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
808pages tracked
757 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
152 changed this week · last read 22 Oct 2026
Claude Documentation
279pages tracked
76 changed this week · last read 22 Oct 2026
Model Context Protocol
357pages tracked
163 changed this week · last read 21 Oct 2026
100 on this page
5,531 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
8 Oct 2026
71 pages
+8066 −5601 lines
claude-code
model-config
±changed
+33−35
claude-codechanged
model-config
| **`opus[1m]`** | Uses Opus with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long s
| **`opus[1m]`** | Uses Opus with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long s
The fallback model must also have a context window at least as large as the session's, or Claude Code doesn't switch and the flagged request ends with the same refusal. On these pr
<span id="sonnet-5-5-and-sonnet-5-context-window" />
+33 −35 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
microsoft-foundry
±changed
+18−0
claude-codechanged
microsoft-foundry
## 1M token context window
On Microsoft Foundry, when Claude Code can tell which model your deployment serves, Fable models, Sonnet 5 and later, and Opus 4.7 and later run with the [1M token context window](
This `settings.json` entry tells Claude Code that a deployment named `team-opus-prod` serves Opus 4.8:
+18 −0 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
google-vertex-ai
±changed
+5−3
claude-codechanged
google-vertex-ai
Claude Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes
The [setup wizard](#sign-in-with-agent-platform) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. Se
Fable models, Sonnet 5 and later, and Opus 4.7 and later run with the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window
+5 −3 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
context-window
±changed
+0−2
claude-codechanged
context-window
Sonnet 5.5 and Sonnet 5 run with the 1M context window and have no `[1m]` variant to select. See [Sonnet 5.5 and Sonnet 5 context window](/docs/en/model-config#sonnet-5-5-and-sonne
+0 −2 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
claude-apps-gateway
±changed
+1−0
claude-codechanged
claude-apps-gateway
| 1M token context window | Available | Fable models, Sonnet 5 and later, and Opus 4.7 and later run with the 1M window by default; see [Extended context](/docs/en/model-config#ext
+1 −0 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
amazon-bedrock
±changed
+5−3
claude-codechanged
amazon-bedrock
Claude Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes
The [setup wizard](#sign-in-with-bedrock) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. See [Pin
Fable models, Sonnet 5 and later, and Opus 4.7 and later run with the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window
+5 −3 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 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 8 Oct 2026 18:37 UTC
claude-code
web-quickstart
±changed
+1−1
claude-codechanged
web-quickstart
You'll need a GitHub repository to [get started](#connect-github). Claude clones it into an isolated virtual machine, makes changes, and pushes a branch for you to review. Sessions
You'll need a GitHub repository to [get started](#connect-github). Claude clones it into an isolated virtual machine, makes changes, and pushes a branch for you to review. Sessions
+1 −1 lines
Upstream edited 8 Oct 2026 18:29 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
claude-code-on-the-web
±changed
+2−2
claude-codechanged
claude-code-on-the-web
A cloud session is a Claude Code session that runs on cloud infrastructure instead of on your machine. By default it runs on infrastructure Anthropic manages, or on your organizati
A cloud session is a Claude Code session that runs on cloud infrastructure instead of on your machine. By default it runs on infrastructure Anthropic manages, or on your organizati
* **Rate limits**: cloud sessions share rate limits with all other Claude and Claude Code usage within your account. Running multiple tasks in parallel consumes more rate limits pr
* **Rate limits**: cloud sessions share rate limits with all other Claude and Claude Code usage within your account. Running multiple tasks in parallel consumes more rate limits pr
+2 −2 lines
Upstream edited 8 Oct 2026 18:29 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
tools-reference
±changed
+8−4
claude-codechanged
tools-reference
A command that a [foreground subagent](/docs/en/sub-agents#run-subagents-in-foreground-or-background) started stops when that subagent's run ends, whether it finished, failed, or w
A command that a [foreground subagent](/docs/en/sub-agents#run-subagents-in-foreground-or-background) started stops when that subagent's run ends, whether it finished, failed, or w
While a command that the main conversation started is still running, a run in non-interactive mode with the `-p` flag [stays open after its result](/docs/en/headless#background-tas
In a run with the `-p` flag whose prompt you pass as text rather than with `--input-format stream-json`, both defaults are 10 minutes instead of 30, because the run [waits for back
+8 −4 lines
Upstream edited 8 Oct 2026 18:27 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
headless
±changed
+12−7
claude-codechanged
headless
If Claude starts a [background Bash task](/docs/en/tools-reference#bash-tool-behavior) during a `claude -p` run, for example a dev server or a watch build, that shell is terminated
If Claude starts a background [subagent](/docs/en/sub-agents) or workflow, `claude -p` instead stays open until that work completes, because its result is part of the final output.
By default the wait ends after 10 minutes of continuous idle waiting, so a stuck subagent or workflow can't hold the process open indefinitely. At that point Claude Code stops what
+12 −7 lines
Upstream edited 8 Oct 2026 18:27 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
artifacts
±changed
+1−1
claude-codechanged
artifacts
| Surface | Claude Code CLI, or the Claude desktop app version 1.13576.0 or later. [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions can also publish artifacts whe
| Surface | Claude Code CLI, or the Claude desktop app version 1.13576.0 or later. [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions can also publish artifacts whe
+1 −1 lines
Upstream edited 8 Oct 2026 18:25 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
common-workflows
±changed
+1−2
claude-codechanged
common-workflows
Claude has built-in access to its documentation and can answer questions about its own features and limitations.
Claude can answer questions about its own features and limitations. It looks up the answers in the current Claude Code documentation, so they aren't limited to the version you're r
* Claude always has access to the latest Claude Code documentation, regardless of the version you're using
+1 −2 lines
Upstream edited 8 Oct 2026 18:24 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
plugin-evals
±changed
+1−1
claude-codechanged
plugin-evals
| An installed plugin by name, `name` or `name@marketplace` | The cases in the installed copy's eval directory, with the installed copy loaded. Results are written under `./evals/r
| An installed plugin by name, `name` or `name@marketplace` | The plugin and the cases in its eval directory, read [in place or from the installed copy](/docs/en/plugins/loading#in
+1 −1 lines
Upstream edited 8 Oct 2026 18:23 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
plugins/mods/troubleshoot
±changed
+4−2
claude-codechanged
plugins/mods/troubleshoot
| `hooks modules are turned off in this process` | Anthropic has turned installed mods off remotely. No setting on your machine turns them back on. |
| `hooks modules are turned off in this process: the rollout switch served off` | Anthropic has turned installed mods off remotely. |
| `hooks modules are turned off in this process: the rollout switch was saved off by an earlier session` | The command used a value an earlier session saved, which may be out of da
| `hooks modules are turned off for installed plugins in this process` | Anthropic has turned installed mods off remotely. No setting on your machine turns them back on. |
| `hooks modules are turned off for installed plugins in this process: the rollout switch served off` | Anthropic has turned installed mods off remotely. |
+4 −2 lines
Upstream edited 8 Oct 2026 18:23 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
errors
±changed
+4−8
claude-codechanged
errors
You've hit your monthly spend limit · raise it at claude.ai/settings/usage
You've hit your monthly spend limit · raise it at https://claude.ai/settings/usage?from=cc_cli_limit_message
You've hit your org's monthly spend limit · visit claude.ai/admin-settings/usage to raise it
You've hit your team's shared budget · ask your admin to raise it at claude.ai/admin-settings/usage
You've hit your org's monthly spend limit · visit https://claude.ai/admin-settings/usage to raise it
+4 −8 lines
Upstream edited 8 Oct 2026 18:22 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
agent-view
±changed
+3−2
claude-codechanged
agent-view
A reply that can't be delivered, because the background service is unreachable or the send fails, is saved and sent to the session as its next prompt when its process starts again,
When a reply can't be delivered, the error message says whether it was saved. A reply prefixed with `!` or `/` is never saved. Claude Code sends a saved reply as the session's next
Claude Code saves a reply you typed with the refused attempt and sends it the next time the session starts.
Claude Code saves a reply you typed with the refused attempt, except one prefixed with `!` or `/`, and sends it the next time the session starts.
| v2.1.290 | A [peek reply](#peek-and-reply) that can't be delivered is no longer saved for the next restart when it starts with `/`, or when it answers a question with predefined
+3 −2 lines
Upstream edited 8 Oct 2026 18:22 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
plugins/mods/events
±changed
+16−2
claude-codechanged
plugins/mods/events
To make a hook that blocks calls fail closed, add a `.catch` error handler that answers in its place. Here, `guard` is your hook function:
To make a hook that blocks calls fail closed, add a `.catch` error handler that answers in its place. Here, `guard` is your hook function, and the handler tests [`next.called`](/do
// guard had already called next, so return what came back
if (next.called) return next(e)
While `guard` works, the handler never runs. When `guard` throws or times out on a Bash call, Claude Code calls the handler with the same event. The handler returns `{ deny }`, so
+16 −2 lines
Upstream edited 8 Oct 2026 18:22 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
settings-reference
±changed
+2−2
claude-codechanged
settings-reference
* **Scope**: [`Any file`](#scopes). Appears in `/config` as **Switch models when a message is flagged**.
* **Scope**: [`Any file`](#scopes). Appears in `/config` as **Switch models when a message is flagged**, with the options **Switch automatically** and **Ask each time**.
* **Default**: `true`, switch automatically
* **Default**: unset. Claude Code switches automatically, though it may [ask first](/docs/en/model-config#ask-before-switching) in an interactive session
+2 −2 lines
Upstream edited 8 Oct 2026 18:17 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models, Opus 5.5, Sonnet 5.5, and Opus 5 is also a model switch. When a safety classifier flags
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models, Opus 5.5, Sonnet 5.5, and Opus 5 is also a model switch. When a safety classifier flags
+1 −1 lines
Upstream edited 8 Oct 2026 18:17 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
model-config
±changed
+12−5
claude-codechanged
model-config
Fable models, Opus 5.5, Sonnet 5.5, and Opus 5 run with safety classifiers, which most often flag cybersecurity and biology content. When a classifier flags a request and the flagg
Fable models, Opus 5.5, Sonnet 5.5, and Opus 5 run with safety classifiers, which most often flag cybersecurity and biology content. For those two categories, the fallback model de
When Claude Code switches a flagged request to the fallback model for its category, it re-runs the request on that model. In your main conversation, it shows a notice in the transc
To decide what happens each time a request is flagged, rather than switching automatically, run `/config` and turn off **Switch models when a message is flagged**, or set [`switchM
+12 −5 lines
Upstream edited 8 Oct 2026 18:17 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
server-managed-settings
±changed
+6−1
claude-codechanged
server-managed-settings
A session receives the managed settings of the organization that owns the credential it authenticates with. An API key from the [Claude Console](https://platform.claude.com) belong
* **OAuth token**: generate a token with [`claude setup-token`](/docs/en/authentication#generate-a-long-lived-token), authorize it for your Team or Enterprise organization, and set
* **Endpoint-managed settings**: deploy a [managed settings file](/docs/en/managed-settings#delivery-mechanisms) to the machine that runs the job.
+6 −1 lines
Upstream edited 8 Oct 2026 18:10 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
feature-availability
±changed
+2−2
claude-codechanged
feature-availability
<td>✓ (Team and Enterprise)</td>
<td>See [Platform availability](/docs/en/server-managed-settings#platform-availability)</td>
Everything in [CLI capabilities that vary by provider](#cli-capabilities-that-vary-by-provider) is available, except that [fast mode](/docs/en/fast-mode) requires [provisioned
Everything in [CLI capabilities that vary by provider](#cli-capabilities-that-vary-by-provider) is available, except that [fast mode](/docs/en/fast-mode) requires [provisioned
+2 −2 lines
Upstream edited 8 Oct 2026 18:10 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 8 Oct 2026 18:07 UTC
claude-code
mcp
±changed
+1−0
claude-codechanged
mcp
* **Response size from HTTP and SSE servers**: Claude Code stops reading a response from an [HTTP](#option-1-add-a-remote-http-server) or [SSE](#option-2-add-a-remote-sse-server) s
+1 −0 lines
Upstream edited 8 Oct 2026 18:05 UTC Recorded here 8 Oct 2026 18:37 UTC
claude-code
plugins/marketplace-reference
±changed
+1−0
claude-codechanged
plugins/marketplace-reference
* **The download folder of a registered GitHub marketplace, `<owner>-<repo>`**: Claude Code downloads a marketplace added from a `github` source such as `acme/x-tools` through a fo
+1 −0 lines
Upstream edited 8 Oct 2026 18:03 UTC Recorded here 8 Oct 2026 18:07 UTC
claude-code
tools-reference
±changed
+9−3
claude-codechanged
tools-reference
An interactive terminal session can make 200 WebSearch calls, counted across the main conversation and every [subagent](/docs/en/sub-agents) it spawns, so searches made by parallel
Set the [`CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION`](/docs/en/env-vars) environment variable to change the cap; it accepts a positive whole number, so the cap can be raised but not
An interactive terminal session has a limit of 200 WebSearch calls. Searches from the main conversation and from [subagents](/docs/en/sub-agents), such as a parallel research fan-o
+9 −3 lines
Upstream edited 8 Oct 2026 17:56 UTC Recorded here 8 Oct 2026 18:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+3−3
claude-codechanged
claude-apps-gateway-deploy
<Warning>
<Info>
Choose the gateway's address before you choose where it runs. If your internal network uses public IPv4 ranges, you can list one range that holds both the gateway and your users'
</Warning>
Choose the gateway's address before you choose where it runs. Usually that's a private address that users reach on your internal network or over a VPN. If your internal network u
+3 −3 lines
Upstream edited 8 Oct 2026 09:32 UTC Recorded here 8 Oct 2026 09:37 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 8 Oct 2026 09:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+20−7
claude-codechanged
claude-apps-gateway-deploy
<Warning>
**Plan your gateway's network first.** At sign-in, Claude Code refuses a Claude apps gateway whose hostname resolves to a public IP address, even one the internet can't reach.
A Claude apps gateway can push settings to users' machines, including hooks that run shell commands. The check helps keep users from accidentally signing in to a malicious gatewa
+20 −7 lines
Upstream edited 8 Oct 2026 09:05 UTC Recorded here 8 Oct 2026 09:07 UTC
claude-code
claude-apps-gateway
±changed
+1−1
claude-codechanged
claude-apps-gateway
Some organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway can't have a private ad
Some organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway has no private address.
+1 −1 lines
Upstream edited 8 Oct 2026 09:05 UTC Recorded here 8 Oct 2026 09:07 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 8 Oct 2026 05:37 UTC
claude-code
changelog
±changed
+5−0
claude-codechanged
changelog
<Update label="2.1.294" description="October 8, 2026">
* Fixed `prompt` and `agent` hooks written as instructions (such as "Block commands that...") allowing what they should block
* Improved how `prompt` hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop early
</Update>
+5 −0 lines
Upstream edited 8 Oct 2026 05:15 UTC Recorded here 8 Oct 2026 05:37 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 8 Oct 2026 03:58 UTC
claude-code
output-styles
±changed
+24−24
claude-codechanged
output-styles
> * For what Claude should know about your project, use [CLAUDE.md](/docs/en/memory).
> * For something that has to happen every time, such as formatting after each edit or blocking a command, use a [hook](/docs/en/hooks-guide).
> * For what Claude should know about your project, use [CLAUDE.md](/docs/en/memory.md).
> * For something that has to happen every time, such as formatting after each edit or blocking a command, use a [hook](/docs/en/hooks-guide.md).
Switching to the Proactive style doesn't change your [permission mode](/docs/en/permission-modes). Your permission mode still decides which tool calls run without asking you, so pe
+24 −24 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
output-styles
±changed
+41−47
claude-codechanged
output-styles
<Note>
An output style gives Claude instructions to follow. It doesn't guarantee that something always happens or never happens. Some needs fit a different feature:
* For what Claude should know about your project, use [CLAUDE.md](/docs/en/memory).
* For something that has to happen every time, such as formatting after each edit or blocking a command, use a [hook](/docs/en/hooks-guide).
+41 −47 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
output-styles
±changed
+4−4
claude-codechanged
output-styles
| `keep-coding-instructions` | No | Set to `true` to keep Claude Code's built-in software engineering instructions alongside your style. Default: `false` |
| `keep-coding-instructions` | No | Set to `true` to keep Claude Code's section of built-in software engineering instructions, which only the full system prompt includes, alongside
* Custom output styles leave out Claude Code's built-in software engineering instructions, such as how to scope changes, write comments, and verify work, unless `keep-coding-instru
Output styles apply to the main conversation and to a [fork](/docs/en/sub-agents#fork-the-current-conversation), which inherits the parent's full conversation and system prompt. Ot
+4 −4 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 8 Oct 2026 03:58 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A configuration that changes the instructions Claude Code gives Claude, to set response behavior, tone, or format. Unlike [CLAUDE.md](#claude-md), which adds project context alongs
A configuration that changes the instructions Claude Code gives Claude, to set response behavior, tone, or format. Unlike [CLAUDE.md](#claude-md), which adds project context alongs
+1 −1 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 8 Oct 2026 03:58 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+2−2
claude-codechanged
agent-sdk/modifying-system-prompts
A custom output style leaves the `claude_code` preset's software engineering instructions out and uses your own. To keep them and layer your instructions on top, set `keep-coding-i
A custom output style leaves the `claude_code` preset's software engineering instructions out and uses your own. To keep them and layer your instructions on top, set `keep-coding-i
| **Customization level** | Additions only | Replace or extend default | Additions only | Complete control |
| **Customization level** | Additions only | Additions; can omit coding instructions | Additions only | Complete control |
+2 −2 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 8 Oct 2026 03:58 UTC
claude-code
quickstart
±changed
+17−17
claude-codechanged
quickstart
* A [Claude subscription](https://claude.com/pricing?utm_source=claude_code\&utm_medium=docs\&utm_content=quickstart_prereq) (Pro, Max, Team, or Enterprise), [Claude Console](https
* A [Claude subscription](https://claude.com/pricing?utm_source=claude_code\&utm_medium=docs\&utm_content=quickstart_prereq) (Pro, Max, Team, or Enterprise), [Claude Console](https
> * **Want Claude Code somewhere other than the terminal**: Claude Code is also available on the [web](https://claude.ai/code), as a [desktop app](/docs/en/desktop), in [VS Code](/
> * **Want Claude Code somewhere other than the terminal**: Claude Code is also available on the [web](https://claude.ai/code), as a [desktop app](/docs/en/desktop.md), in [VS Code
The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation pri
+17 −17 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
quickstart
±changed
+101−105
claude-codechanged
quickstart
<Note>
These cases are covered on other pages:
* **Never used a terminal before**: start with the [terminal guide](/docs/en/terminal-guide)
* **Want Claude Code somewhere other than the terminal**: Claude Code is also available on the [web](https://claude.ai/code), as a [desktop app](/docs/en/desktop), in [VS Code](/
+101 −105 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 20 Oct 2026 18:37 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} 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} theme={null} theme={null} theme={null} theme={null} theme=
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null
+5 −5 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 8 Oct 2026 03:58 UTC
claude-code
quickstart
±changed
+5−5
claude-codechanged
quickstart
```bash theme={null} theme={null} theme={null} theme={null} theme={null} 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} theme={null} theme={null} theme={null} theme={null} theme=
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null
+5 −5 lines
Upstream edited 8 Oct 2026 03:42 UTC Recorded here 8 Oct 2026 03:58 UTC
claude-code
mcp
±changed
+0−2
claude-codechanged
mcp
**Important: Separate server arguments with `--`**
+0 −2 lines
Upstream edited 8 Oct 2026 02:40 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
statusline
±changed
+39−31
claude-codechanged
statusline
**When it updates**
<Note>The status line runs locally and does not consume API tokens. It temporarily hides during certain UI interactions, including the help menu and permission prompts.</Note>
### When the status line updates
**What your script can output**
+39 −31 lines
Upstream edited 8 Oct 2026 02:40 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
setup
±changed
+15−15
claude-codechanged
setup
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} 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} theme={null} theme={null} theme={null} theme={null} theme=
```batch theme={null}
+15 −15 lines
Upstream edited 8 Oct 2026 02:40 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
quickstart
±changed
+17−19
claude-codechanged
quickstart
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} 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} theme={null} theme={null} theme={null} theme={null} theme=
```batch theme={null}
+17 −19 lines
Upstream edited 8 Oct 2026 02:40 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
microsoft-foundry
±changed
+43−35
claude-codechanged
microsoft-foundry
Claude Code supports three authentication methods for Microsoft Foundry. Choose the method that best fits your security requirements.
**Option A: API key authentication**
1. Navigate to your resource in the Microsoft Foundry portal
+43 −35 lines
Upstream edited 8 Oct 2026 02:40 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
claude-platform-on-aws
±changed
+7−4
claude-codechanged
claude-platform-on-aws
Claude Code supports two authentication methods for Claude Platform on AWS. Choose the method that fits how your team manages access.
**Option A: AWS credentials with SigV4**
Claude Code supports two authentication methods for Claude Platform on AWS. Choose the method that fits how your team manages access:
+7 −4 lines
Upstream edited 8 Oct 2026 02:40 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
amazon-bedrock
±changed
+38−13
claude-codechanged
amazon-bedrock
Claude Code uses the default AWS SDK credential chain. Set up your credentials using one of these methods:
**Option A: AWS CLI configuration**
Claude Code uses the default AWS SDK credential chain. If the machine already supplies credentials to that chain, such as an Amazon EC2 instance profile or Amazon ECS task credenti
+38 −13 lines
Upstream edited 8 Oct 2026 02:40 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/cli-reference
±changed
+25−6
claude-codechanged
plugins/cli-reference
Install a plugin from a marketplace you've added. `i` is an alias for `install`.
Install a plugin from one of your marketplaces. `i` is an alias for `install`.
#### JSON result for marketplace commands
+25 −6 lines
Upstream edited 8 Oct 2026 02:24 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
memory
±changed
+3−1
claude-codechanged
memory
Claude Code treats a symlink whose target is outside your working directory like an [external import](#import-additional-files). The linked rules don't load until you approve exter
Claude Code treats a symlink whose target is outside your working directory like an [external import](#import-additional-files). The linked rules don't load until you approve exter
Claude Code asks for that approval once per project, in a dialog at the start of an interactive session. The dialog lists the linked rule files alongside any external `@path` impor
+3 −1 lines
Upstream edited 8 Oct 2026 02:21 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
skills
±changed
+13−0
claude-codechanged
skills
### Check your setup with `/doctor`
Run `/doctor` at the Claude Code prompt for a setup checkup that diagnoses issues and can fix them. Claude reports its findings first and asks for confirmation before changing anyt
+13 −0 lines
Upstream edited 8 Oct 2026 02:21 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
sandboxing
±changed
+1−1
claude-codechanged
sandboxing
* **Sandboxing** provides OS-level enforcement that restricts what shell commands can access at the filesystem and network level. It applies only to Bash, PowerShell, and [Monitor]
* **Sandboxing** provides OS-level enforcement that restricts what shell commands can access at the filesystem and network level. It applies to Bash, PowerShell, and [Monitor](/doc
+1 −1 lines
Upstream edited 8 Oct 2026 02:20 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
sandbox-environments
±changed
+3−3
claude-codechanged
sandbox-environments
| [Sandboxed Bash tool](#sandboxed-bash-tool) | Bash, PowerShell, and Monitor commands and their child processes | No | Minimal on macOS; low on Linux and WSL2 |
| [Sandboxed Bash tool](#sandboxed-bash-tool) | Bash, PowerShell, and Monitor tool commands and their child processes | No | Minimal on macOS; low on Linux and WSL2 |
The sandboxed Bash tool is built into Claude Code. It uses operating system primitives to restrict the filesystem and network access of every Bash, PowerShell, or Monitor command C
The sandboxed Bash tool is built into Claude Code. It uses operating system primitives to restrict the filesystem and network access of Bash, PowerShell, and Monitor tool commands
* [MCP](/docs/en/mcp) servers and [command hooks](/docs/en/hooks#command-hook-fields) are separate processes that run unconstrained on the host.
+3 −3 lines
Upstream edited 8 Oct 2026 02:20 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/security
±changed
+2−1
claude-codechanged
plugins/security
* **Monitors**: a plugin's [monitors](/docs/en/plugins/components#monitors) run as background shell commands that Claude Code starts on its own when the session starts, when you re
* **Hooks and server processes**: command hooks execute shell commands with your full user permissions. Claude Code runs hooks, MCP servers, and the processes a [mod](/docs/en/plug
* **Hooks, monitors, and server processes**: command hooks and monitors are shell commands that run with your full user permissions. Claude Code runs hooks, monitors, MCP servers,
+2 −1 lines
Upstream edited 8 Oct 2026 02:20 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/components
±changed
+1−1
claude-codechanged
plugins/components
The command runs in a shell, in the working directory the session started in.
The command runs in a shell, in the session's current working directory. It runs with your full user permissions and outside the [sandbox](/docs/en/sandboxing).
+1 −1 lines
Upstream edited 8 Oct 2026 02:20 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
permissions
±changed
+1−1
claude-codechanged
permissions
* **Sandboxing** provides OS-level enforcement that restricts shell commands' filesystem and network access. It applies only to Bash, PowerShell, and [Monitor](/docs/en/tools-refer
* **Sandboxing** provides OS-level enforcement that restricts shell commands' filesystem and network access. It applies to Bash, PowerShell, and [Monitor](/docs/en/tools-reference#
+1 −1 lines
Upstream edited 8 Oct 2026 02:20 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugin-evals
±changed
+25−4
claude-codechanged
plugin-evals
* **`type: agent`**: set `type: agent` to have the judge model answer as the server from instructions in the body.
* **`type: agent`**: set `type: agent` to have the judge model answer as the server from instructions in the body. Calls to agent mocks share one [budget per run](#mock-call-budget
| `cases[].arms.with[].aborted` | Present when a [mock](#mock-mcp-servers)'s `expect:` or `abort_when` stopped the run, with `server`, `tool`, and `reason`. The run scores 0 and `e
| `cases[].arms.with[].aborted` | Present when a [mock](#mock-mcp-servers) stopped the run through `expect:`, `abort_when`, or the [agent-mock call budget](#mock-call-budget-exceed
| `expect` | unset | A map from dotted input paths to a type name such as `string`, `number`, `boolean`, `array`, or `object`, a `/regex/`, a literal, or a list of allowed literals
+25 −4 lines
Upstream edited 8 Oct 2026 02:20 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
network-config
±changed
+1−1
claude-codechanged
network-config
| Byte-level watchdog | No bytes arrive on the wire, including SSE keep-alive pings | Direct Anthropic API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and [gateway]
| Byte-level watchdog | No bytes arrive on the wire, including SSE keep-alive pings | Direct Anthropic API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and [gateway]
+1 −1 lines
Upstream edited 8 Oct 2026 02:16 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/marketplace-reference
±changed
+3−1
claude-codechanged
plugins/marketplace-reference
| `plugins.i.source: Invalid string: must start with "./"` | Error | A relative-path `source` without the leading `./`. Before v2.1.285, this mistake printed `Invalid input` instea
* A relative path that doesn't start with `./`, other than `"."` or a [bare name under `metadata.pluginRoot`](#relative-path-plugin-source)
A relative path that doesn't start with `./`, other than `"."` or a [bare name under `metadata.pluginRoot`](#relative-path-plugin-source), fails with `Invalid string: must start wi
+3 −1 lines
Upstream edited 8 Oct 2026 02:16 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
model-config
±changed
+5−4
claude-codechanged
model-config
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
When Claude Code switches your session to the fallback model, it keeps the effort level the flagged request ran at. For example, a session on Opus 5.5 at its default `medium` that
* **Settings or organization default**: a level in your settings that applies to the fallback model, or a default effort your organization set for it, applies instead.
The session header shows the level in effect next to the model name. To change it, run `/effort` in the session.
In the session, run `/effort status` to see the level in effect, or `/effort` to change it.
+5 −4 lines
Upstream edited 8 Oct 2026 02:12 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/org
±changed
+30−32
claude-codechanged
plugins/org
<Note>
These cases are covered on other pages:
* **Installing plugins for yourself**: start at [Install plugins](/docs/en/plugins/install)
* **Controlling which plugins members can use in claude.ai and Cowork**: see [Manage plugins for your organization](https://claude.com/docs/plugins/admin) on claude.com
+30 −32 lines
Upstream edited 8 Oct 2026 02:11 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/org
±changed
+1−1
claude-codechanged
plugins/org
| [`allowManagedModsOnly`](/docs/en/plugins/mods/admin#stop-user-installed-mods-from-loading) | Stops every installed [mod](/docs/en/plugins/mods/overview) that doesn't [count as y
| [`allowManagedModsOnly`](/docs/en/plugins/mods/admin#stop-user-installed-mods-from-loading) | Stops every installed [mod](/docs/en/plugins/mods/overview) that doesn't [count as y
+1 −1 lines
Upstream edited 8 Oct 2026 02:11 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/mods/troubleshoot
±changed
+2−2
claude-codechanged
plugins/mods/troubleshoot
An organization can also set `allowManagedModsOnly` to allow only its own mods, which this command doesn't report. In that case a mod you install doesn't load, and [a message says
An organization can also set `allowManagedModsOnly` to allow only its own mods, which this command doesn't report. In that case Claude Code refuses a mod you install, and [a messag
| `mods are limited to your organization's by policy (allowManagedModsOnly)` | Your organization allows only [its own mods](/docs/en/plugins/mods/admin#install-your-organizations-m
| `mods are limited to your organization's by policy (allowManagedModsOnly)` | Your organization allows only [its own mods](/docs/en/plugins/mods/admin#install-your-organizations-m
+2 −2 lines
Upstream edited 8 Oct 2026 02:11 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/mods/reference
±changed
+1−1
claude-codechanged
plugins/mods/reference
| `allowManagedModsOnly` | Managed settings, as an [option on the built-in guard](/docs/en/plugins/mods/admin#set-options-on-the-built-in-guard) | Only mods that [count as your org
| `allowManagedModsOnly` | Managed settings, as an [option on the built-in guard](/docs/en/plugins/mods/admin#set-options-on-the-built-in-guard) | Only mods that [count as your org
+1 −1 lines
Upstream edited 8 Oct 2026 02:11 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
plugins/mods/admin
±changed
+10−10
claude-codechanged
plugins/mods/admin
To keep every mod your users bring from loading, set the `allowManagedModsOnly` option on the [built-in guard](#know-what-happens-by-default), a policy mod that Claude Code loads a
To keep every mod your users bring from running its hooks, set the `allowManagedModsOnly` option on the [built-in guard](#know-what-happens-by-default), a policy mod that Claude Co
* **No mod a user brings loads**: that covers a mod in a plugin the user installed, a mod loaded with `--plugin-dir`, and a mod [Claude wrote during a session](/docs/en/plugins/mod
* **Your organization's mods still load**: a mod that [counts as your organization's](#install-your-organizations-mods) isn't checked. Every other mod counts as a user's and doesn'
* **No mod a user brings runs its hooks**: that covers a mod in a plugin the user installed, a mod loaded with `--plugin-dir`, and a mod [Claude wrote during a session](/docs/en/pl
+10 −10 lines
Upstream edited 8 Oct 2026 02:11 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
desktop
±changed
+31−2
claude-codechanged
desktop
### Accept a suggested prompt
After Claude replies, the Code tab can show a suggested next prompt as gray text in the empty prompt box. Claude Code [generates each suggestion](/docs/en/interactive-mode#prompt-s
* **Use the suggestion**: press **Tab** or **Right arrow** to place it in the prompt box, edit it if you want, then press **Enter** to send it. Pressing **Enter** before you accept
+31 −2 lines
Upstream edited 8 Oct 2026 02:10 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
sub-agents
±changed
+2−0
claude-codechanged
sub-agents
If an installed [mod](/docs/en/plugins/mods/overview) sets a model in its [`agent.spawn`](/docs/en/plugins/mods/reference#subagents) hook, Claude Code uses that model in place of t
+2 −0 lines
Upstream edited 8 Oct 2026 02:10 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
agent-teams
±changed
+2−0
claude-codechanged
agent-teams
If an installed [mod](/docs/en/plugins/mods/overview) sets a model in its [`agent.spawn`](/docs/en/plugins/mods/reference#subagents) hook, Claude Code uses that model in place of t
+2 −0 lines
Upstream edited 8 Oct 2026 02:10 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
remote-control
±changed
+3−3
claude-codechanged
remote-control
The same toggle appears outside the CLI:
* **Desktop app**: **Settings > Claude Code > Connect new sessions to Remote Control**.
The VS Code extension and the Desktop app also have an auto-connect toggle:
+3 −3 lines
Upstream edited 8 Oct 2026 02:09 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
tools-reference
±changed
+3−3
claude-codechanged
tools-reference
A session can make at most 200 WebSearch calls, counted across the main conversation and every [subagent](/docs/en/sub-agents) it spawns, so searches made by parallel research fan-
Set the [`CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION`](/docs/en/env-vars) environment variable to change the cap; it accepts a positive whole number, so the cap can be raised but not
An interactive terminal session can make 200 WebSearch calls, counted across the main conversation and every [subagent](/docs/en/sub-agents) it spawns, so searches made by parallel
+3 −3 lines
Upstream edited 8 Oct 2026 02:07 UTC Recorded here 8 Oct 2026 03:07 UTC
claude-code
agent-view
±changed
+4−3
claude-codechanged
agent-view
* A session that's working: the reply joins the session's [message queue](/docs/en/interactive-mode#queue-messages-while-claude-works) instead of interrupting the response, and tak
* A session that's working: `/model`, `/effort`, `/rename`, and `/usage` run right away. Other replies join the session's [message queue](/docs/en/interactive-mode#queue-messages-w
* A permission prompt or another dialog, such as a [sandbox](/docs/en/sandboxing) prompt or an MCP server's [request for input](/docs/en/mcp#respond-to-mcp-elicitation-requests): r
* A permission prompt or another dialog, such as a [sandbox](/docs/en/sandboxing) prompt or an MCP server's [request for input](/docs/en/mcp#respond-to-mcp-elicitation-requests): r
* **Working, paused on a permission prompt or other dialog, or attached**: the process keeps running. A running subagent, workflow, or monitor counts as working.
+4 −3 lines
Upstream edited 8 Oct 2026 02:05 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
| `content-type` | Return `text/event-stream` on streamed Anthropic Messages-format responses, and `application/vnd.amazon.eventstream`, unmodified, on Amazon Bedrock-format respon
| `content-type` | Return `text/event-stream` on streamed Anthropic Messages-format responses, and `application/vnd.amazon.eventstream`, unmodified, on Amazon Bedrock-format respon
+1 −1 lines
Upstream edited 8 Oct 2026 02:03 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
mcp
±changed
+0−4
claude-codechanged
mcp
<Warning>
If you frequently encounter output warnings with specific MCP servers you don't control, consider increasing the `MAX_MCP_OUTPUT_TOKENS` limit. You can also ask the server author
</Warning>
+0 −4 lines
Upstream edited 8 Oct 2026 02:02 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
desktop
±changed
+0−1
claude-codechanged
desktop
a-cdn.claude.ai
+0 −1 lines
Upstream edited 8 Oct 2026 02:02 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
common-workflows
±changed
+1−1
claude-codechanged
common-workflows
This includes the full content of the file in the conversation.
This includes the content of the file in the conversation when it fits the [Read tool](/docs/en/tools-reference#read-tool-behavior)'s token limit, 25,000 tokens by default. A t
+1 −1 lines
Upstream edited 8 Oct 2026 02:02 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
keybindings
±changed
+45−0
claude-codechanged
keybindings
| `AbovePrompt` | The [band above the prompt](#above-prompt-actions), or a button in it, has keyboard focus |
| `AbovePromptInput` | An input field in the band above the prompt or in a mod's pane has keyboard focus |
| `AbovePromptSelect` | A select in the band above the prompt or in a mod's pane has keyboard focus |
### Above-prompt actions
+45 −0 lines
Upstream edited 8 Oct 2026 01:58 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
corporate-launcher
±changed
+1−0
claude-codechanged
corporate-launcher
* **Don't depend on how arguments are spelled.** A flag's value can arrive as its own argument, `--flag value`, or joined to the flag, `--flag=value`. Which form a flag uses can ch
+1 −0 lines
Upstream edited 8 Oct 2026 01:56 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
vs-code
±changed
+1−0
claude-codechanged
vs-code
* **Queued messages**: when you send a message while Claude is working, the extension announces "Message queued." for that message.
+1 −0 lines
Upstream edited 8 Oct 2026 01:56 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
plugins/mods/reference
±changed
+2−2
claude-codechanged
plugins/mods/reference
| `Code` | The code | ✓ | ✓ |
| [`Code`](/docs/en/plugins/mods/gallery#show-code-and-changes) | `source`, `language`, `path`, `startLine`, `format`, `wrap` | ✓ | ✓ |
| `Image` | PNG or RGBA bytes up to 2 MiB, or a file path | ✓ | |
| `Image` | PNG or RGBA bytes up to 2 MiB, or a file path, `columns` and `rows` up to 255, and `alt` text. | ✓ | |
+2 −2 lines
Upstream edited 8 Oct 2026 01:56 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
github-actions
±changed
+24−24
claude-codechanged
github-actions
* [Code Review](/docs/en/code-review): automatic review on every pull request, without writing a workflow
* [Claude Code in the cloud](/docs/en/claude-code-on-the-web): Claude Code sessions that run on cloud infrastructure instead of your machine
* [Claude Agent SDK](/docs/en/agent-sdk/overview): custom automation outside GitHub Actions. The Claude Code GitHub Action is built on the SDK
* [GitHub Enterprise Server](/docs/en/github-enterprise-server): Claude Code with self-hosted GitHub
* [Code Review](/docs/en/code-review.md): automatic review on every pull request, without writing a workflow
+24 −24 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
github-actions
±changed
+33−35
claude-codechanged
github-actions
<Note>
* When you install the GitHub App, you grant it several permissions. See [GitHub App permissions](#github-app-permissions) for the full set
* Quick setup works with the Claude API and Claude subscriptions. If you use Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, see [Use Claude Code GitHub Acti
</Note>
> [!NOTE]
+33 −35 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
setup
±changed
+1−1
claude-codechanged
setup
When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or i
The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation
+1 −1 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
quickstart
±changed
+1−1
claude-codechanged
quickstart
When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or i
The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation
+1 −1 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
overview
±changed
+1−1
claude-codechanged
overview
When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found
The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installa
+1 −1 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
github-actions
±changed
+2−0
claude-codechanged
github-actions
| Administration | Read |
| Merge queues | Read |
+2 −0 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
plugins/mods/api
±changed
+5−0
claude-codechanged
plugins/mods/api
A mod can refuse your `$.process.spawn` call after the command has produced output or exited, and nothing the command did is undone. The call then rejects with a message that ends
* **`$.process.spawn started, and a plugin withheld its result:`**: the refusing mod hadn't read the command's output to the end. Claude Code stops the command if it's still runnin
* **`$.process.spawn ran, and a plugin withheld its result:`**: the refusing mod had read the command's output to the end, so the command had exited
+5 −0 lines
Upstream edited 8 Oct 2026 01:49 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
WebSearch is available on the Claude API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws). On Microsoft Foundry it requires a [deployment hosted on Anthropic](https:
WebSearch is available on the Claude API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and Microsoft Foundry. On Google Cloud's Agent Platform it works with Claude
+1 −1 lines
Upstream edited 8 Oct 2026 01:47 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
feature-availability
±changed
+1−2
claude-codechanged
feature-availability
<td>✓ ([deployments hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options))</td>
<td>✓</td>
* [Web search](/docs/en/tools-reference#websearch-tool-behavior): [deployments hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-fo
+1 −2 lines
Upstream edited 8 Oct 2026 01:47 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
plugins/mods/gallery
±changed
+8−0
claude-codechanged
plugins/mods/gallery
Unless Claude Code detects that the terminal draws kitty graphics protocol images with Unicode placeholders, the user sees an `Image`'s `alt` text, dimmed, in place of the picture.
* **Other terminals**: any terminal that isn't one of those two, or that doesn't answer the query.
* **tmux and screen**: a session running inside tmux or screen, in any terminal, kitty and Ghostty included.
* **Background sessions**: every [background session](/docs/en/agent-view), whatever terminal it's attached from.
+8 −0 lines
Upstream edited 8 Oct 2026 01:46 UTC Recorded here 8 Oct 2026 02:07 UTC
7 Oct 2026
75 pages
+1335 −1064 lines
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 7 Oct 2026 23:37 UTC
claude-code
mcp
±changed
+2−4
claude-codechanged
mcp
WebSocket servers don't appear in `claude mcp list` output. Use `claude mcp get <name>` or the `/mcp` panel to check them.
* Asks HTTP servers whether they support the newer revision, and uses it with those that do. In sessions where it fetches feature flags, it also asks claude.ai connector servers, a
* Asks HTTP and stdio servers whether they support the newer revision, and uses it with those that do. In sessions where it fetches feature flags, it also asks claude.ai connector
Claude Code asks stdio servers for that revision when you set [`MCP_PROTOCOL_NEGOTIATION`](/docs/en/env-vars) to `auto`. Anthropic is also turning that on by default, for Claude Co
+2 −4 lines
Upstream edited 7 Oct 2026 23:27 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
settings-reference
±changed
+13−4
claude-codechanged
settings-reference
Choose where Claude Code stores the plan files it writes in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode). Claude Code resolves the path relative to
Choose where Claude Code stores the plan files it writes in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode). Claude Code resolves the path relative to
Claude Code stores plans in `~/.claude/plans` instead of the directory you set in cases such as these:
+13 −4 lines
Upstream edited 7 Oct 2026 23:26 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
desktop
±changed
+10−4
claude-codechanged
desktop
Administrators can distribute SSH connections to team members by adding `sshConfigs` to a [managed settings](/docs/en/managed-settings) file. Connections defined this way appear in
Administrators can distribute SSH connections to team members by setting `sshConfigs` in [managed settings](/docs/en/managed-settings). Connections defined this way appear in each
Administrators can limit Desktop's SSH sessions to an approved set of hosts by adding `sshHostAllowlist` to a [managed settings](/docs/en/managed-settings) file. When set, users ca
Administrators can limit Desktop's SSH sessions to an approved set of hosts by setting `sshHostAllowlist` in [managed settings](/docs/en/managed-settings). When set, users can only
+10 −4 lines
Upstream edited 7 Oct 2026 23:26 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/create
±changed
+1−1
claude-codechanged
plugins/mods/create
The `hooks:` line lists the events your module hooks, each with its filter in braces. The `calls:` line lists every mods API method it calls. A module that reads or sets environmen
Check the `hooks:` line for the events your module hooks, each with its filter in braces, and `calls:` for every mods API method it calls. If your module reads or sets environment
+1 −1 lines
Upstream edited 7 Oct 2026 23:24 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/admin
±changed
+1−1
claude-codechanged
plugins/mods/admin
Two lines in the output describe the mod's code:
The `hooks:` and `calls:` lines in the output describe the mod's code:
+1 −1 lines
Upstream edited 7 Oct 2026 23:24 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/cli-reference
±changed
+1−0
claude-codechanged
plugins/cli-reference
* `gatingHooks`: whether each [mod](/docs/en/plugins/mods/overview) hook that can refuse an action, such as a `tool.call` hook, has a [`.catch` handler](/docs/en/plugins/mods/eve
+1 −0 lines
Upstream edited 7 Oct 2026 23:24 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/test
±changed
+3−1
claude-codechanged
plugins/mods/test
* `returned neither { value } nor { deny }`: a stub for a mods API call returned a bare value
* `returned neither { value } nor { deny }`: a stub for a mods API call returned a bare value, which fails the test
When an `expect` fails inside a stub or hook that you passed to `on` as a plain function rather than an async generator, the test fails. The engine skips that hook, and the failure
+3 −1 lines
Upstream edited 7 Oct 2026 23:23 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/interface
±changed
+1−0
claude-codechanged
plugins/mods/interface
* **Hold the result of each `atom` call in a `const`**: if you declare `count` with `let`, validation fails with `takes a source the scan can read`
+1 −0 lines
Upstream edited 7 Oct 2026 23:23 UTC Recorded here 7 Oct 2026 23:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.