If you see `API Error: 403 {"error":{"type":"forbidden","message":"Request not allowed"}}` after logging in:
If you see `API Error: 403 Request not allowed` after logging in:
+1 −1 lines
Upstream edited 30 Sep 2026 07:04 UTC Recorded here 30 Sep 2026 07:07 UTC
claude-code
model-config
±changed
+4−2
claude-codechanged
model-config
* In the `/model` picker, you keep your current model.
* When you select a Fable model with `/model`, you keep your current model.
In [non-interactive mode](/docs/en/headless) with the `-p` flag and through the Agent SDK, Claude Code never shows the consent prompt. When a Fable request there would bill to usag
In a session another application hosts through the [Agent SDK](/docs/en/agent-sdk/overview), whether the prompt appears is up to that application. If it appears and nobody answers
+4 −2 lines
Upstream edited 30 Sep 2026 07:03 UTC Recorded here 30 Sep 2026 07:07 UTC
claude-code
errors
±changed
+7−7
claude-codechanged
errors
If your account requires the [Fable usage-credits consent](/docs/en/model-config#fable-and-usage-credits), Claude Code asks you to confirm before a Fable request bills usage credit
If your account requires the [Fable usage-credits consent](/docs/en/model-config#fable-and-usage-credits), Claude Code asks you to confirm before a Fable request bills usage credit
This happens in [Remote Control](/docs/en/remote-control) sessions, [background sessions](/docs/en/agent-view), and [agent team](/docs/en/agent-teams) teammate sessions. Claude Cod
**What to do:**
+7 −7 lines
Upstream edited 30 Sep 2026 07:03 UTC Recorded here 30 Sep 2026 07:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 30 Sep 2026 06:37 UTC
claude-code
claude-projects
±changed
+25−13
claude-codechanged
claude-projects
> Give Claude a body of related work in one conversation and let it coordinate parallel cloud sessions that share repositories, instructions, and memory.
> Hand Claude a stream of related tasks in one conversation and let it run them as parallel cloud sessions that share repositories, instructions, and memory.
* **From a cloud session that's already doing the work**: choose **Continue as a project** from that session's menu, and Claude proposes the project's setup from what the session w
* **From a cloud session that's already doing the work**: choose **Continue as project** from that session's menu, and Claude proposes the project's setup from what the session was
If you already have a cloud session doing work that belongs in a project, open the session's menu in the sidebar and choose **Continue as a project** or **Move to project**:
+25 −13 lines
Upstream edited 30 Sep 2026 06:35 UTC Recorded here 30 Sep 2026 06:37 UTC
claude-code
errors
±changed
+25−0
claude-codechanged
errors
| `Can't switch to the default model` | [Request errors](#cant-switch-to-the-default-model) |
<h3 id="cant-switch-to-the-default-model">
Can't switch to the default model
</h3>
+25 −0 lines
Upstream edited 30 Sep 2026 06:29 UTC Recorded here 30 Sep 2026 06:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 30 Sep 2026 05:37 UTC
claude-code
plugins/cli-reference
±changed
+8−5
claude-codechanged
plugins/cli-reference
| `--ablation <mode>` | `none` or `with-without`. See [Compare against a no-plugin baseline](/docs/en/plugin-evals#compare-against-a-no-plugin-baseline) | `with-without` when a plu
| `--ablation <mode>` | `none` or `with-without`. See [Score against the no-plugin baseline](/docs/en/plugin-evals#compare-against-a-no-plugin-baseline) | Decided per case, as that
Run the command from the plugin's root folder, the directory that holds `.claude-plugin/plugin.json` or the skill's `SKILL.md`. To scaffold the suite in another directory on purpos
The optional `name` is a case name. It's required with `--bare` or without a terminal, because the command writes the blank template for that case. The interview doesn't need one.
+8 −5 lines
Upstream edited 30 Sep 2026 05:13 UTC Recorded here 30 Sep 2026 05:37 UTC
claude-code
plugin-evals
±changed
+20−14
claude-codechanged
plugin-evals
A high score on its own doesn't tell you the plugin helped, because Claude might do as well without it. To separate the two, each case's runs are repeated with no plugin loaded by
The two sets of runs are called the with-arm and the without-arm; [Score against the no-plugin baseline](#compare-against-a-no-plugin-baseline) covers how graders are scored across
A high score on its own doesn't tell you the plugin helped, because Claude might do as well without it. To separate the two, a case's runs are repeated with no plugin loaded, and y
+20 −14 lines
Upstream edited 30 Sep 2026 05:13 UTC Recorded here 30 Sep 2026 05:37 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
* `"auto"`: Claude Code runs everything, with background safety checks
* `"auto"`: Claude Code runs without routine prompts; before actions such as shell commands and network requests run, a background classifier checks that they align with your req
+1 −1 lines
Upstream edited 30 Sep 2026 05:12 UTC Recorded here 30 Sep 2026 05:37 UTC
claude-code
plugins/troubleshooting
±changed
+4−1
claude-codechanged
plugins/troubleshooting
You ran `/plugin install <plugin>@<name>` in a session, often from an install line someone sent you, and Claude Code reported that it has no marketplace by that name.
You ran `/plugin install` in a session and Claude Code reported that it has no marketplace by that name. Two forms of the command reach this message:
* **`/plugin install <plugin>@<name>`**: the install line, often one someone sent you, names a marketplace you haven't added. The rest of this entry covers finding and adding it.
* **`/plugin install <source>` with a path, URL, or `owner/repo`**: this form reports the message instead of installing, even for a source you've already added. To install from a s
+4 −1 lines
Upstream edited 30 Sep 2026 05:11 UTC Recorded here 30 Sep 2026 05:37 UTC
claude-code
plugins/marketplace-reference
±changed
+3−3
claude-codechanged
plugins/marketplace-reference
`url` must use `https://` and can't point at a loopback, link-local, or cloud-metadata host.
`url` must use `https://` and can't point at a loopback, link-local, or cloud-metadata host. For the size, timeout, redirect, and extraction limits on the download, see [Stay withi
| `git` | `url`, `ref`, `path`, `sparsePaths` | A `user@host:path` URL, or an `https://` URL that ends in `.git`, contains `/_git/`, or names a github.com or gitlab.com repository.
| `git` | `url`, `ref`, `path`, `sparsePaths` | A `user@host:path` URL, or an `http://` or `https://` URL that ends in `.git`, contains `/_git/`, or names a github.com or gitlab.co
| `url` | `url` | Link to the `marketplace.json` file. Claude Code downloads only that file, so the marketplace's plugins can't use [relative-path sources](#relative-path-plugin-so
+3 −3 lines
Upstream edited 30 Sep 2026 05:11 UTC Recorded here 30 Sep 2026 05:37 UTC
claude-code
plugins/host-marketplace
±changed
+18−0
claude-codechanged
plugins/host-marketplace
### Stay within the download limits for hosted files
When users add your marketplace as a `marketplace.json` URL, or install an entry with an [`archive`](/docs/en/plugins/marketplace-reference#archive-plugin-source) source, Claude Co
+18 −0 lines
Upstream edited 30 Sep 2026 05:11 UTC Recorded here 30 Sep 2026 05:37 UTC
claude-code
hooks
±changed
+11−4
claude-codechanged
hooks
| `UserPromptSubmit` | Yes | Blocks prompt processing and erases the prompt |
| `UserPromptSubmit` | Yes | Blocks the prompt, so it never reaches Claude. See [What a blocked prompt leaves behind](#what-a-blocked-prompt-leaves-behind) |
| `decision` | `"block"` prevents the prompt from being processed and erases it from context. Omit to allow the prompt to proceed |
| `decision` | `"block"` stops the prompt before it reaches Claude. Omit to allow the prompt to proceed |
| `suppressOriginalPrompt` | If `true` when `decision` is `"block"`, omits the original prompt text from the block message shown to the user |
+11 −4 lines
Upstream edited 30 Sep 2026 04:59 UTC Recorded here 30 Sep 2026 05:07 UTC
claude-code
plugin-evals
±changed
+2−2
claude-codechanged
plugin-evals
The first time you run `claude plugin eval` against a directory, Claude Code asks `Trust this plugin directory?` before it loads anything from it, unless you already accepted the t
The first time you run `claude plugin eval` against a directory, Claude Code asks `Trust this plugin directory?` before it loads anything from it, unless you already accepted the t
This is the first run against a directory Claude Code doesn't trust yet, and it can't ask you because stdin or stdout isn't a terminal, you passed `--json`, or the `CI` environment
This is the first run against a directory Claude Code doesn't trust yet, and it can't ask you because stdin or stdout isn't a terminal or you passed `--json`. Run `claude plugin ev
+2 −2 lines
Upstream edited 30 Sep 2026 04:55 UTC Recorded here 30 Sep 2026 05:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 30 Sep 2026 04:37 UTC
claude-code
errors
±changed
+19−0
claude-codechanged
errors
| `Not uploading this working tree` with `the upload cannot follow that setting` | [Command-line errors](#the-repository-upload-cant-follow-a-git-setting) |
<h3 id="the-repository-upload-cant-follow-a-git-setting">
The repository upload can't follow a git setting
</h3>
+19 −0 lines
Upstream edited 30 Sep 2026 04:32 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
claude-code-on-the-web
±changed
+1−0
claude-codechanged
claude-code-on-the-web
* 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`
+1 −0 lines
Upstream edited 30 Sep 2026 04:32 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
prompt-caching
±changed
+4−2
claude-codechanged
prompt-caching
| `DISABLE_PROMPT_CACHING_SONNET` | Disable for Sonnet only |
| `DISABLE_PROMPT_CACHING_OPUS` | Disable for Opus only |
| `DISABLE_PROMPT_CACHING_SONNET` | Disable for the default Sonnet model |
| `DISABLE_PROMPT_CACHING_OPUS` | Disable for the default Opus model |
+4 −2 lines
Upstream edited 30 Sep 2026 04:32 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
model-config
±changed
+4−4
claude-codechanged
model-config
| [Server-managed settings](/docs/en/server-managed-settings) from the admin console | Enforced | Enforced | Enforced, except in [Claude Tag](https://claude.com/docs/claude-tag/ove
| [Server-managed settings](/docs/en/server-managed-settings) from the admin console | Enforced | Enforced | Enforced, except in [Claude Tag](https://claude.com/docs/claude-tag/ove
* Cowork, the agentic-work tab in the Claude Desktop app, runs its sessions on Claude Code but, by design, does not receive server-managed settings from the claude.ai admin console
* Cowork, the agentic-work tab in the Claude Desktop app, runs its sessions on Claude Code but, by design, does not receive server-managed settings from the claude.ai admin console
| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models only |
+4 −4 lines
Upstream edited 30 Sep 2026 04:32 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
tools-reference
±changed
+0−4
claude-codechanged
tools-reference
<Note>
The WebSocket source requires Claude Code v2.1.195 or later.
</Note>
+0 −4 lines
Upstream edited 30 Sep 2026 04:31 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
sub-agents
±changed
+0−2
claude-codechanged
sub-agents
A hyphenated matcher like `db-agent` matches exactly on Claude Code v2.1.195 or later. On earlier versions it is evaluated as an unanchored regular expression and also fires for an
+0 −2 lines
Upstream edited 30 Sep 2026 04:31 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
permission-modes
±changed
+2−6
claude-codechanged
permission-modes
Claude Code v2.1.195 and later block more categories by default. Several depend on [environment](/docs/en/auto-mode-config#define-trusted-infrastructure) entries, such as sensitive
Several of these categories depend on [environment](/docs/en/auto-mode-config#define-trusted-infrastructure) entries, such as sensitive remote targets and protected IaC scopes, tha
+2 −6 lines
Upstream edited 30 Sep 2026 04:31 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
mcp
±changed
+3−3
claude-codechanged
mcp
* `http`, `sse`, and `ws` servers: `url`, `headers`, and `headersHelper`. Before v2.1.195, `headersHelper` passed the placeholder through as a literal string
* `http`, `sse`, and `ws` servers: `url`, `headers`, and `headersHelper`
| A [plugin](/docs/en/plugins/components#mcp-servers) | The plugin's root directory. Requires Claude Code v2.1.195 or later |
| A [plugin](/docs/en/plugins/components#mcp-servers) | The plugin's root directory |
When Claude Code can't produce a schema the API accepts, or on a deployment that doesn't receive the remote configuration that enables the rewrite, it skips that one tool, records
+3 −3 lines
Upstream edited 30 Sep 2026 04:31 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
hooks
±changed
+0−4
claude-codechanged
hooks
Hyphens in the exact-match set require Claude Code v2.1.195 or later. On earlier versions a hyphenated name like `code-reviewer` is evaluated as an unanchored regular expression, s
Hyphens in the exact-match set require Claude Code v2.1.195 or later. On earlier versions a bare hyphenated prefix like `mcp__brave-search` is evaluated as an unanchored regular ex
+0 −4 lines
Upstream edited 30 Sep 2026 04:31 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
fullscreen
±changed
+1−1
claude-codechanged
fullscreen
To keep wheel scrolling but turn off click, drag, and hover handling, set `CLAUDE_CODE_DISABLE_MOUSE_CLICKS=1` instead. Requires Claude Code v2.1.195 or later. `CLAUDE_CODE_DISABLE
To keep wheel scrolling but turn off click, drag, and hover handling, set `CLAUDE_CODE_DISABLE_MOUSE_CLICKS=1` instead. `CLAUDE_CODE_DISABLE_MOUSE` takes precedence when both varia
+1 −1 lines
Upstream edited 30 Sep 2026 04:31 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
server-managed-settings
±changed
+1−1
claude-codechanged
server-managed-settings
* **A non-interactive run**, such as `claude -p` or an Agent SDK session: Claude Code can't show the dialog, so when the delivered settings would require approval, it applies them
* **A non-interactive run**, such as `claude -p`, an Agent SDK session, or a session in the VS Code extension's chat panel or the desktop app's Code tab: Claude Code can't show the
+1 −1 lines
Upstream edited 30 Sep 2026 04:30 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
claude-apps-gateway-config
±changed
+3−3
claude-codechanged
claude-apps-gateway-config
A non-interactive run with the `-p` flag 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 intera
If 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, Claud
A [non-interactive run](/docs/en/server-managed-settings#security-approval-dialogs), such as `claude -p` or an Agent SDK session, can't show the dialog. It applies the pushed setti
+3 −3 lines
Upstream edited 30 Sep 2026 04:30 UTC Recorded here 30 Sep 2026 04:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 30 Sep 2026 03:37 UTC
claude-code
skills
±changed
+17−0
claude-codechanged
skills
### Work on Claude API projects
The bundled `/claude-api` skill loads [Claude API](https://platform.claude.com/docs/en/api/overview) and [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overvie
+17 −0 lines
Upstream edited 30 Sep 2026 03:32 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
keybindings
±changed
+5−2
claude-codechanged
keybindings
| `footer:dismiss` | (unbound) | Removed in v2.1.281. A `keybindings.json` that still names the action remains valid, and the binding does nothing. Before v2.1.281, Backspace and D
| `footer:dismiss` | (unbound) | Binding a key to this action has no effect, and a `keybindings.json` that names it remains valid. Before v2.1.281, Backspace and Delete were bound
In list panels such as `/skills` and `/mcp`, Claude Code applies your `select:pageUp`, `select:pageDown`, `select:first`, and `select:last` bindings. In most other lists, such as t
In list panels such as `/skills`, `/mcp`, and `/tasks`, Claude Code applies your `select:pageUp`, `select:pageDown`, `select:first`, and `select:last` bindings. In most other lists
+5 −2 lines
Upstream edited 30 Sep 2026 03:25 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
claude-security
±changed
+14−3
claude-codechanged
claude-security
The plugin runs locally in your session, uses whichever models you have access to in Claude Code, and each scan counts against your plan's usage limits. If you want a managed servi
The 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).
* A paid plan, 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`.
* 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
+14 −3 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.