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
5,572 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
12 Sep 2026
24 pages
+392 −361 lines
claude-code
model-config
±changed
+5−3
claude-codechanged
model-config
* `s`: switch model for this session only
Typing `/model <name>` directly behaves like `Enter`. If you set a model with `/model` in [non-interactive mode](/docs/en/headless), with the `-p` flag, your choice applies to the
* `s`: switch model for this session only and leave your default unchanged. To use a different key, rebind [`modelPicker:thisSessionOnly`](/docs/en/keybindings#model-picker-actions
+5 −3 lines
Recorded here 12 Sep 2026 02:37 UTC
claude-code
env-vars
±changed
+1−0
claude-codechanged
env-vars
| `OTEL_METRICS_INCLUDE_REPOSITORY` | Set to `true` to tag OpenTelemetry metrics and events with `vcs.*` attributes identifying the session's repository (defa
+1 −0 lines
Recorded here 12 Sep 2026 02:37 UTC
claude-code
desktop-quickstart
±changed
+3−3
claude-codechanged
desktop-quickstart
Start with a small project you know well. It's the fastest way to see what Claude Code can do. On Windows, [Git](https://git-scm.com/downloads/win) must be installed for loca
Start with a small project you know well. It's the fastest way to see what Claude Code can do.
A [session](/docs/en/desktop#work-in-parallel-with-sessions) is a conversation with Claude about your code. Each session tracks its own context and changes, so you can work on
A [session](/docs/en/desktop#work-in-parallel-with-sessions) is a conversation with Claude about your code. Each session tracks its own context and changes.
**Scale up when you're ready.** Open [parallel sessions](/docs/en/desktop#work-in-parallel-with-sessions) from the sidebar to work on multiple tasks at once, each in its own Git wo
+3 −3 lines
Recorded here 12 Sep 2026 02:37 UTC
claude-code
desktop
±changed
+7−7
claude-codechanged
desktop
After installing, launch Claude, sign in, and click the **Code** tab. The first time you open it on Windows, you need [Git for Windows](https://git-scm.com/downloads/win) installed
In the Code tab, each conversation is a **session**: it has its own chat history, project folder, and code changes, independent of any other session. The sidebar lists your session
After installing, launch Claude, sign in, and click the **Code** tab. For a walkthrough of your first session, see the [Get started guide](/docs/en/desktop-quickstart).
+7 −7 lines
Recorded here 12 Sep 2026 02:37 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
* [Desktop app](/docs/en/desktop#work-in-parallel-with-sessions): manage multiple local sessions visually, each in its own worktree
* [Desktop app](/docs/en/desktop#work-in-parallel-with-sessions): manage multiple local sessions visually, optionally each in its own worktree
+1 −1 lines
Recorded here 12 Sep 2026 02:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
Output from a local command such as `/voice` or `/usage`. Displayed as assistant-style text in the transcript.
Claude Code doesn't emit this message type. When you send a command such as `/context` or `/usage` as a prompt, its output arrives as an [`SDKAssistantMessage`](#sdkassistantmessag
+1 −1 lines
Recorded here 12 Sep 2026 02:37 UTC
claude-code
admin-setup
±changed
+1−3
claude-codechanged
admin-setup
* Verify by running `/status` inside a WSL session and reading the `Setting sources` line. Claude Code names only the [managed source it selected](/docs/en/server-managed-settings#
* **In a session that [fetches server-managed settings](/docs/en/server-managed-settings#platform-availability) and receives any keys**: `Enterprise managed settings (remote)`, b
* **In any other session**: `Enterprise managed settings (HKLM)` confirms a registry deployment. `(file)` names the Windows file or the distribution's own `/etc/claude-code/manag
* Verify by running `/status` inside a WSL session and reading the `Setting sources` line. To interpret what it lists, see [Read the source in /status](/docs/en/managed-settings#re
+1 −3 lines
Recorded here 12 Sep 2026 02:37 UTC
claude-code
setup
±changed
+5−5
claude-codechanged
setup
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
+5 −5 lines
Recorded here 12 Sep 2026 02:07 UTC
claude-code
fast-mode
±changed
+1−1
claude-codechanged
fast-mode
* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](/docs/en/costs#add-usage-credits-to-your-subsc
* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](/docs/en/costs#add-usage-credits-to-your-subsc
+1 −1 lines
Recorded here 12 Sep 2026 02:07 UTC
claude-code
errors
±changed
+279−248
claude-codechanged
errors
| Message
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| `API Error: 500 Internal server error`
| `API Error: Repeated 529 Overloaded errors`
| `Request timed out`
+279 −248 lines
Recorded here 12 Sep 2026 02:07 UTC
claude-code
costs
±changed
+2−1
claude-codechanged
costs
Developers usually bring limit questions to their admin, so it helps to know which ceiling they hit. The four situations mean different things:
Developers usually bring limit questions to their admin, so it helps to know which ceiling they hit. These situations mean different things:
* **"You've hit your individual spend limit", "org's monthly spend limit", or "team's shared budget"**: the developer's request would be billed to usage credits, and those credits
+2 −1 lines
Recorded here 12 Sep 2026 02:07 UTC
claude-code
claude-apps-gateway-config
±changed
+1−1
claude-codechanged
claude-apps-gateway-config
The gateway validates each document against the CLI's settings schema at boot, so an unrecognized top-level key fails boot with an error naming every offending key. Deliberately op
The gateway validates each document against the CLI's settings schema at boot, so an unrecognized top-level key fails boot with an error naming every offending key. Deliberately op
+1 −1 lines
Recorded here 12 Sep 2026 02:07 UTC
claude-code
settings-reference
±changed
+12−12
claude-codechanged
settings-reference
| Kind of key | How Claude Code combines it
| :----------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------
| Lists | Combines entries from every source
| Locks | Applies the strictest value any source sets. When no source sets a strict value, applies a looser value only from the highest source
| Restriction allowlists | Takes the list whole from the highest source that sets it, without adding entries from lower sources. When the highest source doesn't
+12 −12 lines
Recorded here 12 Sep 2026 01:37 UTC
claude-code
server-managed-settings
±changed
+2−1
claude-codechanged
server-managed-settings
Two kinds of keys are exceptions to the no-merge rule:
Three kinds of keys are exceptions to the no-merge rule:
* **Gateway sign-in keys**: Claude Code never reads [`forceLoginGatewayUrl`](/docs/en/settings-reference#forcelogingatewayurl) or the `"gateway"` value of [`forceLoginMethod`](/doc
+2 −1 lines
Recorded here 12 Sep 2026 01:37 UTC
claude-code
managed-settings
±changed
+3−1
claude-codechanged
managed-settings
* **`"first-wins"`, the default**: Claude Code uses the highest-ranked source that delivers at least one policy key and ignores the rest rather than merging them, apart from the fe
* **`"first-wins"`, the default**: Claude Code uses the highest-ranked source that delivers at least one policy key and ignores the rest rather than merging them, apart from the ke
The [gateway login keys](#choose-a-delivery-mechanism), [`forceLoginGatewayUrl`](/docs/en/settings-reference#forcelogingatewayurl) and the `"gateway"` value of [`forceLoginMethod`]
+3 −1 lines
Recorded here 12 Sep 2026 01:37 UTC
claude-code
authentication
±changed
+1−6
claude-codechanged
authentication
Deploy the keys through your device management tooling. [Server-managed settings](/docs/en/server-managed-settings) reach only accounts that are already authenticated into your org
* **The `env` block**: [merges per key](/docs/en/server-managed-settings#per-key-exceptions-across-managed-sources) in Claude Code v2.1.223 or later
* **The [cross-source lock keys](/docs/en/server-managed-settings#per-key-exceptions-across-managed-sources)**: honored from any admin source
+1 −6 lines
Recorded here 12 Sep 2026 01:37 UTC
11 Sep 2026
41 pages
+1194 −256 lines
claude-code
tools-reference
±changed
+12−4
claude-codechanged
tools-reference
| `Glob` | Finds files based on pattern matching. See [Glob tool behavior](#glob-tool-behavior)
| `Grep` | Searches for patterns in file contents. See [Grep tool behavior](#grep-tool-behavior)
| `Glob` | Finds files based on pattern matching. Absent by default on macOS, Linux, and WSL. See [Glob tool behavior](#glob-tool-behavior)
| `Grep` | Searches for patterns in file contents. Absent by default on macOS, Linux, and WSL. See [Grep tool behavior](#grep-tool-behavior)
The Glob tool finds files by name pattern. It supports standard glob syntax including `**` for recursive directory matching:
+12 −4 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
Subagents inherit the [built-in tools](/docs/en/tools-reference) and MCP tools available in the main conversation, narrowed by two filters: the first removes a short list of tools
Subagents inherit the [built-in tools](/docs/en/tools-reference) and MCP tools available in the main conversation, narrowed by two filters: the first removes a short list of tools
+1 −1 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
setup
±changed
+7−5
claude-codechanged
setup
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
+7 −5 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
plugins-reference
±changed
+25−25
claude-codechanged
plugins-reference
**Arguments:**
The command takes these arguments:
**Options:**
The command accepts these options:
**Aliases:** `new`
+25 −25 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
plugin-evals
±changed
+28−20
claude-codechanged
plugin-evals
You don't have to write the suite by hand; `claude plugin eval init` asks you about your plugin, proposes the cases and graders, tries them, and writes the files, and you can ask C
You don't have to write the suite manually. `claude plugin eval init` asks you about your plugin, proposes the cases and graders, tries them, and writes the files. You can also ask
For each run of a case, Claude Code starts a fresh, [isolated](#how-runs-are-isolated) [non-interactive session](/docs/en/headless) with only your plugin loaded, sends the prompt,
For each run of a case, Claude Code starts a fresh, [isolated](#how-runs-are-isolated) [non-interactive session](/docs/en/headless) with only your plugin loaded, sends the prompt,
One run of a non-deterministic agent tells you little, so each case runs three times by default. A run's score is the fraction of its graders that passed, weighted if you set weigh
+28 −20 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
permissions
±changed
+7−3
claude-codechanged
permissions
* **Deny rules**: apply when either the symlink path or its target matches. A symlink that points to a denied file is itself denied.
For example, with `Read(./project/**)` allowed and `Read(~/.ssh/**)` denied, a symlink at `./project/key` pointing to `~/.ssh/id_rsa` is blocked: the target fails the allow rule an
* **Deny rules**: apply when either the symlink path or its target matches. A symlink that points to a denied file is itself denied. For example, with `Read(./project/**)` allowed
+7 −3 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
hooks-guide
±changed
+6−1
claude-codechanged
hooks-guide
Your hook prints valid JSON, but the decision doesn't take effect and no error appears in the transcript.
Your hook prints valid JSON, but the decision doesn't take effect and no error appears in the transcript. Check which cause applies:
* **Extra output before the JSON**: something else writes to stdout first, usually an unconditional `echo` in your shell profile, so the output no longer starts with `{` and Claude
* **A field at the wrong level**: compare each field's placement against the [JSON output](/docs/en/hooks#json-output) format. For example, `permissionDecision` belongs inside `hoo
+6 −1 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
google-vertex-ai
±changed
+1−1
claude-codechanged
google-vertex-ai
Choose how you authenticate to Google Cloud: Application Default Credentials from `gcloud`, a service account key file, or credentials already in your environment. The wizard d
Choose how you authenticate to Google Cloud: Application Default Credentials from `gcloud`, a service account key file, or credentials already in your environment. The wizard a
+1 −1 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
corporate-launcher
±changed
+1−1
claude-codechanged
corporate-launcher
With a launcher configured, `ps` and Activity Monitor show the versioned binary name for the background helper processes instead of Claude Code's `claude bg-pty-host` and `claude b
With a launcher configured, `ps` and Activity Monitor no longer show Claude Code's `claude bg-pty-host` and `claude bg-spare` labels for the background helper processes, because th
+1 −1 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--tools` | Restrict which built-in tools Claude can use. Use `""` to disable all, `"default"` for all, or tool names like `"Bash,Edit,Read"
| `--tools` | Restrict which built-in tools Claude can use. Use `""` to disable all, `"default"` for the default set, or tool names like `"Bas
+1 −1 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
artifacts
±changed
+2−0
claude-codechanged
artifacts
If you add a `WebFetch` deny or ask rule with no `domain:` part, it doesn't turn artifacts off or block artifact reads. A [`WebFetch(domain:claude.ai)` rule in `deny` or `ask` does
+2 −0 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
advisor
±changed
+8−8
claude-codechanged
advisor
| Main model | Accepted advisors | Notes
| -------------------- | ------------------------------------ | --------------------------------------------------------------------------------------------------------------------
| Haiku 4.5 | Fable, Opus, Sonnet | Haiku can call the advisor but cannot act as one
| Sonnet 4.6 | Fable, Opus, Sonnet |
| Sonnet 5 | Fable, Opus, Sonnet 5 | A Sonnet 4.6 advisor is rejected
+8 −8 lines
Recorded here 11 Sep 2026 22:07 UTC
claude-code
skills
±changed
+4−0
claude-codechanged
skills
Two tools automate that comparison. For a skill that ships in a [plugin](/docs/en/plugins), [`claude plugin eval`](/docs/en/plugin-evals) runs each prompt in an isolated session wi
If the skill ships in a plugin, you can measure how often it triggers across realistic prompts rather than checking one at a time: write an eval case with a [`tool_used: Skill` gra
+4 −0 lines
Recorded here 11 Sep 2026 20:07 UTC
claude-code
plugins-reference
±changed
+67−16
claude-codechanged
plugins-reference
"monitors": "./monitors.json"
"monitors": "./monitors.json",
"evals": "quality/evals"
| Field | Type | Description
| :---------------------- | :-------------------- | :-------------------------------------------------------------------------------------------------------------------------------
+67 −16 lines
Recorded here 11 Sep 2026 20:07 UTC
claude-code
plugins
±changed
+3−0
claude-codechanged
plugins
Trying the plugin with `--plugin-dir` tells you it can work. To find out how often Claude actually reaches for it and gets the right result, run it against a set of test prompts wi
* [Test plugins with evals](/docs/en/plugin-evals): measure what your plugin changes and gate CI on it
+3 −0 lines
Recorded here 11 Sep 2026 20:07 UTC
claude-code
plugin-marketplaces
±changed
+1−1
claude-codechanged
plugin-marketplaces
Test your marketplace before sharing.
Test your marketplace before sharing. Validation checks file structure; to test whether a plugin changes what Claude does on realistic prompts, run its eval suite with [`claude plu
+1 −1 lines
Recorded here 11 Sep 2026 20:07 UTC
claude-code
plugin-evals
+new page
+617−0
claude-codenew page
plugin-evals
No line of the body moved in this read.
+617 −0 lines
Recorded here 11 Sep 2026 20:07 UTC
claude-code
errors
±changed
+22−0
claude-codechanged
errors
| `` `plugin eval` is currently in early access `` / `` `plugin eval` is currently unavailable ``
<h3 id="plugin-eval-is-currently-in-early-access">
plugin eval is currently in early access
</h3>
+22 −0 lines
Recorded here 11 Sep 2026 20:07 UTC
claude-code
changelog
±changed
+101−0
claude-codechanged
changelog
<Update label="2.1.269" description="September 11, 2026">
* Added `claude plugin eval`: run a plugin's eval suite against Claude Code and get scored, reproducible results (JSON + HTML report); see `claude plugin eval --help`
* Added `/output-style [name]` to list and switch output styles, including over Remote Control and in cloud and other headless sessions
* Added a diff of the files a Bash command changed to the Bash tool result when the Bash tool handles file edits (setting `bashEditDiffEnabled`)
+101 −0 lines
Recorded here 11 Sep 2026 20:07 UTC
claude-code
vs-code
±changed
+23−1
claude-codechanged
vs-code
### Share a plugin install link
To send someone straight to installing a specific plugin, give them the extension's `install-plugin` URL. Opening it launches or focuses VS Code, opens the Claude Code panel, and o
+23 −1 lines
Recorded here 11 Sep 2026 17:37 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
* `"dontAsk"`: Claude Code runs only pre-approved tools and auto-denies every call that would otherwise prompt
* `"dontAsk"`: Claude Code auto-denies every call that would otherwise prompt; reads, other actions that need no approval, and pre-approved tools still run
+1 −1 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
permissions
±changed
+8−8
claude-codechanged
permissions
| Mode | Description
| :------------------ | :-----------------------------------------------------------------------------------------------------------------------------------------------------------
| `default` | Prompts for permission on first use of each tool. Labeled Manual in the CLI, the VS Code and JetBrains extensions, and the desktop app, and Claude Code acce
| `acceptEdits` | Automatically accepts file edits and common filesystem commands such as `mkdir`, `touch`, `mv`, and `cp` for paths in the working directory or `additionalDi
| `plan` | Claude reads files and runs read-only shell commands to explore but doesn't edit your source files; with [auto mode](/docs/en/permission-modes#eliminate-pro
+8 −8 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
permission-modes
±changed
+2−2
claude-codechanged
permission-modes
| [`dontAsk`](#allow-only-pre-approved-tools-with-dontask-mode) | Only pre-approved tools |
| [`dontAsk`](#allow-only-pre-approved-tools-with-dontask-mode) | Reads and pre-approved tools; anything that would prompt is denied |
If you set `dontAsk` mode, Claude Code auto-denies every tool call that would otherwise prompt you. Claude runs only actions matching your `permissions.allow` rules, [read-only Bas
If you set `dontAsk` mode, Claude Code auto-denies every tool call that would otherwise prompt you. Claude still runs actions that need no approval in Manual mode, such as file rea
+2 −2 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
monitoring-usage
±changed
+64−56
claude-codechanged
monitoring-usage
| Attribute | Description | Gated by |
| ------------------------- | --------------------------------------------------------- | ----------------------- |
| `user_prompt` | Prompt text. Value is `<REDACTED>` unless the gate is set | `OTEL_LOG_USER_PROMPTS` |
| `user_prompt_length` | Prompt length in characters | |
| `interaction.sequence` | 1-based counter of interactions in this session | |
+64 −56 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
headless
±changed
+1−1
claude-codechanged
headless
* **`dontAsk`**: Claude Code denies anything not in your `permissions.allow` rules or the [read-only command set](/docs/en/permissions#read-only-commands), which is useful for lock
* **`dontAsk`**: Claude Code denies every call that would otherwise prompt, which is useful for locked-down CI runs. Actions that need no approval in Manual mode still run, such as
+1 −1 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
feature-availability
±changed
+1−1
claude-codechanged
feature-availability
* `/design-sync` and `/import` with its `claude import` subcommand form are unavailable on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and Claude Platform o
* `/design-sync` and `/import` with its `claude import` subcommand form are unavailable on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and Claude Platform o
+1 −1 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* You use Claude Code through Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS. Claude Code doesn't fetch feature flags on these provider
* You use Claude Code through Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS, or through a [Claude apps gateway](/docs/en/claude-apps-g
+1 −1 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
commands
±changed
+2−2
claude-codechanged
commands
| `/design-sync [hint]` | **[Skill](/docs/en/skills#bundled-skills).** Convert your repo's Re
| `/design-sync [hint]` | **[Skill](/docs/en/skills#bundled-skills).** Convert your repo's Re
| `/import [codex\|gemini\|cursor] [--dry-run] [--yes]` | Bring configuration from OpenAI Codex, Google Gemini CLI, or Cursor
| `/import [codex\|gemini\|cursor] [--dry-run] [--yes]` | Bring configuration from OpenAI Codex, Google Gemini CLI, or Cursor
+2 −2 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
claude-apps-gateway
±changed
+2−0
claude-codechanged
claude-apps-gateway
| [`/design-sync`](/docs/en/commands#all-commands) and `/design-login` | Not available | Both need claude.ai, whi
| Features that need feature-flag fetching, such as `/import` and `claude import` | Not available | The CLI skips the flag fetch
+2 −0 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
agent-sdk/typescript
±changed
+37−28
claude-codechanged
agent-sdk/typescript
| Method | Description
| :------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------
| `interrupt()` | Interrupts the query. Only available in streaming input mode. When the CLI advertises the `interrupt_receipt_v1` capability in [`SDKSyste
| `rewindFiles(userMessageId, options?)` | Restores files to their state at the specified user message. Pass `{ dryRun: true }` to preview changes. Requires `enableFileCheckpointin
| `setPermissionMode()` | Changes the permission mode (only available in streaming input mode)
+37 −28 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
agent-sdk/permissions
±changed
+18−16
claude-codechanged
agent-sdk/permissions
Check `allow` rules (from `allowed_tools` and settings.json). If a rule matches, the tool is approved. `rm` and `rmdir` removals targeting a [critical path](/docs/en/permission
Check `allow` rules (from `allowed_tools` and settings.json). If a rule matches, the tool is approved. A call the tool approves on its own is resolved at this step too, with no
`allowed_tools` and `disallowed_tools` (TypeScript: `allowedTools` / `disallowedTools`) add entries to the allow and deny rule lists in the evaluation flow above. If you name one o
`allowed_tools` and `disallowed_tools` (TypeScript: `allowedTools` / `disallowedTools`) add entries to the allow and deny rule lists in the evaluation flow above. If you name one o
| `allowed_tools=["Read", "Grep"]` | `Read` and `Grep` are auto-approved. Other tools not listed here still exist and fall through to the permission mode and `canUseTool`.
+18 −16 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
agent-sdk/agent-loop
±changed
+3−3
claude-codechanged
agent-sdk/agent-loop
* **`allowed_tools` / `allowedTools`** auto-approves listed tools. A read-only agent with `["Read", "Glob", "Grep"]` in its allowed tools list runs those tools without prompting. T
* **`allowed_tools` / `allowedTools`** auto-approves listed tools. A read-only agent with `["Read", "Glob", "Grep"]` in its allowed tools list runs those tools without prompting. T
| `"default"` | Tools not covered by allow rules trigger your `canUseTool` callback; no callback means deny
| `"default"` | Tool calls that need approval and aren't covered by allow rules trigger your `canUseTool` callback; no callback means deny
| `"dontAsk"` | Never prompts. Tools pre-approved by [permission rules](/docs/en/settings-reference#permission-settings) run; everything else is denied. `AskUserQuestion`
+3 −3 lines
Recorded here 11 Sep 2026 15:37 UTC
claude-code
web-quickstart
±changed
+24−8
claude-codechanged
web-quickstart
After you sign in, claude.ai/code prompts you to connect GitHub. Follow the prompt, and claude.ai/code sends you to GitHub's authorization page. Approve the authorization reque
When Quick web setup is off, which it is by default on Team and Enterprise plans, claude.ai/code then asks you to install the Claude GitHub App on your repositories unless it's
After you sign in, claude.ai/code prompts you to connect GitHub. Follow the prompt, and claude.ai/code sends you to GitHub's authorization page. Approve the authorization reque
+24 −8 lines
Recorded here 11 Sep 2026 15:07 UTC
claude-code
terminal-config
±changed
+9−9
claude-codechanged
terminal-config
| Token | Controls |
| :-------- | :--------------------------------------------------- |
| `success` | Success messages and passing checks |
| `error` | Error messages and failures |
| `warning` | Warnings, caution messages, and the auto mode border |
+9 −9 lines
Recorded here 11 Sep 2026 15:07 UTC
claude-code
sandbox-environments
±changed
+1−1
claude-codechanged
sandbox-environments
Use this approach when you want full VM isolation without provisioning infrastructure yourself, or when you are delegating tasks from a device that does not have a local developmen
Use this approach when you want full VM isolation without provisioning infrastructure yourself, or when you are delegating tasks from a device that does not have a local developmen
+1 −1 lines
Recorded here 11 Sep 2026 15:07 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
Claude Code also appends system context mid-conversation, such as file-change notices, and marks that block for caching on every provider and connection.
Claude Code also appends system context mid-conversation, such as file-change notices, and marks that block for caching on every provider and connection unless you set [`CLAUDE_COD
+1 −1 lines
Recorded here 11 Sep 2026 15:07 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `CCR_FORCE_BUNDLE` | Set to `1` to force [`claude --cloud`](/docs/en/claude-code-on-the-web#send-local-repositories-without-github) to bundle
| `CCR_FORCE_BUNDLE` | Set to `1` to force [`claude --cloud`](/docs/en/claude-code-on-the-web#send-local-repositories-without-github) to bundle
+1 −1 lines
Recorded here 11 Sep 2026 15:07 UTC
claude-code
claude-code-on-the-web
±changed
+16−16
claude-codechanged
claude-code-on-the-web
| Method | How it works | Best for
| :--------------- | :------------------------------------------------------------------------------------------ | :----------------------------------------------------------------
| **GitHub App** | Authorize the Claude GitHub App during [web onboarding](/docs/en/web-quickstart). | Browser onboarding; teams that want [Auto-fix](#auto-fix-pul
| **`/web-setup`** | Run `/web-setup` in your terminal to sync your local `gh` CLI token to your Claude account. | Individual developers who already use `gh`
+16 −16 lines
Recorded here 11 Sep 2026 15:07 UTC
claude-code
claude-apps-gateway
±changed
+1−1
claude-codechanged
claude-apps-gateway
| Standard prompt caching | Available | The gateway forwards `cache_c
| Standard prompt caching | Available | The gateway forwards `cache_c
+1 −1 lines
Recorded here 11 Sep 2026 15:07 UTC
claude-code
tools-reference
±changed
+0−1
claude-codechanged
tools-reference
* in a [subagent's `tools` or `disallowedTools`](/docs/en/sub-agents#supported-frontmatter-fields) frontmatter
+0 −1 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
sub-agents
±changed
+4−2
claude-codechanged
sub-agents
| `disallowedTools` | No | Tools to deny, removed from inherited or specified list
| `disallowedTools` | No | Tools to deny, removed from inherited or specified list. An entry with a specifier, such as `Bash(git push *)`, still [removes the whole tool](#ava
A `disallowedTools` entry with a specifier, such as `Bash(git push *)`, still removes the whole tool from the subagent, not only the matching commands. To keep Bash and block speci
This is the inverse of [running a skill in a subagent](/docs/en/skills#run-skills-in-a-subagent). With `skills` in a subagent, the subagent controls the system prompt and loads s
+4 −2 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
skills
±changed
+5−1
claude-codechanged
skills
Add `context: fork` to your frontmatter when you want a skill to run in isolation. The skill content becomes the prompt that drives the subagent. It won't have access to your conve
Add `context: fork` to your frontmatter when you want a skill to run in isolation. Claude Code starts a new subagent of the type set in the `agent` field and gives it the skill con
<Note>
Despite the name, a skill with `context: fork` doesn't run in a [fork of the current conversation](/docs/en/sub-agents#fork-the-current-conversation), which would hand the subage
+5 −1 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
settings-reference
±changed
+20−1
claude-codechanged
settings-reference
| [`copyOnSelect`](#copyonselect) | Turn off automatic copying of text you select with the mouse in [fullscree
When the startup run fails, Claude Code prints the reason and refuses to start. After a non-zero exit or a timeout, the message includes the helper's stderr. The refusal covers int
When the startup run fails, Claude Code prints the reason and refuses to start. After a non-zero exit, the reason includes the helper's stderr, or its stdout when stderr is empty.
}
```
+20 −1 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
sandboxing
±changed
+6−0
claude-codechanged
sandboxing
To change the sandbox for one session without writing to a settings file, start Claude Code with [`--settings`](/docs/en/settings#change-a-setting-for-one-session). For example, th
```bash theme={null}
claude --settings '{"sandbox": {"enabled": true, "allowUnsandboxedCommands": false}}'
+6 −0 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
mcp
±changed
+3−1
claude-codechanged
mcp
In `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code can't show that prompt: it loads project-scoped ser
In `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code can't show that prompt: it loads project-scoped ser
* You can set the client secret only when you add the server. When you authenticate with `claude mcp login` or from `/mcp`, Claude Code uses the stored secret and doesn't prompt
* To add or change the secret later, remove the server with `claude mcp remove <name>`, then add it again with `--client-secret` and the same `--scope`
+3 −1 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A restore point created at each prompt you send. Claude Code snapshots files before every edit so a checkpoint can revert them. Press `Esc` twice or run `/rewind` to restore code,
A restore point created at each prompt you send that starts a turn. Claude Code snapshots files before every edit so a checkpoint can revert them. Press `Esc` twice or run `/rewind
+1 −1 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
fullscreen
±changed
+1−1
claude-codechanged
fullscreen
* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, and `--append-system-prompt` flags
* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-promp
+1 −1 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
errors
±changed
+3−0
claude-codechanged
errors
On macOS, `EPERM` for a directory in `~/Desktop`, `~/Documents`, `~/Downloads`, or iCloud Drive usually means macOS is blocking your terminal app from that folder. Other commands t
* For `EPERM` on macOS, quit your terminal app with Cmd+Q, open it again, return to that folder, and run `claude`. If `ls` in that folder still fails, open **System Settings > Priv
+3 −0 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
checkpointing
±changed
+9−3
claude-codechanged
checkpointing
As you work with Claude, checkpointing automatically captures the state of your code before each user prompt.
As you work with Claude, checkpointing automatically captures the state of your code before each prompt you send that starts a turn.
* Every user prompt creates a new checkpoint
* Every prompt you send that starts a turn creates a new checkpoint
The rewind menu lists each prompt you sent during the session. Select the point you want to act on, then choose an action:
+9 −3 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
Every prompt you send creates a checkpoint. You can restore conversation, code, or both to any previous checkpoint.
Every prompt you send that starts a turn creates a checkpoint. You can restore conversation, code, or both to any previous checkpoint.
+1 −1 lines
Recorded here 11 Sep 2026 14:37 UTC
claude-code
troubleshooting
±changed
+11−0
claude-codechanged
troubleshooting
### Copied text doesn't reach your local clipboard over SSH
When Claude Code runs on a remote machine over SSH, it can't run a clipboard tool on your local machine. Outside tmux, when you select text in [fullscreen rendering](/docs/en/fulls
Some terminals don't act on OSC 52. iTerm2 ignores it until you turn on **Settings > General > Selection > Applications in terminal may access clipboard**, and macOS Terminal.app d
+11 −0 lines
Recorded here 11 Sep 2026 14:07 UTC
10 Sep 2026
55 pages
+679 −383 lines
claude-code
server-managed-settings
±changed
+2−0
claude-codechanged
server-managed-settings
An approval for `sandbox.credentials` or `sandbox.network.tlsTerminate` also covers the [`sandbox.network.allowedDomains`](/docs/en/settings-reference#sandbox-network-alloweddomain
+2 −0 lines
Recorded here 10 Sep 2026 23:07 UTC
claude-code
llm-gateway-connect
±changed
+15−2
claude-codechanged
llm-gateway-connect
These configurations point Claude Code at a gateway through a provider-specific base URL variable in place of `ANTHROPIC_BASE_URL`. Amazon Bedrock and Google Cloud's Agent Platform
These configurations point Claude Code at a gateway through a provider-specific base URL variable in place of `ANTHROPIC_BASE_URL`. Amazon Bedrock and Google Cloud's Agent Platform
Set the block for the provider your gateway team named. The skip-auth variables tell Claude Code not to sign requests with provider credentials, since the gateway holds those. If t
Set the block for the provider your gateway team named. The skip-auth variables in the Amazon Bedrock, Google Cloud's Agent Platform, and Claude Platform on AWS blocks tell Claude
+15 −2 lines
Recorded here 10 Sep 2026 23:07 UTC
claude-code
hooks
±changed
+22−18
claude-codechanged
hooks
For most hook events, exit code 2 is the only exit code that blocks through the code alone. Without valid JSON on stdout, Claude Code treats exit code 1 as a non-blocking error a
For most hook events, exit code 2 is the only exit code that blocks through the code alone. Without valid JSON on stdout, Claude Code treats exit code 1 as a non-blocking error a
| `WorktreeRemove` | No | Failures are logged in debug mode only
| `WorktreeRemove` | Yes | Any non-zero exit code causes worktree removal to fail if the directory still exists afterward. See [WorktreeRemove](#worktreeremove) for wha
| Events | Decision pattern
+22 −18 lines
Recorded here 10 Sep 2026 23:07 UTC
claude-code
cli-reference
±changed
+36−36
claude-codechanged
cli-reference
| Command | Description
| :------------------------------ | :-----------------------------------------------------------------------------------------------------------------------------------------------
| `claude` | Start interactive session
| `claude "query"` | Start interactive session with initial prompt
| `claude -p "query"` | Query via SDK, then exit
+36 −36 lines
Recorded here 10 Sep 2026 23:07 UTC
claude-code
claude-apps-gateway-config
±changed
+12−3
claude-codechanged
claude-apps-gateway-config
* [`pricing`](#pricing): contracted rates and a discount multiplier for the spend meter
* [`pricing`](#pricing): contracted rates and a discount multiplier for the spend meter and for the cost figures developers see
* An [`admin:`](#admin) block, because only the spend meter reads `pricing`. The gateway refuses to start with `pricing` set and no `admin`.
* An [`admin:`](#admin) block or, in v2.1.268 or later, a [`managed:`](#managed) block with at least one policy. The gateway refuses to start with `pricing` set and neither block,
| `overrides` | No | Rows of `{upstream, model, input, output, cache_read, cache_write}` in USD per million tokens. All four rates are required and must be positive.
+12 −3 lines
Recorded here 10 Sep 2026 23:07 UTC
claude-code
agent-view
±changed
+21−14
claude-codechanged
agent-view
* When git or your [`WorktreeRemove` hook](/docs/en/hooks#worktreeremove) fails to remove the worktree, Claude Code keeps the worktree and the session, and the message names the ca
* Delete the session again to remove the directory anyway, by pressing `Ctrl+X` twice on its row in agent view or running the `claude rm <id> --force-remove-worktree <worktree-id
* Fix what stands in the way, such as committing or stashing the uncommitted changes, closing whatever is using the directory, or fixing the hook, then delete the session again.
* Remove the directory yourself, then delete the session again.
+21 −14 lines
Recorded here 10 Sep 2026 23:07 UTC
claude-code
vs-code
±changed
+2−2
claude-codechanged
vs-code
* **Activity Bar**: click the Spark icon in the left sidebar to open the sessions list. Click any session to open it as a full editor tab, or start a new one. This icon is alwa
* **Activity Bar**: click the Spark icon in the left sidebar to open the sessions list. Click any session to open it in your [preferred location](#extension-settings), or start
After you make changes, a banner prompts you to restart Claude Code to apply them.
Plugin changes you make in the dialog apply right away to the Claude Code sessions open in that VS Code window. If the session you opened the dialog from can't reload its plugins,
+2 −2 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
tools-reference
±changed
+12−7
claude-codechanged
tools-reference
| `TaskCreate` | Creates a new task in the task list. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you op
| `TaskGet` | Retrieves full details for a specific task. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless
| `TaskList` | Lists all tasks with their current status. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless
| `TaskCreate` | Creates a new task in the task list. Provided by default only on the models listed under [Task tool availability](#task-tool-availability), and on other
| `TaskGet` | Retrieves full details for a specific task. Provided by default only on the models listed under [Task tool availability](#task-tool-availability), and on
+12 −7 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
skills
±changed
+2−2
claude-codechanged
skills
* **Plugin skill**: disable or uninstall the plugin that provides it, from the `/plugin` menu or with `/plugin uninstall <plugin-name>@<marketplace-name>`. Claude Code unloads the
* **Plugin skill**: disable or uninstall the plugin that provides it, from the `/plugin` menu or with `/plugin uninstall <plugin-name>@<marketplace-name>`. Claude Code unloads the
If the install summary reports `Run /reload-plugins to activate.`, run that command to make the plugin's skills available in the current session. Then ask Claude to evaluate an exi
If the install summary reports `Run /reload-plugins to activate.`, Claude Code then runs that reload for you. If the reload warns that your next message would re-read the conversat
+2 −2 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
security-guidance
±changed
+1−5
claude-codechanged
security-guidance
Check the install summary. If it reports `Run /reload-plugins to activate.`, apply the pending change without a restart:
```text theme={null}
/reload-plugins
```
+1 −5 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
remote-control
±changed
+5−3
claude-codechanged
remote-control
In an interactive terminal session, a `/rc active` indicator sits in the footer below the input box while the connection is up, and is hidden if the terminal is too narrow to fit i
If the connection fails, Claude Code shows a notification with the failure reason and switches the indicator to a failure state that stays in the footer. To read the reason again,
In an interactive terminal session, a `/rc active` indicator shows while the connection is up, and is hidden if the terminal is too narrow to fit it. With [fullscreen rendering](/d
+5 −3 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
prompt-caching
±changed
+11−16
claude-codechanged
prompt-caching
* [Changing output style](#changing-output-style)
A plugin change applies when you run [`/reload-plugins`](/docs/en/discover-plugins#apply-plugin-changes-without-restarting) or start a new session, not when you run `/plugin enable
A change you make in the `/plugin` menu goes through [`/reload-plugins`](/docs/en/discover-plugins#apply-plugin-changes-without-restarting), which Claude Code runs for you when you
* When you [install a plugin from the `/plugin` interface](/docs/en/discover-plugins#install-plugins), Claude Code can activate it during the install. Claude Code tells you in the
* When you [install a plugin from the `/plugin` interface](/docs/en/discover-plugins#install-plugins), Claude Code can activate it during the install. The install summary tells you
+11 −16 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
plugins-reference
±changed
+34−21
claude-codechanged
plugins-reference
| `--json` | Print the result as one JSON object on the last line of stdout instead of the human-readable message, for use in scripts. See [JSON result format](#plugi
<span id="plugin-json-result" />With `--json`, the last line of stdout is one JSON object. Parse only that line, because Claude Code prints any command the marketplace declares ahe
* `command`: the subcommand that ran, such as `install`
+34 −21 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
plugins
±changed
+1−1
claude-codechanged
plugins
After you install the plugin, check the install summary: if it reports `Run /reload-plugins to activate.`, run that command to load the Skills. For complete Skill authoring guidanc
After you install the plugin, check the install summary: if it reports `Run /reload-plugins to activate.`, see [Apply plugin changes without restarting](/docs/en/discover-plugins#a
+1 −1 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
plugin-marketplaces
±changed
+1−1
claude-codechanged
plugin-marketplaces
From the directory that contains `my-marketplace`, start Claude Code and run the following commands. The install command opens a plugin details view where you select an install
From the directory that contains `my-marketplace`, start Claude Code and run the following commands. The install command opens a plugin details view where you select an install
+1 −1 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
4. If the classifier blocks, Claude receives the reason and tries an alternative. In most sessions the reason is the fixed text `Blocked by classifier` rather than a written ex
4. If the classifier blocks, Claude receives the reason and tries an alternative. In most sessions the reason names the rule the classifier matched, such as `[Data Exfiltration
+1 −1 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
mcp
±changed
+4−4
claude-codechanged
mcp
Check the install summary: if it reports `Run /reload-plugins to activate.`, run that command.
If the install summary reports `Run /reload-plugins to activate.`, Claude Code then runs that reload for you. If the reload warns that your next message would re-read the conve
When you complete authentication from `/mcp` and the connection still fails with an HTTP status or a transport error code, Claude Code adds that code and the origin of the URL it t
When you complete authentication from `/mcp` and the connection still fails with an HTTP status or a transport error code, Claude Code adds that code and the origin of the server's
* Claude Code takes the origin after `${VAR}` expansion, so a host that comes from a variable appears expanded.
+4 −4 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
On [Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and later versions of those families](/docs/en/tools-reference#task-tool-availability), Claude keeps track of multi-step work without a w
The list fills only in sessions that have the task-tracking tools, which Claude Code provides by default on [Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku
+1 −1 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
hooks
±changed
+7−7
claude-codechanged
hooks
"reason": "Blocked by classifier"
}
```
| Field | Description
+7 −7 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
errors
±changed
+2−2
claude-codechanged
errors
Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected (or the connection expired). To fix: run /web-setup t
Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected (or the connection expired). To fix: run /web-setup t
* Run `/web-setup` to connect your GitHub CLI login to your Claude account, or connect an account at [claude.ai/code/onboarding](https://claude.ai/code/onboarding?step=alt-auth)
* Run `/web-setup` to connect your GitHub CLI login to your Claude account, or connect an account at [claude.ai/connect-github](https://claude.ai/connect-github)
+2 −2 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
env-vars
±changed
+2−2
claude-codechanged
env-vars
| `CLAUDE_CODE_ENABLE_TODO_TOOLS` | Set to `1` to get the task-tracking tools on the models listed under [Task tool availability](/docs/en/tools-reference#t
| `CLAUDE_CODE_ENABLE_TODO_TOOLS` | Set to `1` to get the task-tracking tools on every model. Without it, Claude Code provides them by default only on the m
| `CLAUDE_CODE_WEBFETCH_DEADLINE_MS` | Upper bound in milliseconds on how long [WebFetch](/docs/en/tools-reference#webfetch-tool-behavior) waits for a page to
* Have a resumed conversation [keep its recorded system prompt](/docs/en/cli-reference#system-prompt-flags-in-resumed-conversations); Claude Code rebuilds the prompt on every reque
+2 −2 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
discover-plugins
±changed
+13−10
claude-codechanged
discover-plugins
Check the install summary: if it reports `Run /reload-plugins to activate.`, run `/reload-plugins`, and if that warns that the reload will re-read the conversation, rerun it as
If the install summary reports `Run /reload-plugins to activate.`, Claude Code then runs that reload for you. If the reload warns that your next message would re-read the conve
* `Run /reload-plugins to activate.`: the plugin isn't active yet, because activating it would [invalidate the prompt cache](/docs/en/prompt-caching#enabling-or-disabling-a-plugin)
* `Run /reload-plugins to activate.`: the plugin isn't active yet, because activating it would [invalidate the prompt cache](/docs/en/prompt-caching#enabling-or-disabling-a-plugin)
* When you run `/plugin disable`, `/plugin enable`, or `/plugin uninstall`, Claude Code opens the plugin panel to apply the change and leaves it open. Press **Esc** to close the pa
+13 −10 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
Recording applies in sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), as sessions signed in with a claude.ai or Console account do b
If you start Claude Code in [bare mode](/docs/en/headless#start-faster-with-bare-mode), by passing `--bare` or setting `CLAUDE_CODE_SIMPLE=1`, recording stays off unless you pass `
+1 −1 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
claude-security
±changed
+1−5
claude-codechanged
claude-security
Check the install summary. If it reports `Run /reload-plugins to activate.`, apply the pending change without a restart:
```text theme={null}
/reload-plugins
```
+1 −5 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
claude-apps-gateway-config
±changed
+2−0
claude-codechanged
claude-apps-gateway-config
Set it to `1` only in the policies whose groups you want traced. A policy that doesn't set it inherits the value from your `match: {}` catch-all policy if that policy sets one, per
+2 −0 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
channels
±changed
+2−2
claude-codechanged
channels
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
+2 −2 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
auto-mode-config
±changed
+4−4
claude-codechanged
auto-mode-config
Two other places on screen that report denials leave out the command or URL: the notice near the input box, such as `bash denied by auto mode · Blocked by classifier · /permissions
The text beneath the call tells you whether there is anything to fix. Text that reports a problem with the classifier itself, such as a model that `is temporarily unavailable` or a
Two other places on screen that report denials leave out the command or URL: the notice near the input box, such as `bash denied by auto mode · [Data Exfiltration] · /permissions`,
+4 −4 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
artifacts
±changed
+1−1
claude-codechanged
artifacts
Claude picks the artifact's title and an emoji for its browser-tab icon. Both appear in your [gallery of artifacts](#share-an-artifact) on claude.ai and in shared links, so ask Cla
Claude picks the artifact's title and an emoji, and both appear in your [gallery of artifacts](#share-an-artifact) on claude.ai and in shared links. Claude can also pick a browser-
+1 −1 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
agent-sdk/typescript
±changed
+14−12
claude-codechanged
agent-sdk/typescript
When a client sends `initialize` to a session that is already running, the control-response wrapper also carries an optional `pending_permission_requests` array. The field is on th
These are requests that were issued before the client connected and are still awaiting a reply. The SDK reads the array for you and dispatches each entry to your [`canUseTool`](#ca
The control-response wrapper for a successful `initialize` also carries a `pending_permission_requests` array. The field is on the response wrapper itself, not in the `SDKControlIn
+14 −12 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
agent-sdk/todo-tracking
±changed
+6−6
claude-codechanged
agent-sdk/todo-tracking
On the models listed under [Model availability](#model-availability), Claude tracks multi-step work without a written todo list, and Claude Code leaves the [task-tracking tools](/d
Claude Code provides the [task-tracking tools](/docs/en/tools-reference#task-tool-availability) by default only on the models listed under [Model availability](#model-availability)
On TypeScript Agent SDK 0.3.233 and later, or Python Agent SDK 0.2.139 and later, the following restriction applies.
The following tools aren't available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, or later versions of those families unless you opt in:
+6 −6 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
agent-sdk/python
±changed
+4−4
claude-codechanged
agent-sdk/python
On Python Agent SDK 0.2.139 and later, the following restriction applies.
The following tools aren't available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, or later versions of those families unless you opt in:
The following tools are available by default only on Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku 4.5. On every other model, including model IDs Claude
On other models, Claude Code provides the Task tools by default and `TodoWrite` only when you set `CLAUDE_CODE_ENABLE_TASKS=0`.
+4 −4 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+3−3
claude-codechanged
agent-sdk/modifying-system-prompts
Recording applies in sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), as sessions using a claude.ai or Console account do by default
To rebuild the prompt on every request instead, set `snapshot: false` on the object form of `systemPrompt` in the TypeScript SDK: `{ type: "preset", preset: "claude_code", append,
If you start Claude Code in [bare mode](/docs/en/headless#start-faster-with-bare-mode) by passing `--bare` through `extraArgs` or setting `CLAUDE_CODE_SIMPLE=1`, recording stays of
+3 −3 lines
Recorded here 10 Sep 2026 22:37 UTC
claude-code
tools-reference
±changed
+1−7
claude-codechanged
tools-reference
When a command reaches its timeout without finishing, Claude Code moves it to the background instead of stopping it. Claude keeps working while the command continues. Claude Code a
Claude Code never auto-backgrounds three kinds of command. It stops them at the timeout instead:
* A command that starts with `sleep`.
+1 −7 lines
Recorded here 10 Sep 2026 21:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.