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
145 changed this week · last read 22 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
ReadSourcePageWhatLines
18 Aug 2026
88 pages
+1389 −1084 lines
claude-code
amazon-bedrock
±changed
+1−1
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
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
+1 −1 lines
Recorded here 18 Aug 2026 15:07 UTC
claude-code
agent-teams
±changed
+1−1
claude-codechanged
agent-teams
* **No background subagents from in-process teammates**: an in-process teammate's own subagents run in the foreground. Asking for a background one, whether with `run_in_background`
* **No background subagents from in-process teammates**: an in-process teammate's own subagents run in the foreground, because a teammate's background work can't outlive the lead's
+1 −1 lines
Recorded here 18 Aug 2026 15:07 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+5−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v1.32352.1" description="2026-08-18">
No configuration changes in this release.
</Update>
* **Breaking:** Managed-config URL settings now reject values that embed credentials (`https://user:password@host…`). Configurations that relied on this fail to load until the cr
+5 −0 lines
Recorded here 18 Aug 2026 05:07 UTC
claude-docs
cowork/changelog
±changed
+19−0
claude-docschanged
cowork/changelog
<Update label="v1.32352.1" description="2026-08-18">
**General**
* Fixed a rare Windows startup failure where the first window could fail to initialize on a fresh install.
+19 −0 lines
Recorded here 18 Aug 2026 05:07 UTC
claude-code
settings
±changed
+1−1
claude-codechanged
settings
| `advisorModel` | Model for the server-side [advisor tool](/docs/en/advisor). Accepts the model aliases `"fable"`, `"opus"`, and `"sonnet"`, or a full model ID
| `advisorModel` | Model for the server-side [advisor tool](/docs/en/advisor). Accepts the model aliases `"fable"`, `"opus"`, and `"sonnet"`, or a full model ID
+1 −1 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
sandboxing
±changed
+1−0
claude-codechanged
sandboxing
* **Corporate proxy**: when your network requires outbound traffic to go through a corporate proxy, set `HTTPS_PROXY`, `HTTP_PROXY`, and `NO_PROXY` as [proxy configuration](/docs/e
+1 −0 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
permission-modes
±changed
+2−2
claude-codechanged
permission-modes
* In the interactive CLI, a deny is dropped when the turn ends
* In [non-interactive mode](/docs/en/headless) and Agent SDK sessions there is no turn boundary, so a deny is reused for the rest of the run
* Claude Code v2.1.234 and later reuse a deny caused by the conversation outgrowing the classifier's context window until new content enters the conversation, or until [compaction]
* A deny that the classifier reached by evaluating the request lasts for the turn in the interactive CLI. In [non-interactive mode](/docs/en/headless) and Agent SDK sessions, Claud
+2 −2 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
* **`--advisor` flag**: Claude Code exits with an error at launch
* **`--advisor` flag**: Claude Code exits with an error at launch. In a [background session](/docs/en/agent-view), it starts the session without the advisor instead of exiting
+1 −1 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
errors
±changed
+22−0
claude-codechanged
errors
| `signed-in claude.ai account or organization changed on this machine`
<h3 id="remote-control-stopped-because-the-signed-in-account-changed">
Remote Control stopped because the signed-in account changed
</h3>
+22 −0 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
env-vars
±changed
+1−0
claude-codechanged
env-vars
| `CLAUDE_AX_PREPARK_MS` | In [screen reader mode](/docs/en/accessibility#what-your-screen-reader-hears), how many milliseconds Claude Code waits,
+1 −0 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
desktop
±changed
+2−1
claude-codechanged
desktop
Claude Code applies three safety behaviors across sessions:
Claude Code applies four safety behaviors across sessions:
* Claude Code checks each message from this surface against the receiving session's [inbound controls](/docs/en/cross-session-messaging#control-inbound-messages). If you set [`cros
+2 −1 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
channels-reference
±changed
+23−7
claude-codechanged
channels-reference
| Field | Type | Description
| :------------------------------------------------------- | :------- | :-----------------------------------------------------------------------------------------------------------
| `capabilities.experimental['claude/channel']` | `object` | Required. Always `{}`. Presence registers the notification listener.
| `capabilities.experimental['claude/channel/permission']` | `object` | Optional. Always `{}`. Declares that this channel can receive permission relay requests. When declared, Clau
| `capabilities.tools` | `object` | Two-way only. Always `{}`. Standard MCP tool capability. See [Expose a reply tool](#expose-a-reply-tool).
+23 −7 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
advisor
±changed
+27−5
claude-codechanged
advisor
If any of these sets an advisor model, the advisor is enabled for sessions whose main model [supports it](#choose-an-advisor-model), and an `Advisor Tool (experimental) is on and m
Each of these enables the advisor for sessions whose main model [supports it](#choose-an-advisor-model). After the session starts, Claude Code shows an `Advisor Tool (experimental)
On some plans, Fable as the advisor also needs your one-time [consent to bill Fable 5 usage to usage credits](/docs/en/model-config#fable-5-and-usage-credits). For what happens bef
If your organization's [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist excludes the saved advisor model, the advisor is not invoked until you pick an
+27 −5 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-code
accessibility
±changed
+48−52
claude-codechanged
accessibility
Claude Code has a screen reader mode that replaces its visual terminal interface with plain, linear text. Instead of boxes, progress animations, and in-place redraws, the mode prin
Claude Code has a screen reader mode that replaces its visual terminal interface with plain, linear text. Instead of boxes, progress animations, and in-place redraws, Claude Code p
Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, see [Accessibility settings beyond screen re
Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersRed
<Note>
+48 −52 lines
Recorded here 18 Aug 2026 03:07 UTC
claude-docs
government/tenant-admin/identity-and-access
±changed
+1−1
claude-docschanged
government/tenant-admin/identity-and-access
Every user signs in through your agency's identity provider (for example, Microsoft Entra, Okta, or ADFS). You register Claude for Government as an application in your identity pro
Every user signs in through your agency's identity provider (for example, Microsoft Entra, Okta, or ADFS). You register Claude for Government as an application in your identity pro
+1 −1 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
vs-code
±changed
+27−23
claude-codechanged
vs-code
When Claude wants to edit a file, it shows a side-by-side comparison of the original and proposed changes, then asks for permission. You can accept, reject, or tell Claude what
<img src="https://mintcdn.com/claude-code/FVYz38sRY-VuoGHA/images/vs-code-edits.png?fit=max&auto=format&n=FVYz38sRY-VuoGHA&q=85&s=e005f9b41c541c5c7c59c082f7c4841c" alt="VS Code
What you see depends on the [permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) shown at the bottom of the prompt box:
+27 −23 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
troubleshooting
±changed
+1−0
claude-codechanged
troubleshooting
| Session started in auto mode, or Claude edits files and runs commands without asking | [Which mode a session start
+1 −0 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
security
±changed
+12−8
claude-codechanged
security
Claude Code uses strict read-only permissions by default. When additional actions are needed (editing files, running tests, executing commands), Claude Code requests explicit permi
In Manual mode, Claude Code starts with read-only permissions. When Claude Code needs to edit files, run tests, or execute commands, it asks you first, and you choose whether to ap
Claude Code requires approval before running Bash commands that can modify your system. A built-in set of [read-only commands](/docs/en/permissions#read-only-commands) such as `ls`
In Manual mode, Claude Code also asks before running Bash commands that can modify your system. It runs a built-in set of [read-only commands](/docs/en/permissions#read-only-comman
+12 −8 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
quickstart
±changed
+9−12
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}
+9 −12 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
how-claude-code-works
±changed
+5−5
claude-codechanged
how-claude-code-works
Checkpoints are separate from git and remain available when you resume a conversation. They only cover file changes, and a restore [skips symlinked and hard-linked files](/docs/en/
Checkpoints are separate from git and remain available when you resume a conversation. They only cover file changes, and a restore [skips symlinked and hard-linked files](/docs/en/
Press `Shift+Tab` to cycle through permission modes:
Choose a permission mode to set what Claude can do without asking you. Press `Shift+Tab` to cycle through the permission modes:
+5 −5 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
headless
±changed
+5−3
claude-codechanged
headless
To set a baseline for the whole session instead of listing individual tools, pass a [permission mode](/docs/en/permission-modes). `dontAsk` denies anything not in your `permissions
`acceptEdits` lets Claude write files without prompting and also auto-approves common filesystem commands such as `mkdir`, `touch`, `mv`, and `cp`. The [actions no mode auto-approv
To set a baseline for the whole session instead of listing individual tools, pass a [permission mode](/docs/en/permission-modes). For `-p`, the [built-in starting permission mode](
+5 −3 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A [permission mode](#permission-mode) where a separate classifier model reviews actions in the background, so most run without approval prompts; explicit ask rules still prompt. Th
A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks
+1 −1 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
feature-availability
±changed
+1−1
claude-codechanged
feature-availability
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and Fa
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and Fa
+1 −1 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--permission-mode` | Begin in a specified [permission mode](/docs/en/permission-modes). Accepts `default`, `acceptEdits`, `plan`, `auto`, `dontAsk`,
| `--permission-mode` | Begin in a specified [permission mode](/docs/en/permission-modes). Accepts `default`, `acceptEdits`, `plan`, `auto`, `dontAsk`,
+1 −1 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
best-practices
±changed
+9−8
claude-codechanged
best-practices
```txt title="claude (default mode)" wrap theme={null}
```txt title="claude" wrap theme={null}
```txt title="claude (default mode)" wrap theme={null}
```txt title="claude" wrap theme={null}
Use [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) to let a classifier handle approvals, `/permissions` to allowlist specific commands, or `/sandbox` for
+9 −8 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
agent-view
±changed
+22−8
claude-codechanged
agent-view
Type a prompt describing a task and press `Enter`. A new background session starts on that task and appears as a row showing whether it's working, waiting on you, or done. The
Type a prompt describing a task and press `Enter`. A new background session starts on that task and appears as a row showing whether it's working, waiting on you, or done. The
A background session takes its settings, provider, permission mode, model, and effort from where and how you dispatched it. The subsections below cover each source, and what persis
#### Settings and provider
+22 −8 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-code
admin-setup
±changed
+1−0
claude-codechanged
admin-setup
| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of th
+1 −0 lines
Recorded here 18 Aug 2026 02:37 UTC
claude-docs
claude-tag/users/when-claude-responds
±changed
+26−15
claude-docschanged
claude-tag/users/when-claude-responds
> Claude Tag replies to DMs, threads it's already in, and channel messages it judges warrant a reply, all without an @-mention. See what triggers a response, how to tell an unpromp
> What Claude Tag does with a channel message nobody tagged it in, and how to turn unprompted replies off for a thread or a channel. Read this if Claude is replying too much, or we
Claude replies without an @-mention in DMs, in any thread it's already part of, and to channel messages it judges warrant a reply. It's an ambient presence in the channel, and the
Claude replies without an @-mention in DMs, in any thread it's already part of, and to channel messages it judges warrant a reply. In a channel, Claude reads the messages and repli
Where you send the message decides whether you need the mention.
+26 −15 lines
Recorded here 18 Aug 2026 02:07 UTC
claude-docs
claude-tag/users/prompt-library
±changed
+1−1
claude-docschanged
claude-tag/users/prompt-library
**Why it works**: Claude already [picks up untagged posts when it judges a reply is warranted](/docs/claude-tag/users/when-claude-responds), and it weighs this channel-memory rule
**Why it works**: Claude already [picks up untagged posts when it judges a reply is warranted](/docs/claude-tag/users/when-claude-responds), and it weighs this channel-memory rule
+1 −1 lines
Recorded here 18 Aug 2026 02:07 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+1−1
claude-docschanged
claude-tag/admins/troubleshooting
| "Claude Code Remote is temporarily degraded. Try again shortly." | The service that runs sessions is briefly unavailable; retry
| "Claude is having trouble starting sessions right now. Try again in a minute." | The service that runs sessions is briefly unavailable; retry
+1 −1 lines
Recorded here 18 Aug 2026 02:07 UTC
claude-docs
claude-tag/admins/set-spend-limit
±changed
+5−4
claude-docschanged
claude-tag/admins/set-spend-limit
| Work | Bills to | Capped by |
| :--------------- | :-------------------------------- | :-------------------------------------------------------------------------------------------------- |
| Channel work | Your organization's usage balance | The spend limit, plus any [per-channel limits](/docs/claude-tag/admins/restrict-access#set-spend-limits) |
| A DM with Claude | The sender's own seat | The seat's usual limits, not the spend limit |
| Work |
+5 −4 lines
Recorded here 18 Aug 2026 02:07 UTC
claude-docs
government/tenant-admin/readiness
±changed
+1−1
claude-docschanged
government/tenant-admin/readiness
* **Configure the seat pool** checks that at least one billing account has a seat pool set. This is also advisory. Without a pool, seat allocations on the [Seats](/docs/government/
* **Configure the seat pool** checks that at least one billing account has a seat pool set. This is also advisory. Until a pool is set, the [Seats](/docs/government/tenant-admin/se
+1 −1 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-docs
government/org-admin/compliance-api
±changed
+1−1
claude-docschanged
government/org-admin/compliance-api
* **Credentials** such as `api_key.created`, `scim_token.created`, and `scim_token.revoked`.
* **Credentials** such as `api_key.created` and `api_key.revoked`.
+1 −1 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-docs
government/org-admin/analytics
±changed
+1−1
claude-docschanged
government/org-admin/analytics
When credit data is available, the credit panel shows the current position of the account your organization draws from as of right now. It displays the **Credits remaining** out of
When credit data is available, the credit panel shows the current position of the account your organization draws from as of right now. It displays the **Credits remaining** out of
+1 −1 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-docs
government/config/plugins-and-connectors
±changed
+1−1
claude-docschanged
government/config/plugins-and-connectors
A package is marked **Runs code** when it declares components that can run code on members' machines. That means any file under `hooks/` or `monitors/`, a `.mcp.json` at the root,
A package is marked **Runs code** when it declares components that can run code on members' machines. That means any file under `hooks/` or `monitors/`, a `.mcp.json` at the root,
+1 −1 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-code
settings
±changed
+2−0
claude-codechanged
settings
| `ripgrep` | Custom `ripgrep` binary for the sandbox. Set `command` to the binary's path. To pass arguments to that binary, also set `args`. If you
* The sandbox `ripgrep` binary, [`sandbox.ripgrep`](#sandbox-settings)
+2 −0 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-code
server-managed-settings
±changed
+1−0
claude-codechanged
server-managed-settings
* **Sandbox binary settings**: `sandbox.bwrapPath`, `sandbox.socatPath`, and `sandbox.ripgrep`. Each of these settings points at an executable, and Claude Code runs that executable
+1 −0 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-code
interactive-mode
±changed
+21−2
claude-codechanged
interactive-mode
| `Up/Down arrows` or `Ctrl+P`/`Ctrl+N` | Move cursor or navigate command history
| `Esc` | Interrupt Claude, or close a dialog
| `Up/Down arrows` or `Ctrl+P`/`Ctrl+N` | Move cursor or navigate command history
| `Esc` | Interrupt Claude, or close a dialog
## Queue messages while Claude works
+21 −2 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-code
how-claude-code-works
±changed
+1−1
claude-codechanged
how-claude-code-works
* **Press `Esc`** to stop Claude immediately. The running tool call is canceled and Claude waits for your next instruction.
* **Press `Esc`** to stop Claude immediately. The running tool call is canceled and Claude waits for your next instruction. If you have messages queued, Claude Code [sends them nex
+1 −1 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-code
errors
±changed
+16−0
claude-codechanged
errors
| `N sessions ended while this machine was offline — the environment was cleaned up on the server and can't be resumed.`
<h3 id="sessions-ended-while-this-machine-was-offline">
Sessions ended while this machine was offline
</h3>
+16 −0 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-code
claude-apps-gateway-deploy
±changed
+12−7
claude-codechanged
claude-apps-gateway-deploy
| Data | Path | Sent to Anthrop
| ------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ | ---------------
| Inference (prompts, completions) | CLI → gateway → your upstream | Only if the Ant
| Telemetry (OTLP metrics, plus [opt-in logs and traces](/docs/en/claude-apps-gateway-config#telemetry)) | CLI → gateway → your collector | Never
| Identity (email, groups, sub) | IdP → gateway → JWT → CLI; the CLI stamps it on OTLP exports | Never
+12 −7 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-code
claude-apps-gateway-config
±changed
+57−10
claude-codechanged
claude-apps-gateway-config
<a id="per-user-identity-headers-for-a-proxy-you-run" />
##### Per-user identity headers for a proxy you run
+57 −10 lines
Recorded here 18 Aug 2026 01:37 UTC
claude-docs
government/tenant-admin/readiness
±changed
+5−5
claude-docschanged
government/tenant-admin/readiness
* **Configure the seat pool** checks that at least one billing account has a seat pool set. This is also advisory. Until a pool is set, the [Seats](/docs/government/tenant-admin/se
* **Register a domain** is required. Claude for Government routes users to your tenant by the domain of their email address, so until at least one domain is registered nobody can s
* **Set up SCIM provisioning** is optional. SCIM lets your directory push users and groups into Claude for Government automatically. If you plan to use it, generate a provisioning
* **Add a routing rule** is required. Routing rules decide which organization each user joins when they sign in. Until at least one rule points at an active organization, every new
* **Configure the seat pool** checks that at least one billing account has a seat pool set. This is also advisory. Until a pool is set, the [Seats](/docs/government/tenant-admin/se
+5 −5 lines
Upstream edited 18 Aug 2026 01:27 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
worktrees
±changed
+1−1
claude-codechanged
worktrees
* **Permission approvals**: choosing "Yes, don't ask again" for a Bash command in a worktree session saves the rule to the main checkout's `.claude/settings.local.json`, so it appl
* **Permission approvals**: choosing "Yes, and don't ask again" for a Bash command in a worktree session saves the rule to the main checkout's `.claude/settings.local.json`, so it
+1 −1 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
settings
±changed
+1−1
claude-codechanged
settings
| `teammateDefaultModel` | Default model for [agent team](/docs/en/agent-teams) teammates when the spawn prompt doesn't specify one. Set to a model alias such as `"sonnet"`,
| `teammateDefaultModel` | Removed in v2.1.234; Claude Code ignores a leftover value. See [Specify teammates and models](/docs/en/agent-teams#specify-teammates-and-models)
+1 −1 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
sandboxing
±changed
+1−1
claude-codechanged
sandboxing
The sandbox's [auto-allow mode](#sandbox-modes) is separate from [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode): auto-allow approves Bash commands because
The sandbox's [auto-allow mode](#sandbox-modes) is separate from [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode): auto-allow approves Bash commands because
+1 −1 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
permissions
±changed
+12−10
claude-codechanged
permissions
| Tool type | Example | Approval required | "Yes, don't ask again" behavior |
| :---------------- | :--------------- | :---------------------------------------------------------------------------------- | :------------------------------------- |
| Read-only | File reads, Grep | No, within the [working directory and additional directories](#working-directories) | N/A |
| Bash commands | Shell execution | Yes, except a built-in set of [read-only commands](#read-only-commands) | Permanently per repository and command |
| File modification | Edit/write files | Yes | Until session end |
+12 −10 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
permission-modes
±changed
+15−0
claude-codechanged
permission-modes
## Common setups
Permission modes decide whether Claude asks before an action, and the [Bash sandbox](/docs/en/sandboxing) and outer [isolation boundaries](/docs/en/sandbox-environments) decide wha
+15 −0 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
model-config
±changed
+2−2
claude-codechanged
model-config
* **Subagent and teammate models**: the `model` field in [subagent](/docs/en/sub-agents#choose-a-model) frontmatter, the Agent tool's `model` parameter, [agent team](/docs/en/agent
* **Subagent and teammate models**: the `model` field in [subagent](/docs/en/sub-agents#choose-a-model) frontmatter, the Agent tool's `model` parameter, [agent team](/docs/en/agent
* **Subagent or teammate override**: Claude Code falls back to the [subagent's inherited model](/docs/en/sub-agents#choose-a-model) or the [default teammate model](/docs/en/agent-t
* **Subagent or teammate override**: Claude Code falls back to the [subagent's inherited model](/docs/en/sub-agents#choose-a-model) or the [lead's model for a teammate](/docs/en/ag
+2 −2 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
| `SessionEnd` | why the session
| `SessionEnd` | why the session
+1 −1 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
hooks
±changed
+9−9
claude-codechanged
hooks
| `SessionEnd` | why the session ended
| `SessionEnd` | why the session ended
| Reason | Description |
| :---------------------------- | :----------------------------------------- |
| `clear` | Session cleared with `/clear` command |
+9 −9 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
fullscreen
±changed
+19−1
claude-codechanged
fullscreen
The relaunched session keeps the conversation as it appears on screen. Claude Code also carries over the model you last picked with [`/model`](/docs/en/model-config#setting-your-mo
Claude Code carries these into the relaunched session:
* The conversation as it appears on screen. After a [`/rewind`](/docs/en/checkpointing#rewind-and-summarize), that means:
* If you rewound earlier in the session, Claude Code relaunches from the rewound point, not from the longer transcript saved on disk. For example, if you rewound past your last t
+19 −1 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
errors
±changed
+27−1
claude-codechanged
errors
| `Cannot switch renderers in this session`
| `Cannot switch renderers while work is running in the background`
These errors come from the `claude` command line, its subcommands, and commands such as `/security-review` that gather context by running shell commands before their prompt runs.
These errors come from the `claude` command line, its subcommands, and commands such as `/security-review` that gather context by running shell commands before their prompt runs. S
+27 −1 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
agent-teams
±changed
+8−4
claude-codechanged
agent-teams
Teammates don't inherit the lead's `/model` selection by default. To change the model used when the prompt doesn't specify one, set **Default teammate model** in `/config`. Pick **
Claude Code checks each teammate's model, whether requested in your prompt or set through **Default teammate model**, against your organization's [`availableModels`](/docs/en/model
When your prompt doesn't name a model for a teammate, Claude Code runs the teammate on the lead's current model, unless [`CLAUDE_CODE_SUBAGENT_MODEL`](/docs/en/model-config#environ
+8 −4 lines
Recorded here 18 Aug 2026 01:07 UTC
claude-code
skills
±changed
+12−0
claude-codechanged
skills
### Remove a skill
How you remove a skill depends on where it came from:
+12 −0 lines
Recorded here 18 Aug 2026 00:37 UTC
claude-code
settings
±changed
+7−7
claude-codechanged
settings
| Feature | User location | Project location | Local location |
| :-------------- | :------------------------ | :--------------------------------- | :----------------------------- |
| **Settings** | `~/.claude/settings.json` | `.claude/settings.json` | `.claude/settings.local.json` |
| **Subagents** | `~/.claude/agents/` | `.claude/agents/` | None |
| **MCP servers** | `~/.claude.json` | `.mcp.json` | `~/.claude.json` (per-project) |
+7 −7 lines
Recorded here 18 Aug 2026 00:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
Adding a bare tool name like `Bash` or `WebFetch` as a [deny rule](/docs/en/permissions#manage-permissions) removes that tool from Claude's context entirely. Built-in tool definiti
Adding a bare tool name like `Bash` or `WebFetch` as a [deny rule](/docs/en/permissions#manage-permissions) removes that tool from Claude's context entirely. Built-in tool definiti
+1 −1 lines
Recorded here 18 Aug 2026 00:37 UTC
claude-code
permissions
±changed
+3−1
claude-codechanged
permissions
You can view and manage Claude Code's tool permissions with `/permissions`. This UI lists all permission rules and the `settings.json` file each rule comes from.
You can view and manage Claude Code's tool permissions with `/permissions`. The dialog lists all permission rules and the `settings.json` file each rule comes from. You can open th
To block Claude's file tools from reading a file or directory, add a `Read` deny rule for its path, such as `Read(./.env)` or `Read(./secrets/**)`; [Exclude sensitive files](/docs/
+3 −1 lines
Recorded here 18 Aug 2026 00:37 UTC
claude-code
errors
±changed
+10−7
claude-codechanged
errors
| `Anthropic profile login expired · Run /login to use your claude.ai account instead, or re-authenticate the profile`
* In the Code tab of the [Desktop app](/docs/en/desktop), the session-limit card shows an **Auto-continue when limits reset** checkbox. The weekly-limit card doesn't offer it. When
Your Console organization has run out of prepaid credits.
Your Console organization has run out of prepaid credits, or Claude Code is sending your requests with a Console API key when you meant to use your subscription.
* If you have a Pro, Max, Team, or Enterprise plan and see this, run `/status` and check the `API key` row. An approved `ANTHROPIC_API_KEY` in your environment routes requests thro
+10 −7 lines
Recorded here 18 Aug 2026 00:37 UTC
claude-code
commands
±changed
+5−5
claude-codechanged
commands
If you send a command while Claude is responding, it queues and runs after the current turn finishes. Some commands, such as `/status`, `/tasks`, and `/usage`, run immediately with
If you send a command while Claude is responding, Claude Code queues it and runs it after the current turn finishes. Claude Code runs some commands immediately without interrupting
| `/add-dir <path>` | Add a working directory for file access during the current session. Type a partial
| `/add-dir <path>` | Add a working directory for file access during the current session. Type a partial
| `/bug [report]` | Report a bug or share your conversation. You choose how much session history to in
+5 −5 lines
Recorded here 18 Aug 2026 00:37 UTC
claude-code
statusline
±changed
+1−1
claude-codechanged
statusline
* Because `statusLine` executes a shell command, Claude Code runs it under the same [workspace trust rule as hooks in settings files](/docs/en/permissions#what-runs-before-you-trus
* Because `statusLine` executes a shell command, Claude Code runs it under the same [workspace trust rule as hooks in settings files](/docs/en/permissions#what-runs-before-you-trus
+1 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
plugin-marketplaces
±changed
+3−1
claude-codechanged
plugin-marketplaces
When a user adds an `https://` repository URL that Claude Code [clones rather than fetches](/docs/en/discover-plugins#add-from-other-git-hosts), such as a bare `github.com` or `git
Exact matching doesn't normalize URLs: a trailing slash, `.git` suffix, or `ssh://` versus `https://` form are treated as different values. If your organization's marketplace can b
The allowlist's exact matching doesn't normalize URLs: a trailing slash, `.git` suffix, or `ssh://` versus `https://` form are treated as different values. If your organization's m
+3 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
permissions
±changed
+7−3
claude-codechanged
permissions
Claude Code saves trust per workspace, keyed on the git repository root or, outside a repository, the directory you started Claude Code from. When you start in your home directory,
Claude Code keys and stores the trust you accept according to where you start it:
* In a repository, Claude Code keys the trust on the git repository root, so the trust covers the whole repository apart from any git repository nested inside it, such as a submodu
* Outside a repository, Claude Code keys the trust on the directory you started it from, and the trust covers any subdirectory of that directory apart from a git repository nested
+7 −3 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
network-config
±changed
+2−1
claude-codechanged
network-config
| `*.frame.claudeusercontent.com` | [Artifact](/docs/en/artifacts) content reads. The CLI fetches an artifact's files from this host when Claude opens one, and only when the A
The preceding table covers the standalone CLI. The Claude Desktop app and claude.ai in a browser load their application code and user content from additional Anthropic CDN hosts, i
The preceding table covers the standalone CLI. The Claude Desktop app and claude.ai in a browser load their application code and user content from additional Anthropic CDN hosts, i
+2 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
Approvals in an untracked `.claude/settings.local.json` also apply, but only after you accept a trust dialog for that folder or one of its parent directories: Claude Code runs git
Claude Code also applies approvals from an untracked `.claude/settings.local.json`, but it runs git to check whether the file is tracked, and it runs that check only in a [trusted
+1 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
* **Interactive session**: Claude Code holds back hooks from every settings file, including your own `~/.claude/settings.json`, until you accept the [workspace trust dialog](/docs/
* **Interactive session**: Claude Code holds back hooks from every settings file, including your own `~/.claude/settings.json`, until you accept the [workspace trust dialog](/docs/
+1 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
google-vertex-ai
±changed
+5−0
claude-codechanged
google-vertex-ai
If a region value isn't shaped like a region or location name, Claude Code treats it as unset. For example, Claude Code treats a value containing a slash, dot, or space as unset. C
* `VERTEX_REGION_CLAUDE_*`: Claude Code falls back to `CLOUD_ML_REGION`.
* `CLOUD_ML_REGION`: Claude Code falls back to `us-east5`.
+5 −0 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* Run `claude` in the directory and accept the trust dialog. The dialog appears even when a parent directory is already trusted, lists the rules being held back, and lets you decli
* Run `claude` in the directory and accept the trust dialog. [Project allow rules and workspace trust](/docs/en/permissions#project-allow-rules-and-workspace-trust) says which fold
+1 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `ANTHROPIC_AWS_BASE_URL` | Override the [Claude Platform on AWS](/docs/en/claude-platform-on-aws) endpoint URL. Use for custom regions or when rout
| `ANTHROPIC_AWS_BASE_URL` | Override the [Claude Platform on AWS](/docs/en/claude-platform-on-aws) endpoint URL. Use for custom regions or when rout
+1 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
discover-plugins
±changed
+14−5
claude-codechanged
discover-plugins
Add any git repository by providing the full URL. This works with any Git host, including GitLab, Bitbucket, and self-hosted servers. Include the `.git` suffix so Claude Code clone
Include the `https://` prefix as well. Claude Code v2.1.196 and later reject a host typed without it, such as `gitlab.com/company/plugins.git`, as an invalid GitHub `owner/repo` sh
Add a git marketplace repository by providing its full URL. For an `https://` URL, whether to include the `.git` suffix depends on the host:
+14 −5 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
cloud-environments
±changed
+2−0
claude-codechanged
cloud-environments
If sessions in the environment work with [artifacts](/docs/en/artifacts), include `*.frame.claudeusercontent.com` in your list. Claude Code fetches artifact content from that host.
+2 −0 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
claude-platform-on-aws
±changed
+3−1
claude-codechanged
claude-platform-on-aws
`ANTHROPIC_AWS_WORKSPACE_ID` is required and is sent on every request as the `anthropic-workspace-id` header. Replace the example `wrkspc_01ABCDEFGHIJKLMN` value with your own work
`ANTHROPIC_AWS_WORKSPACE_ID` is required. Claude Code sends it on every request as the `anthropic-workspace-id` header. Replace the example `wrkspc_01ABCDEFGHIJKLMN` value with you
Claude Code computes the base URL as `https://aws-external-anthropic.{region}.api.aws` from the AWS region, which it resolves with the [same precedence as Amazon Bedrock](/docs/en/
+3 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
claude-code
amazon-bedrock
±changed
+5−1
claude-codechanged
amazon-bedrock
The active profile is `AWS_PROFILE` if set, otherwise `default`. Set `AWS_SHARED_CREDENTIALS_FILE` or `AWS_CONFIG_FILE` to point at non-default file paths. Run `/status` to see t
If a value from any of these sources isn't shaped like a region name, Claude Code treats it as unset and continues down the order. For example, Claude Code treats a value contain
The active profile is `AWS_PROFILE` if set, otherwise `default`. Set `AWS_SHARED_CREDENTIALS_FILE` or `AWS_CONFIG_FILE` to point at non-default file paths.
+5 −1 lines
Recorded here 18 Aug 2026 00:07 UTC
17 Aug 2026
46 pages
+677 −440 lines
claude-code
tools-reference
±changed
+2−2
claude-codechanged
tools-reference
Where a subagent's permission prompts appear depends on whether it runs in the foreground or the background. Claude Code runs subagents in the background by default. For the cases
Where you see a subagent's permission prompts depends on whether it runs in the foreground or the background. Claude Code runs subagents in the background by default, apart from th
To limit what a subagent can reach in the first place, narrow its `tools` field, leave Bash off the list, or set deny rules in your settings, as described in [Control subagent capa
To [limit what a subagent can reach](/docs/en/sub-agents#control-subagent-capabilities) in the first place, narrow its `tools` field, for example by leaving Bash off the list, or s
+2 −2 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
sub-agents
±changed
+9−7
claude-codechanged
sub-agents
* **Background subagents** run concurrently while you continue working. As of v2.1.186, when a background subagent reaches a tool call that needs permission, the prompt surfaces in
For each subagent Claude spawns, Claude Code picks the mode from the first of these cases that applies:
* **Background subagents** run concurrently while you continue working. When a background subagent reaches a tool call that needs permission, Claude Code surfaces the prompt in you
+9 −7 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
statusline
±changed
+40−39
claude-codechanged
statusline
| Field | Description
| -------------------------------------------------------------------------------- | -----------------------------------------------------------------------------------------------
| `model.id`, `model.display_name` | Current model identifier and display name
| `cwd`, `workspace.current_dir` | Current working directory. Both fields contain the same value; `workspace.current_dir` is prefe
| `workspace.project_dir` | Directory where Claude Code was launched, which may differ from `cwd` if the working directory
+40 −39 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
settings
±changed
+1−1
claude-codechanged
settings
| `prUrlTemplate` | URL template for the PR badge shown in the footer and in tool-result summaries. Substitutes `{host}`, `{owner}`, `{repo}`, `{number}`, and `{
| `prUrlTemplate` | URL template for the PR badge shown in the footer and in tool-result summaries. Substitutes `{host}`, `{owner}`, `{repo}`, `{number}`, and `{
+1 −1 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
interactive-mode
±changed
+25−2
claude-codechanged
interactive-mode
The badge disappears once the pull request merges or closes. `Cmd+click` (macOS) or `Ctrl+click` (Windows/Linux) the link to open the pull request in your browser. The status refre
The badge disappears once the pull request merges or closes. `Cmd+click` (macOS) or `Ctrl+click` (Windows/Linux) the link to open the pull request in your browser. How often Claude
* **Anthropic API with [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) on**: about every 90 seconds while you're active in the session, and less
* **Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, Claude Platform on AWS, or feature-flag fetching off**: every 60 seconds
+25 −2 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
how-claude-code-works
±changed
+1−1
claude-codechanged
how-claude-code-works
[Subagents](/docs/en/sub-agents) get their own fresh context, completely separate from your main conversation. Their work doesn't bloat your context. When done, they return a summa
[Subagents](/docs/en/sub-agents) work in their own context window. A subagent starts fresh unless it's a [fork](/docs/en/sub-agents#fork-the-current-conversation), which starts wit
+1 −1 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
features-overview
±changed
+13−11
claude-codechanged
features-overview
| Feature | When it loads | What loads | Context cost |
| --------------------- | ------------------------------ | --------------------------------------------------- | -------------------------------------------- |
| **CLAUDE.md** | Session start | Full content | Every request |
| **Skills** | Session start + when used | Descriptions at start, full content when used | Low (descriptions every request)\* |
| **MCP servers** | Session start | Tool names; full schemas on demand | Low until a tool is used |
+13 −11 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
env-vars
±changed
+3−2
claude-codechanged
env-vars
| `CLAUDE_CODE_FORK_SUBAGENT` | Controls [fork mode](/docs/en/sub-agents#turn-fork-mode-on-or-off), which lets Claude spawn [forked subagents](/docs/en/
| `CLAUDE_CODE_FORK_SUBAGENT` | Controls [fork mode](/docs/en/sub-agents#turn-fork-mode-on-or-off), which lets Claude spawn [forked subagents](/docs/en/
| `FORCE_HYPERLINK` | Set to `1` to enable clickable OSC 8 hyperlinks when your terminal supports them but isn't auto-detected, or `0` to disa
| `FORCE_HYPERLINK` | Set to `1` to enable clickable OSC 8 hyperlinks when your terminal supports them but isn't auto-detected, or `0` to disa
* Have Claude Code refresh the [PR review status badge](/docs/en/interactive-mode#pr-review-status) less often while you're idle; Claude Code refreshes it every 60 seconds instead
+3 −2 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
agents
±changed
+1−1
claude-codechanged
agents
* A [forked subagent](/docs/en/sub-agents#fork-the-current-conversation), started with `/subtask`, is a subagent that inherits your full conversation context instead of starting fr
* A [forked subagent](/docs/en/sub-agents#fork-the-current-conversation) is a subagent that inherits your full conversation context instead of starting fresh. It's a way to spawn a
+1 −1 lines
Recorded here 17 Aug 2026 22:37 UTC
claude-code
changelog
±changed
+54−0
claude-codechanged
changelog
<Update label="2.1.234" description="August 17, 2026">
* Added the optional `CLAUDE_CODE_PROJECT_DIR_NAME` environment variable: hosts that give each session its own config directory can choose a short name for the per-project transc
* Added the `selection:clear` keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view
* Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states
+54 −0 lines
Recorded here 17 Aug 2026 21:07 UTC
claude-docs
third-party/claude-desktop/vertex
±changed
+14−14
claude-docschanged
third-party/claude-desktop/vertex
| Setting | Type | Availability | Default | Descriptio
| ------------------------------------------------------------------------------------------------------------------------------ | -------- | --------------- | ------- | ----------
| <span id="inferencevertexprojectid" />GCP project ID<br />`inferenceVertexProjectId` | `string` | MDM + Bootstrap | — | Google Clo
| <span id="inferencevertexregion" />GCP region<br />`inferenceVertexRegion` | `string` | MDM + Bootstrap | — | GCP region
| <span id="inferencevertexbaseurl" />Vertex AI base URL<br />`inferenceVertexBaseUrl` | `string` | MDM + Bootstrap | — | PSC endpoi
+14 −14 lines
Recorded here 17 Aug 2026 20:37 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+1−1
claude-docschanged
third-party/claude-desktop/gateway
```yaml theme={null} theme={null} theme={null} theme={null}
```yaml theme={null}
+1 −1 lines
Recorded here 17 Aug 2026 20:37 UTC
claude-docs
third-party/claude-desktop/extensions
±changed
+96−38
claude-docschanged
third-party/claude-desktop/extensions
| Layer | Provisioned by | Delivered via
| -------------------- | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------
| Managed MCP servers | Admin | `managedMcpServers` configuration key
| Organization plugins | Admin | A [plugin marketplace](#plugin-marketplaces-admin) git repository (recommended) or a [system-wide directory](#organization-plugins-admin)
| User extensions | End user | In-app Connectors and Plugins UI
+96 −38 lines
Recorded here 17 Aug 2026 20:37 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+34−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v1.32352.0" description="2026-08-17">
<div className="cfg-keys">
| MDM key | Type | Description
| ------------------------------------------------------------------------------------------------------------------- | --------- | --------------------------------------------
+34 −0 lines
Recorded here 17 Aug 2026 20:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+59−57
claude-docschanged
third-party/claude-desktop/configuration
| Setting | Type | Availability | D
| ------------------------------------------------------------------------------------------------------------------------------------------------ | --------- | --------------- | -
| <span id="inferencecustomheaders" />Custom inference headers<br />`inferenceCustomHeaders` | `object` | MDM + Bootstrap | —
| <span id="inferencesessionlifetimesec" />Sign-in session lifetime<br />`inferenceSessionLifetimeSec` | `integer` | MDM + Bootstrap | —
| <span id="inferencecredentialhelper" />Helper script<br />`inferenceCredentialHelper` | `string` | MDM + Bootstrap | —
+59 −57 lines
Recorded here 17 Aug 2026 20:37 UTC
claude-docs
cowork/changelog
±changed
+43−0
claude-docschanged
cowork/changelog
<Update label="v1.32352.0" description="2026-08-17">
**General**
* Fixed Windows updates sometimes leaving the app half installed, with later updates failing too.
+43 −0 lines
Recorded here 17 Aug 2026 20:37 UTC
claude-code
sub-agents
±changed
+4−11
claude-codechanged
sub-agents
Directories added with `--add-dir` are also scanned: a `.claude/agents/` folder inside an added directory loads alongside project subagents. See [Additional directories](/docs/en/p
When you add a directory with `--add-dir` or `/add-dir`, Claude Code also loads its `.claude/agents/` folder, alongside your project subagents. See [Additional directories](/docs/e
Two cases still need a restart:
Three cases still need a restart:
* Claude Code doesn't watch `.claude/agents/` inside directories added with `--add-dir` or `/add-dir`, so after adding or editing a subagent there, restart to load the change.
+4 −11 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
skills
±changed
+3−3
claude-codechanged
skills
The `--add-dir` flag and `/add-dir` command [grant file access](/docs/en/permissions#additional-directories-grant-file-access-not-configuration) rather than configuration discovery
Other `.claude/` configuration such as output styles is not loaded from additional directories. See the [exceptions table](/docs/en/permissions#additional-directories-grant-file-ac
The `--add-dir` flag and `/add-dir` command [grant file access](/docs/en/permissions#additional-directories-grant-file-access-not-configuration) rather than configuration discovery
+3 −3 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
sandboxing
±changed
+6−6
claude-codechanged
sandboxing
* `rm` or `rmdir` commands that target `/`, your home directory, or other critical system paths still go through the regular permission flow
* `rm` or `rmdir` commands that target a [critical path](/docs/en/permission-modes#critical-paths) still go through the regular permission flow
| | What it controls | What replaces the prompt
| :----------------------------------------------------------------- | :------------------------------------------ | :--------------------------------------------------------------
| `/sandbox` | What a Bash command can access once it runs | The sandbox boundary itself, in [auto-allow mode](#sandbox-mode
+6 −6 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
sandbox-environments
±changed
+1−7
claude-codechanged
sandbox-environments
When you pass `--dangerously-skip-permissions`, Claude acts without asking you first. Claude Code still prompts you only for:
* Explicit [ask rules](/docs/en/permissions#manage-permissions)
* Connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools)
* MCP tools marked [`requiresUserInteraction`](/docs/en/mcp#require-approval-for-a-specific-tool)
+1 −7 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
permissions
±changed
+11−13
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
+11 −13 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
permission-modes
±changed
+84−41
claude-codechanged
permission-modes
A permission mode sets which actions Claude can take in a session without asking you first. In Manual mode, Claude Code stops and asks you before most actions that edit files, run
A permission mode sets which actions Claude can take in a session without asking you first. In Manual mode, Claude Code stops and asks you before most actions that edit files, run
Writes to [protected paths](#protected-paths) are never auto-approved except in `bypassPermissions` mode and in planning sessions with bypass permissions available.
Modes set the baseline. Layer [permission rules](/docs/en/permissions#manage-permissions) on top to pre-approve or block specific tools. These controls apply in every mode, includi
+84 −41 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
hooks
±changed
+8−6
claude-codechanged
hooks
| Field | Description
| :------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------
| `permissionDecision` | `"allow"` skips the permission prompt, except for [tools that require user interaction](#pretooluse-decision-control) and connector tools [your organ
| `permissionDecisionReason` | For `"allow"` and `"ask"`, shown to the user but not Claude. For `"deny"`, shown to Claude. For `"defer"`, ignored
| `updatedInput` | Modifies the tool's input parameters before execution. Replaces the entire input object, so include unchanged fields alongside modified ones. Combine
+8 −6 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
headless
±changed
+1−1
claude-codechanged
headless
`acceptEdits` lets Claude write files without prompting and also auto-approves common filesystem commands such as `mkdir`, `touch`, `mv`, and `cp`. Apart from the [read-only comman
`acceptEdits` lets Claude write files without prompting and also auto-approves common filesystem commands such as `mkdir`, `touch`, `mv`, and `cp`. The [actions no mode auto-approv
+1 −1 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
desktop
±changed
+7−7
claude-codechanged
desktop
| Mode | Settings key | Behavior
| ---------------------- | ------------------- | -----------------------------------------------------------------------------------------------------------------------------------
| **Manual** | `default` | Claude asks before editing files or running commands. You see a diff and can accept or reject each change.
| **Accept edits** | `acceptEdits` | Claude auto-accepts file edits and common filesystem commands like `mkdir`, `touch`, and `mv`, but still asks before running other
| **Plan** | `plan` | Claude reads files and runs commands to explore, then proposes a plan without editing your source code. Good for complex tasks wher
+7 −7 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
channels
±changed
+1−7
claude-codechanged
channels
If Claude hits a permission prompt while you're away from the terminal, the session pauses until you respond. Channel servers that declare the [permission relay capability](/docs/e
* Explicit ask rules
* Connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools)
* MCP tools marked [`requiresUserInteraction`](/docs/en/mcp#require-approval-for-a-specific-tool)
+1 −7 lines
Recorded here 17 Aug 2026 20:07 UTC
claude-code
agent-sdk/user-input
±changed
+3−3
claude-codechanged
agent-sdk/user-input
**The callback never fires for auto-approved tools.** Any approval earlier in the [permission evaluation flow](/docs/en/agent-sdk/permissions#how-permissions-are-evaluated), an a
`AskUserQuestion`, MCP tools marked [`requiresUserInteraction`](/docs/en/mcp#require-approval-for-a-specific-tool), and connector tools [your organization set to `ask`](/docs/en/
**The callback never fires for auto-approved tools.** Any approval earlier in the [permission evaluation flow](/docs/en/agent-sdk/permissions#how-permissions-are-evaluated), an a
+3 −3 lines
Recorded here 17 Aug 2026 20:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.