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
146 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
5,575 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
2 Oct 2026
91 pages
+2800 −1383 lines
claude-code
sub-agents
±changed
+15−11
claude-codechanged
sub-agents
<span id="inline-server-trust" />Claude Code loads an inline server from an agent file in your project's `.claude/agents/` directory, or in an `--add-dir` directory's `.claude/agen
The MCP restrictions that apply to the main session also cover servers declared in subagent frontmatter:
* [`--strict-mcp-config`](/docs/en/cli-reference) and [`--bare`](/docs/en/cli-reference)
* [Enterprise managed MCP configuration](/docs/en/managed-mcp)
+15 −11 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
sessions
±changed
+12−3
claude-codechanged
sessions
You can run `claude --resume <session-id>` from any directory, so you can resume a session that started elsewhere or moved with [`/cd`](/docs/en/commands). Claude Code looks for th
1. The current project directory and its git worktrees
2. Every other project on this machine
+12 −3 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
managed-settings
±changed
+12−5
claude-codechanged
managed-settings
4. The HKCU registry, on Windows, and on WSL once the HKLM registry or the Windows managed settings file turns [`wslInheritsWindowsSettings`](/docs/en/settings-reference#wslinherit
<span id="present-admin-documents" />
Claude Code never applies the user-writable HKCU registry beneath an admin document that is present. A document is present when it sets any policy key to a value other than `null`,
+12 −5 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
desktop
±changed
+8−6
claude-codechanged
desktop
<span id="auto-mode-availability" />
Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-config#work-with-fable). Orga
In Enterprise deployments that route Desktop to Google Cloud's Agent Platform, auto mode is also available by default; see [Auto mode on Bedrock, Agent Platform, or Foundry](/docs/
+8 −6 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
claude-directory
±changed
+5−3
claude-codechanged
claude-directory
<span id="state-files-to-keep" />
Other files appear depending on which features you use. Caches and lock files are safe to delete. Keep these state files:
<h4 id="state-files-to-keep">
State files to keep
+5 −3 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
mcp
±changed
+2−0
claude-codechanged
mcp
After you resume a session, Claude can call a tool from the saved conversation while the tool's MCP server is still connecting. While the server is on its first connection attempt,
+2 −0 lines
Upstream edited 2 Oct 2026 13:29 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
vs-code
±changed
+22−2
claude-codechanged
vs-code
* **Model**: select **Switch model…** from the command menu to change the model mid-session. You can also click the model name at the bottom of the prompt box to open the same pick
* **Model**: select **Switch model…** from the command menu to change the model mid-session. You can also click the model name at the bottom of the prompt box to open the same pick
| `showMessageTimestamps` | `false` | Show when each message was sent. A date line marks where the day changes. Requires Claude Code v2.1.284 or later |
| `environmentVariables` | `[]` | Set environment variables for the Claude process. Use Claude Code settings instead for shared config. |
| `environmentVariables` | `[]` | Set environment variables for the Claude process. Use Claude Code settings instead for shared config. A [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) e
+22 −2 lines
Upstream edited 2 Oct 2026 13:26 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
interactive-mode
±changed
+3−3
claude-codechanged
interactive-mode
Run `/recap` to generate a summary on demand. Claude Code caps both automatic recaps and `/recap` output at 400 characters. To turn automatic recaps off, open `/config` and turn of
Session recap is on by default for every plan and provider. The recap is always skipped in non-interactive mode.
Run `/recap` to generate a summary on demand. It runs only when you ask for it yourself. When it arrives in a message relayed from a Slack, Teams, or project thread, or in a prompt
+3 −3 lines
Upstream edited 2 Oct 2026 13:24 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
settings-reference
±changed
+2−1
claude-codechanged
settings-reference
* Windows variables that pick the programs and machine-wide configuration for the processes Claude Code starts, such as `SystemRoot`, `ComSpec`, `ProgramData`, `LOCALAPPDATA`, `P
* `"customEndpoint"`: the Anthropic API or a cloud provider's API sent to another host, such as an [LLM gateway](/docs/en/llm-gateway) named by `ANTHROPIC_BASE_URL`, a provider's
* `"customEndpoint"`: the Anthropic API or a cloud provider's API sent to another host, such as an [LLM gateway](/docs/en/llm-gateway) named by `ANTHROPIC_BASE_URL` or by a provi
+2 −1 lines
Upstream edited 2 Oct 2026 13:24 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
microsoft-foundry
±changed
+2−0
claude-codechanged
microsoft-foundry
Set `ANTHROPIC_FOUNDRY_RESOURCE` to the resource name alone, such as `my-resource`. Claude Code [refuses a URL or host name](/docs/en/errors#anthropic-foundry-resource-must-be-a-fo
+2 −0 lines
Upstream edited 2 Oct 2026 13:24 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
memory
±changed
+10−1
claude-codechanged
memory
To toggle it, open `/memory` in a session and use the auto memory toggle, which saves `autoMemoryEnabled` to your user settings at `~/.claude/settings.json`. To turn it off for a s
To toggle it, open `/memory` in a session and use the auto memory toggle, which saves `autoMemoryEnabled` to your user settings at `~/.claude/settings.json`.
The toggle turns auto memory off but doesn't turn it back on in these sessions:
+10 −1 lines
Upstream edited 2 Oct 2026 13:24 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
sandboxing
±changed
+3−3
claude-codechanged
sandboxing
When you define the same filesystem array in multiple [settings scopes](/docs/en/settings#settings-precedence), Claude Code merges them, combining paths from every scope rather tha
When you define the same filesystem array in multiple [settings scopes](/docs/en/settings#settings-precedence), Claude Code merges them, combining the paths rather than replacing o
The example below blocks reading from the entire home directory while still allowing reads from the current project. Place it in your project's `.claude/settings.json`, because the
The example below blocks reading from the entire home directory while still allowing reads from the current project. Place it in your project's `.claude/settings.json`, because the
Which files can set a port depends on your other sandbox settings:
+3 −3 lines
Upstream edited 2 Oct 2026 13:17 UTC Recorded here 2 Oct 2026 13:37 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 2 Oct 2026 13:07 UTC
claude-code
permissions
±changed
+10−0
claude-codechanged
permissions
A permission prompt shows what Claude is about to do, followed by your options. This example is the prompt for a Bash command, from a session in Manual mode:
<Frame>
<img src="https://mintcdn.com/claude-code/oa7CKjMeIChox26S/images/permission-prompt-bash-light.png?fit=max&auto=format&n=oa7CKjMeIChox26S&q=85&s=87585d008a29304873466399f7b476f6"
+10 −0 lines
Upstream edited 2 Oct 2026 12:54 UTC Recorded here 2 Oct 2026 13:07 UTC
claude-code
permission-modes
±changed
+9−1
claude-codechanged
permission-modes
**During a session**: press `Shift+Tab` to cycle permission modes. From `auto`, the first press switches to `default`, and the cycle then runs `default` → `acceptEdits` → `plan
**During a session**: press `Shift+Tab` to cycle permission modes. From `auto`, the first press switches to `default`, and the cycle then runs `default` → `acceptEdits` → `plan
Watch the status bar in this clip of a session that started in auto mode. Each time you press `Shift+Tab`, it changes from `auto mode on` to `manual mode on`, `accept edits on`
+9 −1 lines
Upstream edited 2 Oct 2026 12:54 UTC Recorded here 2 Oct 2026 13:07 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 2 Oct 2026 07:37 UTC
claude-code
setup
±changed
+5−5
claude-codechanged
setup
```bash theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null}
+5 −5 lines
Upstream edited 2 Oct 2026 07:14 UTC Recorded here 2 Oct 2026 07:37 UTC
claude-code
claude-tag
±changed
+9−10
claude-codechanged
claude-tag
No line of the body moved in this read.
+9 −10 lines
Recorded here 2 Oct 2026 06:37 UTC
claude-code
errors
±changed
+41−16
claude-codechanged
errors
| `Cannot add MCP server: your organization's managed settings allow only MCP servers that plugins provide` | [Command-line errors](#cannot-add-mcp-server-when-managed-settings-all
* A server error or overloaded response that arrives after Claude has finished thinking but before it has started any text or tool call. Claude Code retries a server error at that
In an interactive session signed in with a claude.ai subscription, Claude Code can also wait in the open session and continue the interrupted task shortly after the reset. While it
In an interactive session signed in with a claude.ai subscription, Claude Code can also wait in the open session and continue the interrupted task shortly after the reset. See [Wai
If the machine also holds an Anthropic-issued credential and the managed settings set `forceLoginMethod` or `forceLoginOrgUUID`, Claude Code exits at startup instead. That credenti
+41 −16 lines
Upstream edited 2 Oct 2026 06:22 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
sub-agents
±changed
+6−8
claude-codechanged
sub-agents
* **Model**: inherits from the main conversation, capped at Opus on the Claude API, so Explore never runs on a more expensive model than the one you already chose for the sessi
* **Model**: the main conversation's model. When the main conversation runs Fable, Explore's model depends on how you connect:
* With a Claude subscription, an Anthropic Console account, or an [LLM gateway](/docs/en/llm-gateway) reached through `ANTHROPIC_BASE_URL`, Explore runs on the Opus model tha
* On Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), or a [Claude apps gateway](/docs/en/claude-a
As of v2.1.198, Explore inherits the main conversation's model instead of always running on Haiku. On the Claude API, the inherited model is capped at Opus: a main conversation
+6 −8 lines
Upstream edited 2 Oct 2026 06:22 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
feature-availability
±changed
+1−1
claude-codechanged
feature-availability
* **Subagents**: the built-in [Explore subagent](/docs/en/sub-agents#built-in-subagents) caps its inherited model at Opus on the Claude API, and inherits the main conversation's mo
* **Subagents**: when the main conversation runs Fable, the built-in [Explore subagent](/docs/en/sub-agents#built-in-subagents) runs on Opus with a Claude subscription, an Anthropi
+1 −1 lines
Upstream edited 2 Oct 2026 06:22 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
vs-code
±changed
+13−5
claude-codechanged
vs-code
* A plugin that failed to load shows a short reason on its row. Click the reason for what you can do about it, including copying the full error message to look up in [Troubleshoo
| `marketplace` | Where the plugin comes from: a GitHub `owner/repo`, an `https://` URL, or a git SSH URL such as `[email protected]:owner/repo.git`. Defaults to `anthropics/claude-pl
Some values that the [Marketplaces tab](#manage-marketplaces) accepts don't work in a link, such as a local path or an `http://` address. For those, VS Code shows an error message
+13 −5 lines
Upstream edited 2 Oct 2026 06:21 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
remote-control
±changed
+2−2
claude-codechanged
remote-control
* **Some commands are local-only**: commands that only run in the terminal interface, such as `/plugin` or `/resume`, work only from the local CLI, whether or not you pass an argum
* **Some commands are local-only**: commands that only run in the terminal interface, such as `/plugin` or `/resume`, work only from the local CLI, whether or not you pass an argum
* `/mcp`: from the mobile app, returns a text summary of server status instead of opening the picker. On the web, `/mcp` on its own opens a directory of [claude.ai connectors](/d
* `/mcp`: from the mobile app, returns a text summary of server status instead of opening the picker. On the web, `/mcp` on its own opens a directory of [claude.ai connectors](/d
+2 −2 lines
Upstream edited 2 Oct 2026 06:20 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
mcp
±changed
+4−0
claude-codechanged
mcp
#### Retry failed servers yourself
To retry every server that failed or needs authentication, run `/mcp reconnect all`. In the interactive terminal this requires Claude Code v2.1.284 or later, and earlier versions p
+4 −0 lines
Upstream edited 2 Oct 2026 06:20 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
managed-mcp
±changed
+57−31
claude-codechanged
managed-mcp
Servers your organization delivers through `managedMcpServers` load without an allowlist entry, and [How a server is evaluated](#how-a-server-is-evaluated) covers `managed-mcp.json
Servers your organization delivers through `managedMcpServers` load without an allowlist entry, and [Servers that skip the allowlist check](#servers-that-skip-the-allowlist-check)
| `serverName` | The user-assigned label. Exact match only; wildcards are not expanded | Either type, but see the Warning below |
| `serverName` | The user-assigned label. Exact match only; wildcards are not expanded | Either type, but see [How `serverName` entries match](#how-servername-entries-match) |
| `allowedMcpServers` | All servers allowed | No servers allowed, apart from [those that skip the allowlist check](#how-a-server-is-evaluated) | Only matching servers allowed, apar
+57 −31 lines
Upstream edited 2 Oct 2026 06:16 UTC Recorded here 4 Oct 2026 05:37 UTC
claude-code
managed-mcp
±changed
+1−0
claude-codechanged
managed-mcp
| [`strictPluginOnlyCustomization`](/docs/en/settings-reference#strictpluginonlycustomization) is `true` or includes `mcp`, and the user runs `claude mcp add` | [`Cannot add MCP se
+1 −0 lines
Upstream edited 2 Oct 2026 06:16 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
ultrareview
±changed
+1−1
claude-codechanged
ultrareview
If the subcommand exits before the findings arrive, they never reach your terminal, and running it again starts a new review rather than resuming that one. The new review [counts a
If the subcommand exits before the findings arrive, they never reach your terminal. The review may still be running in the cloud. Running the subcommand again starts a new review r
+1 −1 lines
Upstream edited 2 Oct 2026 06:08 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
llm-gateway-protocol
±changed
+18−3
claude-codechanged
llm-gateway-protocol
| [Context management](https://platform.claude.com/docs/en/build-with-claude/context-editing) | Context management beta header pairs with the `context_management` body field | `400
| [Context management](https://platform.claude.com/docs/en/build-with-claude/context-editing) | Context management beta header pairs with the `context_management` body field | `400
| [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) and [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) | The `o
| [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) and [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) | The `o
* When the upstream rejects `output_config.effort`, Claude Code retries the request without effort and leaves it out of later requests to that model until Claude Code exits. Claude
+18 −3 lines
Upstream edited 2 Oct 2026 06:08 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
interactive-mode
±changed
+9−6
claude-codechanged
interactive-mode
While Claude Code waits, a line at the bottom of the session shows when it will continue:
While Claude Code waits, the lines at the bottom of the session show when your limit resets and when Claude will continue:
Usage limit reached · continuing automatically at 3:45pm · esc to cancel
Usage limit reached · limit resets 3:45pm
Continuing automatically at 3:45pm · esc to cancel
+9 −6 lines
Upstream edited 2 Oct 2026 06:08 UTC Recorded here 2 Oct 2026 06:37 UTC
claude-code
code-review
±changed
+1−1
claude-codechanged
code-review
* You 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 [la
* You 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 [do
+1 −1 lines
Upstream edited 2 Oct 2026 06:08 UTC Recorded here 2 Oct 2026 06:37 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 2 Oct 2026 06:07 UTC
claude-code
plugins/troubleshooting
±changed
+19−10
claude-codechanged
plugins/troubleshooting
* For a source that differs from its settings declaration, re-add the marketplace from the declared source or change the declaration. `claude plugin marketplace add` refuses the sa
* For a source that differs from its settings declaration, re-add the marketplace from the declared source or change the declaration. `claude plugin marketplace add` refuses the sa
<h3 id="cannot-add-marketplace-its-network-source-differs">
`Cannot add marketplace "<name>": its network source differs from the one declared for it in settings`
</h3>
+19 −10 lines
Upstream edited 2 Oct 2026 06:05 UTC Recorded here 2 Oct 2026 06:07 UTC
claude-code
plugins/marketplace-reference
±changed
+2−2
claude-codechanged
plugins/marketplace-reference
| `git-subdir` | `url`, `path`, `ref`, `sha` | One subdirectory of a git repository, fetched with a sparse partial clone |
| `git-subdir` | `url`, `path`, `ref`, `sha` | One subdirectory of a git repository, fetched with a sparse checkout |
`url` accepts a full git URL or GitHub `owner/repo` shorthand. `path` is the subdirectory that holds the plugin, and Claude Code downloads only that subdirectory.
`url` accepts a full git URL or GitHub `owner/repo` shorthand. `path` is the subdirectory that holds the plugin, and Claude Code checks out only that subdirectory. Over an `https`
+2 −2 lines
Upstream edited 2 Oct 2026 06:05 UTC Recorded here 2 Oct 2026 06:07 UTC
claude-code
errors
±changed
+15−3
claude-codechanged
errors
| `Failed to authenticate: OAuth token revoked` | [Authentication](#oauth-token-revoked-or-expired) |
| `Your account does not have access to Claude. Please login again or contact your administrator.` | [Authentication](#oauth-token-revoked-or-expired) |
**What to do:**
* Run `/login` to sign in again
+15 −3 lines
Upstream edited 2 Oct 2026 06:04 UTC Recorded here 2 Oct 2026 06:07 UTC
claude-code
worktrees
±changed
+3−1
claude-codechanged
worktrees
For a `"fresh"` base, Claude Code keeps `origin/HEAD` current: when the repository hasn't been fetched in the last 24 hours, it fetches the default branch, capped at five seconds,
For a `"fresh"` base, Claude Code keeps `origin/HEAD` current: when the repository hasn't been fetched in the last 24 hours, it fetches the default branch, capped at five seconds,
This fetch never waits for input in your terminal. If git or ssh would ask for a password, a key passphrase, or confirmation of a new SSH host, the fetch fails instead and Claude C
+3 −1 lines
Upstream edited 2 Oct 2026 06:03 UTC Recorded here 2 Oct 2026 06:07 UTC
claude-code
ultrareview
±changed
+3−3
claude-codechanged
ultrareview
Without arguments, ultrareview reviews the diff between your current branch and the default branch, including uncommitted and staged changes. For uncommitted changes to files named
For a branch review, Claude Code bundles the repository state and uploads it to a cloud sandbox; when you [review a pull request](#review-a-pull-request), Claude Code uploads nothi
Without arguments, ultrareview reviews the diff between your current branch and the default branch, including uncommitted and staged changes.
+3 −3 lines
Upstream edited 2 Oct 2026 06:03 UTC Recorded here 2 Oct 2026 06:07 UTC
claude-code
claude-code-on-the-web
±changed
+21−3
claude-codechanged
claude-code-on-the-web
When you run `claude --cloud` from a repository that has no git remote, or from a github.com repository that the Claude GitHub App isn't installed on, Claude Code bundles your loca
On macOS, Linux, and WSL, Claude Code leaves uncommitted changes to files named like credentials or keys out of the upload and names the files it left out. This covers `.env` files
When you run `claude --cloud` from a repository that has no git remote, or from a github.com repository that the Claude GitHub App isn't installed on, Claude Code bundles your loca
+21 −3 lines
Upstream edited 2 Oct 2026 06:03 UTC Recorded here 2 Oct 2026 06:07 UTC
claude-code
permission-modes
±changed
+2−2
claude-codechanged
permission-modes
* **A direct connection to the Anthropic API**: in an interactive terminal session, on every claude.ai plan and on accounts that use the Claude API, as Anthropic rolls it out. Requ
* **A direct connection to the Anthropic API**: in interactive terminal sessions and in `-p`, Agent SDK, [VS Code extension](/docs/en/vs-code), and [desktop app](/docs/en/desktop)
To skip asking the server and always use Claude Code's own classifier requests, set [`CLAUDE_CODE_AUTO_MODE_SERVER=0`](/docs/en/env-vars). On a direct connection to the Anthropic A
To skip asking the server and always use Claude Code's own classifier requests, set [`CLAUDE_CODE_AUTO_MODE_SERVER=0`](/docs/en/env-vars). On a direct connection to the Anthropic A
+2 −2 lines
Upstream edited 2 Oct 2026 06:01 UTC Recorded here 2 Oct 2026 06:07 UTC
claude-code
self-hosted-environments-identity
±changed
+3−3
claude-codechanged
self-hosted-environments-identity
This command extracts the creator identity, preferring the SSO provider's subject, then the email address, then the creator's `act.sub` subject, `user:<id>` or `agent:<id>`:
This command extracts the creator identity, preferring the email address, then the creator's `act.sub` subject, `user:<id>` or `agent:<id>`:
"$CLAUDE_RUNNER_CLAUDE_BIN" self-hosted-runner decode-token | jq -re '.act.attested_by.sub // .act.email // .act.sub'
"$CLAUDE_RUNNER_CLAUDE_BIN" self-hosted-runner decode-token | jq -re '.act.email // .act.sub'
| `act.attested_by` | The upstream identity provider's attestation for the creating user, when available. `act.attested_by.sub` is the subject your SSO provider, such as Google or
+3 −3 lines
Upstream edited 2 Oct 2026 05:28 UTC Recorded here 2 Oct 2026 05:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+2−2
claude-codechanged
self-hosted-environments-configuration
| `CLAUDE_CODE_SESSION_ACCESS_TOKEN` | The session JWT, prefixed `sk-ant-cc-`. Its `act` claim identifies the session creator, with the creator's email and upstream identity-provid
| `CLAUDE_CODE_SESSION_ACCESS_TOKEN` | The session JWT, prefixed `sk-ant-cc-`. Its `act` claim identifies the session creator, with the creator's email when the creating surface re
Use `jq -re` rather than `jq -r` when the extracted claim gates an auth decision, so an absent claim exits non-zero instead of passing the literal string `null` downstream. Session
Use `jq -re` rather than `jq -r` when the extracted claim gates an auth decision, so an absent claim exits non-zero instead of passing the literal string `null` downstream. Session
+2 −2 lines
Upstream edited 2 Oct 2026 05:28 UTC Recorded here 2 Oct 2026 05:37 UTC
claude-code
plugins/mods/reference
±changed
+1−1
claude-codechanged
plugins/mods/reference
| `$.ui.invalidate('ui.render')` redraws | Throttled to 10 a second, 30 for the visible pane and the band. Calls that come sooner are coalesced. |
| `$.ui.invalidate('ui.render')` redraws | Throttled to 10 a second, or 30 in the terminal for the visible pane, the expanded band, and the hint line under the prompt. Calls that c
+1 −1 lines
Upstream edited 2 Oct 2026 05:25 UTC Recorded here 2 Oct 2026 05:37 UTC
claude-code
plugins/mods/interface
±changed
+1−1
claude-codechanged
plugins/mods/interface
Claude Code throttles redraws of a site, so your mod can call `$.ui.invalidate` as often as its data changes. The visible pane and the band have a higher limit than other sites, an
Claude Code throttles redraws of a site, so your mod can call `$.ui.invalidate` as often as its data changes. For how often each site can redraw, see the [limits table](/docs/en/pl
+1 −1 lines
Upstream edited 2 Oct 2026 05:25 UTC Recorded here 2 Oct 2026 05:37 UTC
claude-code
monitoring-usage
±changed
+21−4
claude-codechanged
monitoring-usage
| `input_tokens` | Input token count from the API usage block | |
| `input_tokens` | Input token count from the API usage block. Excludes tokens read from or written to the prompt cache, which are reported in `cache_read_tokens` and `cache_creati
* `type`: (`"input"`, `"output"`, `"cacheRead"`, `"cacheCreation"`)
* `type`: (`"input"`, `"output"`, `"cacheRead"`, `"cacheCreation"`). The `"input"` type excludes tokens read from or written to the prompt cache, which are counted under `"cacheRea
* `input_tokens`: Number of input tokens
+21 −4 lines
Upstream edited 2 Oct 2026 05:05 UTC Recorded here 2 Oct 2026 05:07 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 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/troubleshoot
±changed
+6−6
claude-codechanged
plugins/mods/troubleshoot
When a mod does nothing, two checks find the reason: what Claude Code reads from the mod's files, and the line it writes when it skips something. For the first, in your shell run [
When a mod does nothing, check what Claude Code reads from the mod's files, and the line it writes when it skips something. For the first, in your shell run [`claude plugin validat
| `hooks modules are turned off here` | A setting is keeping your mods out: `disableAllHooks` in your own settings, or your organization's policy |
| `hooks modules are turned off here` | A setting is blocking your mods: `disableAllHooks` in your own settings, or your organization's policy |
The line starts with the mod's name, then `hooks module did not load: options do not fit plugin.json userConfig:` and a reason. An option doesn't fit its [`userConfig`](/docs/en/pl
+6 −6 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/test
±changed
+21−19
claude-codechanged
plugins/mods/test
> Write automated tests for a Claude Code mod that raise events, stub Claude Code's answers, and press buttons, with no session, sign-in, or network.
You can write automated tests for a mod and run them from your shell with [`claude plugin test`](/docs/en/plugins/mods/reference#commands). A test raises the events your hooks hand
> Write automated tests for a Claude Code mod that fire events, stub Claude Code's answers, and press buttons, with no session, sign-in, or network.
+21 −19 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/reference
±changed
+24−24
claude-codechanged
plugins/mods/reference
> Complete reference for Claude Code mods: hooks module layout, every event, every mods API method, render sites, elements by surface, limits, and settings.
Look up any event a [mod](/docs/en/plugins/mods/overview) can hook, mods API method it can call, or render site it can draw in, for the Claude Code CLI and the Desktop app as of v2
> Complete reference for Claude Code mods: hooks module layout, events, mods API methods, render sites, elements by surface, limits, and settings.
+24 −24 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/overview
±changed
+8−8
claude-codechanged
plugins/mods/overview
You can start with a mod in one of three ways:
To start with a mod:
Before you install a mod, you can list which events it hooks and what it asks Claude Code to do, such as read a file or make a network request, without running it. Get the plugin's
Before you install a mod, you can list which events it handles and what it asks Claude Code to do, such as read a file or make a network request, without running it. Get the plugin
* **Every installed mod, for one session**: start Claude Code with [`--safe-mode`](/docs/en/cli-reference#cli-flags), which also leaves out your other customizations
+8 −8 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/interface
±changed
+33−33
claude-codechanged
plugins/mods/interface
A mod can draw its own interface in Claude Code and change parts of the interface Claude Code already draws. Each place a mod can draw is called a [render site](/docs/en/plugins/mo
A mod can draw its own interface in Claude Code and change parts of the interface Claude Code already draws. Each place a mod can draw is called a [render site](/docs/en/plugins/mo
Claude Code has no built-in tabs element, so the tabs are two buttons in a row. The mod keeps track of which one is active and draws that tab's content under the row.
The tabs are two buttons in a row. The mod keeps track of which one is active and draws that tab's content under the row.
The code does three jobs, one in each hook:
+33 −33 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/events
±changed
+14−12
claude-codechanged
plugins/mods/events
To change what Claude Code acts on, such as the text of a prompt, call `next` with a modified copy of the event. The event itself is immutable: it's frozen at every depth, and assi
To change what Claude Code acts on, such as the text of a prompt, call `next` with a modified copy of the event. The event itself is immutable: it's deeply frozen, and assigning to
The event name can be a wildcard. `'classic.*'` matches every [settings hook event](#hook-the-settings-hook-events). `'*'` matches every event except the [telemetry events](/docs/e
The event name can be a wildcard. `'classic.*'` matches every [settings hook event](#hook-the-settings-hook-events). `'*'` matches every event except the [telemetry events](/docs/e
Hook these events to see or change a tool call, a prompt, or a turn as it happens. For every event and what a hook can return, see the [events reference](/docs/en/plugins/mods/refe
+14 −12 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/create
±changed
+11−11
claude-codechanged
plugins/mods/create
A mod is a Claude Code [plugin](/docs/en/plugins/overview) with an entry file, called the hooks module: a JavaScript or TypeScript file whose functions Claude Code calls when event
A mod is a Claude Code [plugin](/docs/en/plugins/overview) with an entry file, called the hooks module: a JavaScript or TypeScript file whose functions Claude Code calls when event
* **Mods are stopped**: you started with `--safe-mode` or `--bare`, you set `disableAllHooks`, or your organization's [managed settings block it](/docs/en/plugins/mods/admin#choose
* **Mods are disabled**: you started with `--safe-mode` or `--bare`, you set `disableAllHooks`, or your organization's [managed settings block it](/docs/en/plugins/mods/admin#choos
The hooks in `first-mod` handle their events in the three ways a hook can:
+11 −11 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/api
±changed
+10−10
claude-codechanged
plugins/mods/api
A Claude API failure doesn't reject the call, so check `r.isAnswered`, and read `r.reason` when it's `false`. The call rejects only for a request Claude Code won't send, such as a
A Claude API failure doesn't reject the call, so check `r.isAnswered`, and read `r.reason` when it's `false`. The call rejects for a request Claude Code won't send, such as a model
Work that outlives one event, such as checking on something once a minute, runs on a timer you start from `session.start`. A hook itself runs for one event and has a time limit of
Work that outlives one event, such as checking on something once a minute, runs on a timer you start from `session.start`. A hook itself runs for one event and has a [time limit](/
| `$.ui.toast(text)` | A small box at the top right, with the mod's name above the text, that disappears after a few seconds |
+10 −10 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/mods/admin
±changed
+14−14
claude-codechanged
plugins/mods/admin
* **Deny rules and your managed hooks take precedence.** Where the guard loads, a user's mod can't approve a call that a `deny` rule refuses, whichever settings file holds the rule
* **Deny rules and your managed hooks take precedence.** Where the guard loads, a user's mod can't approve a call that a `deny` rule refuses, whichever settings file holds the rule
[Manage plugins for your organization](/docs/en/plugins/org) lists every way a plugin loads and the setting that controls each.
[Manage plugins for your organization](/docs/en/plugins/org) lists the ways a plugin loads and the setting that controls each.
* **`disableSideloadFlags`**: rejects `--plugin-dir` and `--plugin-url` at startup, so nobody loads a mod from a directory, and keeps mods Claude writes during a session from loadi
+14 −14 lines
Upstream edited 2 Oct 2026 04:34 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
permissions
±changed
+1−1
claude-codechanged
permissions
That precedence covers hooks in settings files and in a plugin's `hooks/hooks.json`. A [mod](/docs/en/plugins/mods/overview) you install that hooks `tool.check` answers after the r
That precedence covers hooks in settings files and in a plugin's `hooks/hooks.json`. A [mod](/docs/en/plugins/mods/overview) you install that handles `tool.check` answers after the
+1 −1 lines
Upstream edited 2 Oct 2026 04:30 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
A [mod](/docs/en/plugins/mods/overview) you install that hooks `tool.check` can approve an action before step 3, and the classifier doesn't check an action the mod approves. Se
A [mod](/docs/en/plugins/mods/overview) you install that handles `tool.check` can approve an action before step 3, and the classifier doesn't check an action the mod approves.
+1 −1 lines
Upstream edited 2 Oct 2026 04:30 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
A [mod](/docs/en/plugins/mods/overview) you install that hooks `tool.check` can approve a call that your `PreToolUse` hook blocked, unless the hook is in managed settings. [Extend
A [mod](/docs/en/plugins/mods/overview) you install that handles `tool.check` can approve a call that your `PreToolUse` hook blocked, unless the hook is in managed settings. [Exten
+1 −1 lines
Upstream edited 2 Oct 2026 04:30 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
troubleshoot-install
±changed
+9−0
claude-codechanged
troubleshoot-install
| `Bus error` or `oh no: Bun has crashed` while a session is running | [Keep the executable readable](#bus-error-while-a-session-is-running) |
### `Bus error` while a session is running
If a running session exits and your shell prints `Bus error`, one cause is that Claude Code could no longer read its own executable file from disk. For example, the file was trunca
+9 −0 lines
Upstream edited 2 Oct 2026 04:14 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
setup
±changed
+19−6
claude-codechanged
setup
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
+19 −6 lines
Upstream edited 2 Oct 2026 04:14 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
cross-session-messaging
±changed
+6−1
claude-codechanged
cross-session-messaging
* 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
You can message a session shown as `offline` in [the listing](#see-which-sessions-claude-can-reach), one whose Remote Control connection has dropped. The send goes through, but the
A session's row in [the listing](#see-which-sessions-claude-can-reach) can show a condition that changes what happens when Claude messages that session:
* **`offline`**: that session's Remote Control connection has dropped. The message goes through, but arrives only after that session's machine reconnects.
+6 −1 lines
Upstream edited 2 Oct 2026 04:13 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/code-intelligence
±changed
+11−11
claude-codechanged
plugins/code-intelligence
> Code intelligence plugins work in terminal sessions. In [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code doesn't start plugin language servers, so Claude gets no di
> Code intelligence plugins work in terminal sessions. In [cloud sessions](/docs/en/claude-code-on-the-web.md), Claude Code doesn't start plugin language servers, so Claude gets no
To get started, find your language in the table under [Install a code intelligence plugin](#install-a-code-intelligence-plugin). The plugins in that table come from Anthropic's [of
To get started, find your language in the table under [Install a code intelligence plugin](#install-a-code-intelligence-plugin). The plugins in that table come from Anthropic's [of
In the VS Code extension or the desktop app, follow [Install a plugin](/docs/en/plugins/install#install-a-plugin) instead of this step. In a terminal, start Claude Code by running
+11 −11 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
plugins/code-intelligence
±changed
+37−39
claude-codechanged
plugins/code-intelligence
<Note>
Code intelligence plugins work in terminal sessions. In [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code doesn't start plugin language servers, so Claude gets no di
</Note>
> [!NOTE]
>
+37 −39 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
sub-agents
±changed
+2−0
claude-codechanged
sub-agents
If you're the plugin's author, ship the hooks in the plugin's [`hooks/hooks.json`](/docs/en/plugins/components#hooks) and the MCP servers in its [`.mcp.json`](/docs/en/plugins/co
+2 −0 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
The [`skill-creator` plugin](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/skill-creator) automates the comparison loop inside Claude Code. Install it fro
The [`skill-creator` plugin](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/skill-creator) automates the comparison loop inside Claude Code. In the VS Code
+1 −1 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/overview
±changed
+2−1
claude-codechanged
plugins/overview
Start on claude.com instead if either of these describes you:
These cases are covered on other pages:
* **You want Claude Code inside VS Code or a JetBrains IDE**: that's the VS Code extension or the JetBrains plugin, not a Claude Code plugin. See [Use Claude Code in VS Code](/do
+2 −1 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/install
±changed
+7−3
claude-codechanged
plugins/install
### Update one plugin now
In a session, open the plugin on the **Installed** tab in `/plugin` and select **Update now**, or in your shell run `claude plugin update <plugin>@<marketplace>`.
### Update plugins now
+7 −3 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugins/code-intelligence
±changed
+1−1
claude-codechanged
plugins/code-intelligence
To install the plugin listed for your language in the step 1 table, run `/plugin install` in a Claude Code session, replacing `typescript-lsp` with that plugin's name:
In the VS Code extension or the desktop app, follow [Install a plugin](/docs/en/plugins/install#install-a-plugin) instead of this step. In a terminal, start Claude Code by runn
+1 −1 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
plugin-evals
±changed
+2−2
claude-codechanged
plugin-evals
* The same authentication and model provider your normal Claude Code sessions use. Eval runs, judge-scored graders, and `claude plugin eval init` call the model with your credentia
* The same authentication and model provider your normal Claude Code sessions use. Eval runs, judge-scored graders, and `claude plugin eval init` call the model with your credentia
* **Install and credentials**: a CI runner needs a Claude Code install and [credentials in the environment](/docs/en/authentication) such as `ANTHROPIC_API_KEY`.
* **Install and credentials**: a CI runner needs a Claude Code install and [credentials in the environment](/docs/en/authentication) such as `ANTHROPIC_API_KEY` or your cloud provi
+2 −2 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
In a Claude Code session, run:
In the VS Code extension or the desktop app, follow [Install a plugin](/docs/en/plugins/install#install-a-plugin) instead of this step. In a terminal, start Claude Code by runn
+1 −1 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
large-codebases
±changed
+1−1
claude-codechanged
large-codebases
The official marketplace has plugins for TypeScript, Python, Go, Rust, and other common languages. Run the command below inside a Claude Code session to install the TypeScript plug
The official marketplace has plugins for TypeScript, Python, Go, Rust, and other common languages. In the VS Code extension or the desktop app, install one by following [Install a
+1 −1 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
claude-security
±changed
+1−1
claude-codechanged
claude-security
In a Claude Code session, install from the [official Anthropic marketplace](/docs/en/plugins/anthropic-marketplaces):
In 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 `cla
+1 −1 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 UTC
claude-code
channels
±changed
+4−4
claude-codechanged
channels
In Claude Code, run:
Start Claude Code by running `claude` in your terminal, then enter this at its prompt:
In Claude Code, run:
Start Claude Code by running `claude` in your terminal, then enter this at its prompt:
In Claude Code, run:
+4 −4 lines
Upstream edited 2 Oct 2026 04:12 UTC Recorded here 2 Oct 2026 04:37 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 2 Oct 2026 04:07 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
The setting applies only to Remote Control. Regular Claude chat, Claude Code in the terminal, and API usage are unaffected.
The setting applies to Remote Control in both Claude Code and [Cowork](https://claude.com/docs/cowork/overview). This page covers the Claude Code side. Regular Claude chat, Claude
+1 −1 lines
Upstream edited 2 Oct 2026 03:57 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+7−3
claude-codechanged
self-hosted-environments-deploy
On a runner on v2.1.280 or later, commits you make from a `checkout` or `post-session` lifecycle hook are signed as the session too, without the `Co-authored-by:` trailer. [Git con
If the stop timeout runs out before the runner finishes, the host kills the runner. The sessions it still holds get no `post-session` hook. The runner doesn't deregister, and the c
If the stop timeout runs out before the runner finishes, the host kills the runner. The sessions it still holds get no `post-session` hook. The runner doesn't deregister, and the c
* **Resumed sessions lose unpushed work**: when a session is released or its runner is restarted, and the user sends another message, the session resumes on a fresh runner that clo
+7 −3 lines
Upstream edited 2 Oct 2026 03:56 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
self-hosted-environments-configuration
±changed
+30−6
claude-codechanged
self-hosted-environments-configuration
Runs once per repository, in place of the runner's built-in clone and fetch. Use the hook to clone from a read-through mirror, seed a working tree from an archive, or apply per-ses
Runs once per repository, in place of the runner's built-in clone and fetch. Use the hook to clone from a read-through mirror, seed a working tree from an archive, or apply per-ses
| `GIT_CONFIG_COUNT`, `GIT_CONFIG_KEY_n`, `GIT_CONFIG_VALUE_n` | Git settings the runner fixes for the git your hook runs. [Git configuration inside lifecycle hooks](#git-configura
| `GIT_CONFIG_COUNT`, `GIT_CONFIG_KEY_n`, `GIT_CONFIG_VALUE_n` | Git settings the runner fixes for the git your hook runs. [Git configuration inside lifecycle hooks](#git-configura
# Pin config the session could have planted in the checkout's .git/config:
+30 −6 lines
Upstream edited 2 Oct 2026 03:56 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
self-hosted-environments
±changed
+2−2
claude-codechanged
self-hosted-environments
4. If the runner stops polling for about 60 seconds, the server requeues the session for another runner.
4. If the runner stops polling, its lease lapses after about 60 seconds, and the server requeues the session for another runner within a few minutes.
* The runner releases a session that's mid-turn as soon as that turn finishes.
* The runner releases a session that's mid-turn after that turn finishes. It first waits for the session's process to report the turn's end to Anthropic, for no longer than [`SE
+2 −2 lines
Upstream edited 2 Oct 2026 03:56 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
Admins can also configure the organization default to override user selection. With override on, it takes precedence over the `model` value in user, project, and local settings, so
Admins can also configure the organization default to override user selection. With override on, it takes precedence over the `model` value in user, project, and local settings, so
+1 −1 lines
Upstream edited 2 Oct 2026 03:54 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
admin-setup
±changed
+1−1
claude-codechanged
admin-setup
* [Organization default model](/docs/en/model-config#organization-default-model): set which model new sessions start on. Users can change it unless your organization enforces the d
* [Organization default model](/docs/en/model-config#organization-default-model): set which model new sessions start on. Members can still switch models. To return them to your def
+1 −1 lines
Upstream edited 2 Oct 2026 03:54 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
network-config
±changed
+4−0
claude-codechanged
network-config
Claude Desktop and claude.ai also render some tool results inside a conversation as interactive widgets, such as the [MCP Apps](https://claude.com/docs/connectors/building/mcp-apps
#### Third-party hosts for artifact fonts and libraries
+4 −0 lines
Upstream edited 2 Oct 2026 03:54 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
plugins/mods/overview
±changed
+15−1
claude-codechanged
plugins/mods/overview
* **Install one**: see [Install or update a mod](#install-or-update-a-mod)
* **Install one**: see [Install or update a mod](#install-or-update-a-mod), or [try a sample mod](#try-a-sample-mod)
### Try a sample mod
+15 −1 lines
Upstream edited 2 Oct 2026 03:48 UTC Recorded here 2 Oct 2026 04:07 UTC
claude-code
plugins/mods/interface
±changed
+13−1
claude-codechanged
plugins/mods/interface
The permission prompt isn't a render site, so a mod can't change what it shows. The question dialog, `AskUserQuestion`, is one, so a mod can change that.
At these sites, `next(e)` returns a reference to Claude Code's drawing, `{ type: 'engine', ref }`, unless a mod that runs after yours returned a tree of its own. To change what's i
```javascript theme={null}
on('ui.render', { component: 'Spinner' }, async ($, e, next) => {
+13 −1 lines
Upstream edited 2 Oct 2026 03:43 UTC Recorded here 2 Oct 2026 04:07 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 2 Oct 2026 03:37 UTC
claude-code
prompt-library
±changed
+277−54
claude-codechanged
prompt-library
if (!href || href[0] !== '/' || href[1] === '/') return href;
if (!href) return undefined;
if (href[0] === '#' || href.startsWith('https://')) return href;
if (!(/^\/[A-Za-z0-9]/).test(href)) return undefined;
const widthFor = s => (s || '').length + 3 + 'ch';
+277 −54 lines
Upstream edited 2 Oct 2026 03:23 UTC Recorded here 2 Oct 2026 03:37 UTC
claude-code
plugins/manifest-reference
±changed
+22−1
claude-codechanged
plugins/manifest-reference
Claude Code merges whatever you declare with `hooks/hooks.json` when that file exists.
A hooks file wraps the event map in a top-level `"hooks"` key, the shape [`hooks/hooks.json`](/docs/en/plugins/components#hooks) uses. A file that contains only the event map, with
Claude Code merges whatever you declare with `hooks/hooks.json` when that file exists. This array loads one hooks file and declares one inline `PostToolUse` hook:
}
+22 −1 lines
Upstream edited 2 Oct 2026 03:05 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
security
±changed
+1−1
claude-codechanged
security
* **Branch restrictions**: Git push operations are restricted to the current working branch
* **Push restrictions**: The [GitHub proxy](/docs/en/cloud-environments#github-proxy) rejects branch deletions and pushes of anything other than a branch, such as a tag. GitHub dec
+1 −1 lines
Upstream edited 2 Oct 2026 02:41 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
routines
±changed
+1−5
claude-codechanged
routines
Claude pushes its work to branches prefixed with `claude/`, which are always accepted. When your prompt directs Claude to push to another branch, Claude Code checks the push first
* The branch is protected on GitHub
* Someone else has an open pull request from that branch
* The branch carries commits authored by someone other than you
+1 −5 lines
Upstream edited 2 Oct 2026 02:41 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
* **Push protection**: `git push` works only against the session's current working branch; cloning, fetching, and PR operations work normally.
* **Push restrictions**: the proxy rejects branch deletions and pushes of anything other than a branch, such as a tag. It doesn't limit which branches a push can update. To do that
+1 −1 lines
Upstream edited 2 Oct 2026 02:41 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
tools-reference
±changed
+2−0
claude-codechanged
tools-reference
When the URL is a claude.ai [artifact](/docs/en/artifacts) link, Claude Code can also ask for approval to read the artifact itself. For the cases where it asks, see [Read an artifa
+2 −0 lines
Upstream edited 2 Oct 2026 02:41 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
permission-modes
±changed
+2−1
claude-codechanged
permission-modes
* When Claude reads an [artifact someone else made](/docs/en/artifacts#read-an-artifact-shared-with-you), the approval cases listed in that section apply
The [actions no mode auto-approves](#actions-no-mode-auto-approves) still prompt in this mode. The [Remove-Item in PowerShell](#remove-item-in-powershell) denies also apply in this
The [actions no mode auto-approves](#actions-no-mode-auto-approves) still prompt in this mode. Reading [another organization's public artifact](/docs/en/artifacts#read-an-artifact-
+2 −1 lines
Upstream edited 2 Oct 2026 02:41 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
artifacts
±changed
+9−0
claude-codechanged
artifacts
Claude Code asks for your approval before Claude reads the artifact in these cases, in addition to any prompt your permission mode or rules call for:
* **Cloud session without network access**: for a [cloud environment](/docs/en/cloud-environments#access-levels), that's the **None** level. In [auto mode](/docs/en/permission-mode
* **Another organization's public artifact**: Claude Code asks you first, even in auto mode. Where Claude Code can't ask you, such as in `bypassPermissions` mode, Claude can't read
+9 −0 lines
Upstream edited 2 Oct 2026 02:41 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
model-config
±changed
+13−1
claude-codechanged
model-config
#### Effort level after a fallback
When Claude Code switches your session to the fallback model, it keeps the effort level the flagged request ran at in place of that model's default effort. For example, a session o
A different level applies in cases such as these:
+13 −1 lines
Upstream edited 2 Oct 2026 02:40 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
vs-code
±changed
+17−3
claude-codechanged
vs-code
If the conversation is open in another Claude Code process, such as `claude` in a terminal or another VS Code window, a notice appears in place of the prompt box: `This conversatio
### Continue conversations after a reload
If another Claude Code process still has the conversation open, you're asked before it opens here, with the same **Open here anyway** notice as when you [resume it from session his
+17 −3 lines
Upstream edited 2 Oct 2026 02:39 UTC Recorded here 2 Oct 2026 03:07 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* `The response stream was malformed`: an event arrived for a content block that had already finished, or an event arrived damaged. A damaged event is one whose data isn't valid JS
* `The response stream was malformed`: an event arrived for a content block that had already finished, or an event arrived damaged. A damaged event is one whose data isn't valid JS
+1 −1 lines
Upstream edited 2 Oct 2026 02:39 UTC Recorded here 2 Oct 2026 03:07 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 2 Oct 2026 02:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
The classifier runs on Claude Sonnet 5 by default rather than on your `/model` selection. A classifier model that Anthropic configures server-side takes precedence over that de
The classifier runs on Claude Sonnet 5 by default rather than on your `/model` selection. A classifier model that Anthropic configures server-side takes precedence over that de
+1 −1 lines
Upstream edited 2 Oct 2026 02:36 UTC Recorded here 2 Oct 2026 02:37 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: the classifier's Claude Sonnet 5 default applies only when the allowlist permits Sonnet 5.
* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: the classifier's Claude Sonnet 5 default applies only when the allowlist permits Sonnet 5.
+1 −1 lines
Upstream edited 2 Oct 2026 02:36 UTC Recorded here 2 Oct 2026 02:37 UTC
claude-code
desktop-linux
±changed
+32−36
claude-codechanged
desktop-linux
<Note>
Linux support for the Claude desktop app is in beta.
</Note>
> [!NOTE]
>
+32 −36 lines
Upstream edited 2 Oct 2026 02:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
desktop-linux
±changed
+1−1
claude-codechanged
desktop-linux
Installing the `.deb` also registers Anthropic's apt repository at `/etc/apt/sources.list.d/claude-desktop.list`, so future updates arrive with your system's [regular package updat
The `.deb` contains Anthropic's signing key and installs it at `/usr/share/keyrings/claude-desktop-archive-keyring.asc`, so you don't need to download the key yourself. Unless you
+1 −1 lines
Upstream edited 2 Oct 2026 02:35 UTC Recorded here 2 Oct 2026 02:37 UTC
claude-code
settings-reference
±changed
+10−6
claude-codechanged
settings-reference
| [`sandbox.enableWeakerNetworkIsolation`](#sandbox-enableweakernetworkisolation) | Let `gh`, `gcloud`, and `terraform` verify TLS behind a MITM proxy inside the [sandbox](/docs/en
| [`sandbox.enableWeakerNetworkIsolation`](#sandbox-enableweakernetworkisolation) | Let `gh`, `gcloud`, and `terraform` verify TLS behind a MITM proxy inside the [sandbox](/docs/en
Linux and WSL2 only. See [Bubblewrap fails to start inside a container](/docs/en/sandboxing#troubleshooting).
Linux and WSL2 only. See [Bubblewrap fails to start inside a container](/docs/en/sandboxing#bubblewrap-fails-to-start-inside-a-container).
If you don't use a MITM proxy, list the failing tools in [`excludedCommands`](#sandbox-excludedcommands) instead; see [Go-based CLIs fail TLS verification on macOS](/docs/en/sandbo
+10 −6 lines
Upstream edited 2 Oct 2026 02:27 UTC Recorded here 2 Oct 2026 02:37 UTC
claude-code
sandboxing
±changed
+107−162
claude-codechanged
sandboxing
If sandboxed commands fail with `Operation not permitted` inside a container, see the Bubblewrap entry under [Troubleshooting](#troubleshooting).
If sandboxed commands fail with `Operation not permitted` inside a container, see [Bubblewrap fails to start inside a container](#bubblewrap-fails-to-start-inside-a-container).
* A bare `Bash` ask rule, or the equivalent `Bash(*)` form, is skipped for commands that run sandboxed; it still applies to commands that fall back to the regular permission flow.
* A bare `Bash` ask rule, or the equivalent `Bash(*)` form, is skipped for commands that run sandboxed; it still applies to commands that fall back to the regular permission flow.
In plan mode, auto-allow doesn't widen approvals; see [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) for how Claude Code gates commands while you p
+107 −162 lines
Upstream edited 2 Oct 2026 02:27 UTC Recorded here 2 Oct 2026 02:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.