HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
812pages tracked
765 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
ReadSourcePageWhatLines
15 Aug 2026
36 pages
+445 −184 lines
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--worktree`, `-w` | Start Claude in an isolated [git worktree](/docs/en/worktrees) at `<repo>/.claude/worktrees/<name>`. If no name is given, one is
| `--worktree`, `-w` | Start Claude in an isolated [git worktree](/docs/en/worktrees) at `<repo>/.claude/worktrees/<name>`. If you don't give a name, C
+1 −1 lines
Recorded here 15 Aug 2026 02:07 UTC
claude-code
agent-view
±changed
+22−17
claude-codechanged
agent-view
The `#N` label that can appear at the right edge of a row is a [pull request the session is linked to](#pull-request-status), not part of the state icon.
The `#N` or `!N` label that can appear at the right edge of a row is a link to the session's [pull request or merge request](#pull-request-status), not part of the state icon.
When a session opens a pull request, a `#1234` label appears at the right edge of the row, linked to the pull request. Claude Code emits the link even when it can't detect hyperlin
When a session [opens a pull request](#how-file-edits-are-isolated), Claude Code adds a label at the right edge of the row, linked to the pull request:
+22 −17 lines
Recorded here 15 Aug 2026 02:07 UTC
claude-code
sub-agents
±changed
+18−9
claude-codechanged
sub-agents
Claude Code clears a background subagent's row from the subagent panel below the prompt input in one of two ways, depending on how the subagent ended:
* When a subagent finishes successfully, Claude Code removes its row immediately and, except in [screen reader mode](/docs/en/accessibility), shows `/tasks to see subagents` in the
* When a subagent fails or you stop it, Claude Code keeps its row for 30 seconds. To clear the row sooner, select it and press `x`.
+18 −9 lines
Recorded here 15 Aug 2026 01:37 UTC
claude-code
settings
±changed
+1−1
claude-codechanged
settings
When a repository's `.claude/settings.json` includes `extraKnownMarketplaces`, Claude Code adds those marketplaces for a team member after they accept the workspace trust dialog fo
When a repository's `.claude/settings.json` includes `extraKnownMarketplaces`, Claude Code adds those marketplaces for a team member after they accept the workspace trust dialog fo
+1 −1 lines
Recorded here 15 Aug 2026 01:37 UTC
claude-code
env-vars
±changed
+14−14
claude-codechanged
env-vars
Claude Code turns some features on through feature flags it fetches from Anthropic. `DISABLE_GROWTHBOOK`, `DISABLE_TELEMETRY`, `DO_NOT_TRACK`, and `CLAUDE_CODE_DISABLE_NONESSENTIAL
* [The auto-mode starting default](/docs/en/permission-modes#which-mode-a-session-starts-in) on Pro, Max, and Team plans; sessions start in Manual instead
* In the VS Code extension, [reading settings files for the starting mode](/docs/en/permission-modes#switch-permission-modes)
* [Remote Control](/docs/en/remote-control#requirements)
+14 −14 lines
Recorded here 15 Aug 2026 01:07 UTC
claude-code
settings
±changed
+11−11
claude-codechanged
settings
| `disableAutoMode` | Set to `"disable"` to prevent [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) from being activated. Removes `auto` fr
| `disableAutoMode` | Set to `"disable"` to prevent [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) from being activated. Removes `auto` fr
| Keys | Description
| :---------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------
| `allow` | Array of permission rules to allow tool use. Tool-name globs are supported only in the tool position after a literal `mcp__<server>__` prefi
+11 −11 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
sessions
±changed
+4−1
claude-codechanged
sessions
* Permission mode: the mode the session was in. `plan` and `bypassPermissions` are never restored; [bypassing permissions](/docs/en/permission-modes#skip-all-checks-with-bypassperm
* Permission mode: the mode the session was in, with these exceptions. Pass `--permission-mode` to override the restored mode.
* `plan` and `bypassPermissions` are never restored; a session that was in one of them resumes in the mode a new session would start in. To [bypass permissions](/docs/en/permissi
* `auto` is restored only when your account still meets the [auto mode requirements](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)
* Manual is restored as Manual when a new session would start in auto mode from the [built-in default](/docs/en/permission-modes#which-mode-a-session-starts-in); when a `defaultM
+4 −1 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+7−1
claude-codechanged
self-hosted-environments-deploy
Connector tools, such as GitHub, Slack, Linear, and the other claude.ai connectors, are called from Anthropic's side rather than from your runner, so when a self-hosted session use
Connector tools, such as GitHub, Slack, Linear, and the other claude.ai connectors, are called from Anthropic's side rather than from your runner, so when a self-hosted session use
* `https://api.anthropic.com/v2/ccr-sessions/*`
* `https://api.anthropic.com/v1/code/sessions/*`
+7 −1 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
permissions
±changed
+5−5
claude-codechanged
permissions
Claude Code uses a tiered permission system to balance power and safety:
Claude Code uses a tiered permission system to balance power and safety. The table shows, for each tool type, whether Manual mode asks before the action runs. The other [permission
Claude Code supports several permission modes that control how it approves tool calls. See [Permission modes](/docs/en/permission-modes) for when to use each one. Set the `defaultM
Claude Code supports several permission modes that control how it approves tool calls. See [Permission modes](/docs/en/permission-modes) for when to use each one. To change the mod
| `default` | Standard behavior: prompts for permission on first use of each tool. Labeled Manual in the CLI, the VS Code and JetBrains extensions, and the desktop app, a
+5 −5 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
permission-modes
±changed
+105−47
claude-codechanged
permission-modes
When Claude wants to edit a file, run a shell command, or make a network request, it pauses and asks you to approve the action. Permission modes control how often that pause happen
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
On Pro, Max, and Team plans, the built-in starting mode is auto mode. [Which mode a session starts in](#which-mode-a-session-starts-in) covers the surfaces and settings that change
Each mode makes a different tradeoff between convenience and oversight. The table below shows what Claude can do without a permission prompt in each mode.
+105 −47 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
network-config
±changed
+2−0
claude-codechanged
network-config
An [artifact](/docs/en/artifacts) that loads a typeface from [Google Fonts](/docs/en/artifacts#improve-the-visual-design) also requests `fonts.googleapis.com` and `fonts.gstatic.co
+2 −0 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
env-vars
±changed
+2−0
claude-codechanged
env-vars
* [The auto-mode starting default](/docs/en/permission-modes#which-mode-a-session-starts-in) on Pro, Max, and Team plans; sessions start in Manual instead
* In the VS Code extension, [reading settings files for the starting mode](/docs/en/permission-modes#switch-permission-modes)
+2 −0 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
desktop
±changed
+2−0
claude-codechanged
desktop
An [artifact](/docs/en/artifacts) that loads a typeface from [Google Fonts](/docs/en/artifacts#improve-the-visual-design) also requests `fonts.googleapis.com` and `fonts.gstatic.co
+2 −0 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-code
artifacts
±changed
+11−7
claude-codechanged
artifacts
For typography, Claude can load a typeface from Google Fonts, the one external font source an artifact page can load from. Claude inlines any other typeface as a `@font-face` data
| Constraint | Effect
| :------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------
| No external requests | The CSP blocks scripts, stylesheets, fonts, and images loaded from any other host, along with `fetch`, XHR, and WebSocket calls. Claude inlines CSS and Jav
+11 −7 lines
Recorded here 15 Aug 2026 00:37 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+4−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v1.30096.5" description="2026-08-14">
No configuration changes in this release.
</Update>
+4 −0 lines
Recorded here 15 Aug 2026 00:07 UTC
claude-docs
cowork/changelog
±changed
+18−0
claude-docschanged
cowork/changelog
<Update label="v1.30096.5" description="2026-08-14">
**General**
* No user-facing changes.
+18 −0 lines
Recorded here 15 Aug 2026 00:07 UTC
14 Aug 2026
71 pages
+1198 −512 lines
claude-docs
third-party/claude-desktop/configuration
±changed
+8−8
claude-docschanged
third-party/claude-desktop/configuration
```yaml theme={null} theme={null} theme={null} theme={null}
```yaml theme={null} theme={null} theme={null} theme={null} theme={null}
```json theme={null} theme={null} theme={null} theme={null}
```json theme={null} theme={null} theme={null} theme={null} theme={null}
```json theme={null} theme={null} theme={null} theme={null}
+8 −8 lines
Recorded here 14 Aug 2026 23:07 UTC
claude-code
tools-reference
±changed
+4−4
claude-codechanged
tools-reference
The `Permission required` column shows whether the tool prompts in the default permission mode for paths inside the working directory. File-access tools marked No, including `Rea
On Pro, Max, and Team plans, Claude Code starts sessions in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), where a classifier decides most of these prom
When Monitor runs a command, it uses the same [permission rules as Bash](/docs/en/permissions#tool-specific-permission-rules), so `allow` and `deny` patterns you have set for Bash
When Monitor runs a command, it uses the same [permission rules as Bash](/docs/en/permissions#tool-specific-permission-rules), so `allow` and `deny` patterns you have set for Bash
Opening a WebSocket prompts for approval, and the prompt doesn't offer an option to skip future prompts for the same host.
+4 −4 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
terminal-config
±changed
+1−1
claude-codechanged
terminal-config
| `promptBorder` | Input box border in the default permission mode |
| `promptBorder` | Input box border in Manual mode |
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
sub-agents
±changed
+7−7
claude-codechanged
sub-agents
| Agent | Model | When Claude uses it
| :---------------- | :------- | :----------------------------------------------------------------------------------------------------------------------------------------------
| claude | Inherits | When a task doesn't fit a more specialized agent. A catch-all with every tool [available to subagents](#available-tools). Also the [default age
| statusline-setup | Sonnet | When you run `/statusline` to configure your status line
| claude-code-guide | Haiku | When you ask questions about Claude Code features
+7 −7 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
To keep a command from aborting at the default permission prompt, pre-approve it with [`allowed-tools`](#pre-approve-tools-for-a-skill). A matching ask or deny rule still aborts th
To keep an unmatched command from aborting here, pre-approve it with [`allowed-tools`](#pre-approve-tools-for-a-skill). A matching ask or deny rule still aborts the invocation rega
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+1−1
claude-codechanged
self-hosted-environments-configuration
Only enable auto mode on an environment whose session containers run with [default-deny network egress](/docs/en/self-hosted-environments-deploy#default-deny-egress) and the rest
Only pin auto mode on an environment whose session containers run with [default-deny network egress](/docs/en/self-hosted-environments-deploy#default-deny-egress) and the rest of
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
sandboxing
±changed
+5−5
claude-codechanged
sandboxing
Ask Claude to run a command, such as a build or a test suite. By default, commands inside the sandbox can write only to the working directory and the session temp directory. Th
Ask Claude to run a command, such as a build or a test suite. By default, commands inside the sandbox can write only to the working directory and the session temp directory. Th
When a command can be sandboxed, Claude Code runs it inside the sandbox and approves it automatically, without asking your permission. Commands that cannot be sandboxed, such as th
When a command can be sandboxed, Claude Code runs it inside the sandbox and approves it automatically, without asking your permission. Commands that cannot be sandboxed, such as th
Auto-allow mode works independently of your permission mode setting, with one exception: [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode). Even if yo
+5 −5 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
Switching between [permission modes](/docs/en/permission-modes), such as from default to accept edits, does not change the system prompt or tool definitions, so mode changes are ca
Switching between [permission modes](/docs/en/permission-modes), such as from Manual to accept edits, does not change the system prompt or tool definitions, so mode changes are cac
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
network-config
±changed
+15−6
claude-codechanged
network-config
Claude Code reads the certificate and key files at startup and re-reads them each time it applies settings. It doesn't watch those paths during a session, so it keeps presenting th
To rotate the certificate and key:
* **Running session**: replace the files at the same paths, then restart Claude Code so it picks up the new pair. A mid-session settings application, such as a remote managed-setti
+15 −6 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
Press `Esc` to return to the CLI. Ask Claude to do something that requires permission, then switch away from the terminal. You should receive a desktop notification.
Press `Esc` to return to the CLI. Press `Shift+Tab` until the status bar shows `⏸ manual mode on`, ask Claude to do something that requires permission, then switch away from th
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
goal
±changed
+1−1
claude-codechanged
goal
A goal doesn't change permissions. In the default permission mode, Claude still asks before tool calls that your settings don't already allow, such as the test command above. To le
A goal doesn't change your permission mode. To let goal turns run unattended, run `/goal` in [auto mode](/docs/en/auto-mode-config). In [Manual mode](/docs/en/permission-modes), Cl
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* `Shell command permission check failed for pattern "..."`: the command's permission check returned something other than allow. Injected commands never prompt, so the invocation a
* `Shell command permission check failed for pattern "..."`: the command's permission check returned something other than allow. Injected commands never prompt, so the invocation a
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
env-vars
±changed
+1−0
claude-codechanged
env-vars
| `CLAUDE_CODE_DISABLE_MTLS_RELOAD_ON_STALE_CONNECTION` | Set to `1` to stop Claude Code from re-reading the [mTLS client certificate and key](/docs/en/network-config#mtls-authen
+1 −0 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
desktop-quickstart
±changed
+9−5
claude-codechanged
desktop-quickstart
* **Code**: An interactive coding assistant with direct access to your local files. You review and approve each change in real time.
* **Code**: An interactive coding assistant with direct access to your local files. Depending on the permission mode, you approve each change as Claude proposes it or review the ch
By default, the Code tab starts in [Manual mode](/docs/en/desktop#choose-a-permission-mode), where Claude proposes changes and waits for your approval before applying them. You
What happens next depends on the [permission mode](/docs/en/desktop#choose-a-permission-mode) shown in the selector next to the send button:
+9 −5 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
desktop
±changed
+13−13
claude-codechanged
desktop
Permission modes control how much autonomy Claude has during a session: whether it asks before editing files, running commands, or both. You can switch modes at any time using the
Permission modes control how much autonomy Claude has during a session: whether it asks before editing files, running commands, or both. You can switch modes at any time using the
| **Manual** | `default` | Claude asks before editing files or running commands. You see a diff and can accept or reject each change. Recommended for new user
| **Manual** | `default` | Claude asks before editing files or running commands. You see a diff and can accept or reject each change.
| Key | Description
+13 −13 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
claude-apps-gateway-config
±changed
+23−18
claude-codechanged
claude-apps-gateway-config
* Disabled tools, from bare tool-name `permissions.deny` entries
* The egress allowlist, from `sandbox.network.allowedDomains`
* Disabled tools, from bare tool-name `permissions.deny` entries. If you set `disabledBuiltinTools` in the policy's `desktop` block, the gateway serves the union of your value and
* The egress allowlist, from `sandbox.network.allowedDomains`. If you set `coworkEgressAllowedHosts` in the policy's `desktop` block, the gateway uses that value instead of the der
To set `disabledBuiltinTools` or `coworkEgressAllowedHosts` in a policy's `desktop` block, you need Claude Code v2.1.232 or later on the gateway server.
+23 −18 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
changelog
±changed
+23−0
claude-codechanged
changelog
<Update label="2.1.233" description="August 14, 2026">
* Added GitLab merge request URL support to the `--worktree` flag and the `claude agents` view (where MRs display as `!N`)
* Added an opt-in `forward_user_identity` apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attri
* Added opt-in memory cgroup support for Bash tool commands on Linux (`CLAUDE_CODE_TOOL_MEMORY_LIMIT`) so a runaway build can't stall the session
+23 −0 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
auto-mode-config
±changed
+2−4
claude-codechanged
auto-mode-config
Starting August 14, 2026, auto mode becomes the default permission mode for new sessions on Pro, Max, and Team plans. You can switch modes at any time. A default you set yourself
For how to enable auto mode and what it blocks by default, see [Permission modes](/docs/en/permission-modes#eliminate-prompts-with-auto-mode). This page is the configuration refere
For how sessions end up in auto mode and what the classifier blocks by default, see [auto mode on the Permission modes page](/docs/en/permission-modes#eliminate-prompts-with-auto-m
* [Permission modes](/docs/en/permission-modes#eliminate-prompts-with-auto-mode): what auto mode is, what it blocks by default, and how to enable it
+2 −4 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
agent-sdk/permissions
±changed
+1−1
claude-codechanged
agent-sdk/permissions
Claude explores the codebase and produces a plan without editing your source files. Read-only tools run as in default mode.
Claude explores the codebase and produces a plan without editing your source files. Read-only tools run as they do in the `default` permission mode.
+1 −1 lines
Recorded here 14 Aug 2026 22:37 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
In an interactive session with [agent teams](/docs/en/agent-teams) enabled, a subagent that Claude spawns from the main conversation with a `name` launches as a teammate instead, u
In an interactive session with [agent teams](/docs/en/agent-teams) enabled, a subagent that Claude spawns from the main conversation with a `name` launches as a teammate instead, u
+1 −1 lines
Recorded here 14 Aug 2026 22:07 UTC
claude-code
claude-security
±changed
+1−1
claude-codechanged
claude-security
You don't have to start from the menu: ask for a job directly, as arguments to the command, such as `/claude-security scan my branch`, or in plain language, such as "scan commit ab
You don't have to start from the menu: ask for a job directly, as arguments to the command, such as `/claude-security scan my branch`, or in plain language, such as "scan commit ab
+1 −1 lines
Recorded here 14 Aug 2026 22:07 UTC
claude-code
chrome
±changed
+1−1
claude-codechanged
chrome
Before Claude's first browser action, Claude Code asks for permission to use the `claude-in-chrome` skill. Approve it and Claude opens a new tab and starts the task.
If Claude Code asks for permission before a browser action, approve it. The dialog starts with `Claude in Chrome wants to` and offers an option to allow all actions on that sit
+1 −1 lines
Recorded here 14 Aug 2026 22:07 UTC
claude-code
channels-reference
±changed
+2−0
claude-codechanged
channels-reference
This walkthrough tests the permission dialog itself, so once the session is open, press `Shift+Tab` until the status bar shows `⏸ manual mode on`. In auto mode the classifier would
+2 −0 lines
Recorded here 14 Aug 2026 22:07 UTC
claude-code
agent-teams
±changed
+4−8
claude-codechanged
agent-teams
Enabling agent teams also changes ordinary delegation. Claude may [name a subagent](/docs/en/sub-agents#subagent-names) on its own, and while agent teams are enabled, a subagent th
Enabling agent teams also changes ordinary delegation. Claude may [name a subagent](/docs/en/sub-agents#subagent-names) on its own, and while agent teams are enabled, a subagent th
An agent team forms when the first teammate is spawned, with the main session acting as the lead. Claude spawns a teammate the same way it spawns a [subagent](/docs/en/sub-agents),
* **You request teammates**: give Claude a task that benefits from parallel work and explicitly ask for teammates. Claude spawns them based on your instructions.
+4 −8 lines
Recorded here 14 Aug 2026 22:07 UTC
claude-code
remote-control
±changed
+34−19
claude-codechanged
remote-control
If the connection fails, Claude Code shows a notification with the failure reason, and the indicator changes to a failure state that stays in the footer. Select the indicator and p
If the connection fails, Claude Code shows a notification with the failure reason and switches the indicator to a failure state that stays in the footer. To read the reason again,
<span id="session-ended-elsewhere" />Read the reason before you reconnect. When the session was taken over or ended from another device, app, or Claude Code session, or the server
+34 −19 lines
Recorded here 14 Aug 2026 21:23 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
* **Describe the outcome, not the steps**: hand it the result you want and let it plan the path. To keep it working until that outcome holds, [set a goal](/docs/en/goal).
* **Describe the outcome, not the steps**: hand it the result you want and let it plan the path. To keep it working toward that outcome, [set a goal](/docs/en/goal).
+1 −1 lines
Recorded here 14 Aug 2026 21:23 UTC
claude-code
hooks-guide
±changed
+4−4
claude-codechanged
hooks-guide
The model's only job is to return a yes/no decision as JSON:
The model's only job is to return its decision as JSON:
* `Stop` and `SubagentStop`: the `reason` is fed back to Claude so it keeps working
* `Stop` and `SubagentStop`: the `reason` is fed back to Claude so it keeps working, unless the response also sets `"impossible": true` to mark the condition as one that can neve
This example uses a `Stop` hook to ask the model whether all requested tasks are complete. If the model returns `"ok": false`, Claude keeps working and uses the `reason` as its nex
+4 −4 lines
Recorded here 14 Aug 2026 21:23 UTC
claude-code
hooks
±changed
+24−22
claude-codechanged
hooks
* **[Prompt hooks](#prompt-and-agent-hook-fields)** (`type: "prompt"`): send a prompt to a Claude model for single-turn evaluation. The model returns a yes/no decision as JSON. See
* **[Prompt hooks](#prompt-and-agent-hook-fields)** (`type: "prompt"`): send a prompt to a Claude model for single-turn evaluation. The model returns its decision as JSON. See [Pro
The [`/goal`](/docs/en/goal) command is a built-in shortcut for a session-scoped prompt-based Stop hook. Use it when you want Claude to keep working until a condition holds witho
The [`/goal`](/docs/en/goal) command is a built-in shortcut for a session-scoped prompt-based Stop hook. Use it when you want Claude to keep working toward a condition without wr
| Field | Required | Description
+24 −22 lines
Recorded here 14 Aug 2026 21:23 UTC
claude-code
goal
±changed
+20−15
claude-codechanged
goal
> Set a completion condition with /goal and Claude keeps working across turns until the condition is met.
> Set a completion condition with /goal and Claude keeps working across turns until the condition is met or judged impossible.
The `/goal` command sets a completion condition and Claude keeps working toward it without you prompting each step. After each turn, a small fast model checks whether the condition
The `/goal` command sets a completion condition and Claude keeps working toward it without you prompting each step. After each turn, a small fast model checks whether the condition
| Approach | Next turn starts when | Stops when |
+20 −15 lines
Recorded here 14 Aug 2026 21:23 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
When the server reports instead that the previous session no longer exists, Claude Code shows [`Remote Control could not resume the previous session under the current login`](/docs
If the server reports instead that the previous session is gone, you don't see this message. Claude Code starts a new session in its place or shows [`Previous session is unavailabl
+1 −1 lines
Recorded here 14 Aug 2026 21:23 UTC
claude-code
scheduled-tasks
±changed
+1−1
claude-codechanged
scheduled-tasks
Scheduled tasks let Claude re-run a prompt automatically on an interval. Use them to poll a deployment, babysit a PR, check back on a long-running build, or remind yourself to do s
Scheduled tasks let Claude re-run a prompt automatically on an interval. Use them to poll a deployment, babysit a PR, check back on a long-running build, or remind yourself to do s
+1 −1 lines
Recorded here 14 Aug 2026 21:21 UTC
claude-code
prompt-library
±changed
+3−3
claude-codechanged
prompt-library
next: "Use `/goal` to keep Claude iterating until the screenshots match"
next: "Use `/goal` to keep Claude iterating toward matching screenshots"
next: "Set this as a `/goal` so Claude keeps writing tests until coverage hits the target"
next: "Set this as a `/goal` so Claude keeps writing tests toward the coverage target"
next: "Set this as a `/goal` so Claude keeps measuring and iterating until it hits the number"
+3 −3 lines
Recorded here 14 Aug 2026 21:21 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/goal [condition\|clear]` | Set a [goal](/docs/en/goal): Claude keeps working across turns until the condition
| `/goal [condition\|clear]` | Set a [goal](/docs/en/goal): Claude keeps working across turns until the condition
+1 −1 lines
Recorded here 14 Aug 2026 21:21 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
* **Across a session**: set the check as a [`/goal` condition](/docs/en/goal). A separate evaluator re-checks it after every turn and Claude keeps working until it holds.
* **Across a session**: set the check as a [`/goal` condition](/docs/en/goal). A separate evaluator re-checks it after every turn and Claude keeps working until the goal resolves.
+1 −1 lines
Recorded here 14 Aug 2026 21:21 UTC
claude-code
output-styles
±changed
+1−1
claude-codechanged
output-styles
* **Proactive**: Claude executes immediately, makes reasonable assumptions instead of pausing for routine decisions, and prefers action over planning. This is stronger autonomous-e
* **Proactive**: Claude executes immediately, makes reasonable assumptions instead of pausing for routine decisions, and prefers action over planning. This is stronger autonomous-e
+1 −1 lines
Recorded here 14 Aug 2026 21:13 UTC
claude-code
mcp-quickstart
±changed
+1−1
claude-codechanged
mcp-quickstart
The first time Claude calls the server, it asks for permission to use the new tool. Approve it to continue. The tool call in Claude's output is labeled with the server name, wh
If Claude Code asks for permission the first time Claude calls the server, approve it. The tool call in Claude's output is labeled with the server name, which is how you confir
+1 −1 lines
Recorded here 14 Aug 2026 21:13 UTC
claude-code
common-workflows
±changed
+1−1
claude-codechanged
common-workflows
You can also press `Shift+Tab` mid-session to cycle to plan mode. The cycle runs `default` → `acceptEdits` → `plan`. See [Plan mode](/docs/en/permission-modes#analyze-before-you-ed
You can also press `Shift+Tab` mid-session until the status bar shows `⏸ plan mode on`. See [Plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) for the ap
+1 −1 lines
Recorded here 14 Aug 2026 20:43 UTC
claude-code
channels
±changed
+1−1
claude-codechanged
channels
The message arrives in your Claude Code session. The terminal shows it as an inbound channel line like `← fakechat · web: what's in my working directory?`, while the model rece
The message arrives in your Claude Code session. The terminal shows it as an inbound channel line like `← fakechat · web: what's in my working directory?`, while the model rece
+1 −1 lines
Recorded here 14 Aug 2026 20:43 UTC
claude-code
workflows
±changed
+1−1
claude-codechanged
workflows
| Default, accept edits | Every run, unless you've selected **Yes, and don't ask again** for that workflow in this project
| Manual, accept edits | Every run, unless you've selected **Yes, and don't ask again** for that workflow in this project
+1 −1 lines
Recorded here 14 Aug 2026 20:29 UTC
claude-code
web-quickstart
±changed
+7−1
claude-codechanged
web-quickstart
The mode dropdown next to the input defaults to **Accept edits**, where Claude makes changes and pushes a branch without stopping for approval. Switch to **Plan** if you want C
The mode dropdown next to the input shows the mode the session will run in:
* **Auto**: a classifier reviews Claude's actions instead of asking you. Appears when your organization allows auto mode and the selected model supports it
* **Accept edits**: Claude makes changes and pushes a branch without stopping for approval
+7 −1 lines
Recorded here 14 Aug 2026 20:29 UTC
claude-code
jetbrains
±changed
+1−1
claude-codechanged
jetbrains
* Using manual approval mode for edits
* Using Manual mode for edits, because `acceptEdits` and auto mode both approve edits inside your working directory without asking, except in [protected paths](/docs/en/permission-
+1 −1 lines
Recorded here 14 Aug 2026 20:29 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Shift+Tab`, or `Alt+M` on Windows when the Node or Bun runtime doesn't enable VT input mode | Cycle permission modes
| `Shift+Tab`, or `Alt+M` on Windows when the Node or Bun runtime doesn't enable VT input mode | Cycle permission modes
+1 −1 lines
Recorded here 14 Aug 2026 20:29 UTC
claude-code
cli-reference
±changed
+2−2
claude-codechanged
cli-reference
| `--agents` | Define custom subagents dynamically via JSON. Uses the same field names as subagent [frontmatter](/docs/en/sub-agents#supported-
| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-t
| `--append-subagent-system-prompt` | Append custom text to the end of every [subagent](/docs/en/sub-agents)'s system prompt, including nested subagents. Only applies
| `--append-subagent-system-prompt` | Append custom text to the end of every [subagent](/docs/en/sub-agents)'s system prompt, nested subagents included, apart from a
+2 −2 lines
Recorded here 14 Aug 2026 20:19 UTC
claude-code
worktrees
±changed
+1−1
claude-codechanged
worktrees
Non-interactive runs with `-p` have no exit prompt, so Claude doesn't clean up their worktrees. Remove them with `git worktree remove`.
Non-interactive runs with `-p` have no exit prompt, so Claude doesn't clean up their worktrees, and Claude Code leaves the lock it took on each one at creation in place until a lat
+1 −1 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
Viewing a file with Bash also satisfies the read-before-edit requirement when the command is `cat`, `head`, `tail`, `sed -n 'X,Yp'`, `grep`, `egrep`, or `fgrep` on a single file wi
Viewing a file with Bash also satisfies the read-before-edit requirement when the command is `cat`, `nl`, `bat`, `batcat`, `head`, `tail`, `sed -n 'X,Yp'`, `grep`, `egrep`, `fgrep`
+1 −1 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
sub-agents
±changed
+2−2
claude-codechanged
sub-agents
The `--agents` flag accepts JSON with the same [frontmatter](#supported-frontmatter-fields) fields as file-based subagents: `description`, `prompt`, `tools`, `disallowedTools`, `mo
The `--agents` flag accepts JSON with a `prompt` field plus these [frontmatter](#supported-frontmatter-fields) fields: `description`, `tools`, `disallowedTools`, `model`, `permissi
In [non-interactive mode](/docs/en/headless), the [`--append-subagent-system-prompt`](/docs/en/cli-reference#cli-flags) flag appends the text you provide to the end of every subage
In [non-interactive mode](/docs/en/headless), pass [`--append-subagent-system-prompt`](/docs/en/cli-reference#cli-flags) to append your text to the end of every subagent's system p
+2 −2 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
skills
±changed
+10−10
claude-codechanged
skills
* A skill at any of these levels also overrides a bundled skill with the same name.
* For example, a `code-review` skill in your project's `.claude/skills/` replaces the bundled `/code-review`.
* A skill at any of these levels also overrides a bundled skill with the same name, but not the bundled skill's aliases.
* For example, a `code-review` skill in your project's `.claude/skills/` replaces the bundled `/code-review`, and typing the bundled alias `/review` never runs your skill.
Files in `.claude/commands/` support the same [frontmatter](#frontmatter-reference). Skills are recommended since they support additional features like supporting files.
+10 −10 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
permissions
±changed
+2−1
claude-codechanged
permissions
| [Command files](/docs/en/skills#where-skills-live) in `.claude/commands/` | Yes. When the added directory and your project both define a command with the same na
Claude Code discovers commands and output styles from the current working directory and its parents, your user directory at `~/.claude/`, and managed settings. Hooks and other `.cl
Claude Code discovers output styles from the current working directory and its parents, your user directory at `~/.claude/`, and managed settings. Hooks and other `.claude/settings
+2 −1 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
large-codebases
±changed
+1−1
claude-codechanged
large-codebases
Once conventions live in plugins, a teammate starting Claude in an unfamiliar part of the tree has no signal about which plugin that area's owners maintain. A [`SessionStart` hook]
Once conventions live in plugins, a teammate starting Claude in an unfamiliar part of the tree has no signal about which plugin that area's owners maintain. A [`SessionStart` hook]
+1 −1 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
hooks-guide
±changed
+15−14
claude-codechanged
hooks-guide
Any text your command writes to stdout is added to Claude's context. This example reminds Claude of project conventions and recent work. Add this to `.claude/settings.json` in your
Claude Code adds plain text your command writes to stdout to Claude's context. This example reminds Claude of project conventions and recent work. Add this to `.claude/settings.jso
* **Exit 0**: the hook reports no objection through its exit code. For a `PreToolUse` hook this doesn't approve the tool call: the normal [permission flow](/docs/en/permissions) st
* **Exit 0**: the hook reports no objection through its exit code. For a `PreToolUse` hook this doesn't approve the tool call: the normal [permission flow](/docs/en/permissions) st
* JSON that passes schema validation: Claude Code ignores the exit code, the JSON alone decides the outcome, and the hook isn't reported as an error. The per-event exceptions, li
+15 −14 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
hooks
±changed
+53−44
claude-codechanged
hooks
| Location | Scope | Shareable |
| :--------------------------------------------------------- | :---------------------------- | :---------------------------------------------------- |
| `~/.claude/settings.json` | All your projects | No, local to your machine |
| `.claude/settings.json` | Single project | Yes, can be committed to the repo |
| `.claude/settings.local.json` | Single project | No, gitignored when Claude Code saves a setting to it |
+53 −44 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `CLAUDE_CODE_ENABLE_APPEND_SUBAGENT_PROMPT` | Set to `1` to enable appending extra text to the end of every [subagent](/docs/en/sub-agents)'s system prompt. The [`--a
| `CLAUDE_CODE_ENABLE_APPEND_SUBAGENT_PROMPT` | Set to `1` to enable appending extra text to the end of the system prompt of every [subagent](/docs/en/sub-agents) other
+1 −1 lines
Recorded here 14 Aug 2026 20:17 UTC
claude-docs
third-party/claude-desktop/vertex
±changed
+2−0
claude-docschanged
third-party/claude-desktop/vertex
When your IdP is Microsoft Entra ID, you can run this sign-in through the [OS identity broker](/docs/third-party/claude-desktop/entra-broker) on Windows and macOS instead of the sy
+2 −0 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+5−1
claude-docschanged
third-party/claude-desktop/telemetry
[`otlpHeaders`](/docs/third-party/claude-desktop/configuration#otlpheaders) is a JSON object that maps each header name to its value, for example `{"Authorization":"Bearer <token>"
[`otlpHeaders`](/docs/third-party/claude-desktop/configuration#otlpheaders) is a JSON object that maps each header name to its value, for example `{"Authorization":"Bearer <token>"
For a collector credential that cannot be a static header, [`otlpHeadersHelper`](/docs/third-party/claude-desktop/configuration#otlpheadershelper) names a script on the device that
With [`updateViaUpdatesHost`](/docs/third-party/claude-desktop/configuration#updateviaupdateshost) set to `true`, the app reads the update feed from `releases.claude.com` instead o
+5 −1 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/local-access
±changed
+12−2
claude-docschanged
third-party/claude-desktop/local-access
A leading `~` expands to the user's home directory, so a single profile can express per-user roots like `~/Documents/Claude` across the fleet.
A leading `~` expands to the user's home directory, so a single profile can express per-user roots like `~/Documents/Claude` across the fleet. A path may also reference one of a fi
Each entry is either a plain path string or an object with these fields:
+12 −2 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+7−6
claude-docschanged
third-party/claude-desktop/gateway
```yaml theme={null}
```yaml theme={null} theme={null} theme={null} theme={null}
| Setting | MDM key | Required | Description
| ---------------------- | ------------------------- | --------------------------- | -----------------------------------------------------------------------------------------------
| Credential kind | `inferenceCredentialKind` | Yes — must be `interactive` | Selects sign-in instead of an API key.
+7 −6 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/foundry
±changed
+1−1
claude-docschanged
third-party/claude-desktop/foundry
`inferenceFoundryTenantId` and `inferenceFoundryClientId` can be set only via an MDM profile, not via a bootstrap server. `inferenceFoundryAuthFlow` can be set via either.
`inferenceFoundryTenantId`, `inferenceFoundryClientId`, and `inferenceFoundryAuthFlow` can be set through an MDM profile or a [bootstrap server](/docs/third-party/claude-desktop/bo
+1 −1 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/extensions
±changed
+14−13
claude-docschanged
third-party/claude-desktop/extensions
For a server whose OAuth sign-in goes to Microsoft Entra ID, you can run that sign-in through the [OS identity broker](/docs/third-party/claude-desktop/entra-broker) instead of the
To write the configuration by hand instead, add the repository to the [`allowedPluginMarketplaces`](/docs/third-party/claude-desktop/configuration) configuration key. The key is re
To write the configuration by hand instead, add the repository to the [`allowedPluginMarketplaces`](/docs/third-party/claude-desktop/configuration) configuration key. The key is re
* **Connectors:** install local desktop extensions (`.mcpb`) from the Connectors settings page
+14 −13 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/entra-broker
±changed
+11−6
claude-docschanged
third-party/claude-desktop/entra-broker
Several Claude Desktop on 3P features authenticate to Microsoft Entra ID, including the Microsoft Foundry inference provider and the Microsoft 365 connector. Each of these can run
Several Claude Desktop on 3P features can authenticate to Microsoft Entra ID, including the Microsoft Foundry inference provider, gateway and Workforce Identity sign-in when Entra
| Feature | How to enable it | Page |
| ------------------------------------ | ------------------------------------------ | -------------------------------------------------------------------------------- |
| Microsoft Foundry inference provider | Set `inferenceFoundryAuthFlow` to `broker` | [Microsoft Foundry](/docs/third-party/claude-desktop/foundry#in-app-entra-id-sign-in) |
+11 −6 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/credential-helper
±changed
+1−1
claude-docschanged
third-party/claude-desktop/credential-helper
The helper's output is cached for `inferenceCredentialHelperTtlSec` seconds (default 3600). After expiry it re-runs at the next session start.
The helper's output is cached for `inferenceCredentialHelperTtlSec` seconds (default 3600). Claude Desktop checks the cached credential's expiry before each turn and, when it has e
+1 −1 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+18−18
claude-docschanged
third-party/claude-desktop/configuration
| Documented type | What to write | Example |
| ---------------- | ---------------------------------------------------------------------- | --------------------------------------------- |
| string | Plain string | `vertex` |
| boolean | `"true"` or `"false"` (or `1` / `0`) | `"true"` |
| integer | Decimal string | `"3600"` |
+18 −18 lines
Recorded here 14 Aug 2026 19:25 UTC
claude-code
tools-reference
±changed
+5−5
claude-codechanged
tools-reference
| `Agent` | Spawns a [subagent](/docs/en/sub-agents) with its own context window to handle a task. See [Agent tool behavior](#agent-tool-behavior)
| `Agent` | Spawns a [subagent](/docs/en/sub-agents) with its own context window to handle a task. With [agent teams](/docs/en/agent-teams) enabled, a call that carr
The Agent tool spawns a subagent in a separate context window. The subagent works through its task autonomously, then returns a single text result to the parent conversation. The p
The Agent tool spawns a subagent in a separate context window. The subagent works through its task autonomously, then returns a single text result to the parent conversation. The p
The same Agent tool also launches [forked subagents](/docs/en/sub-agents#fork-the-current-conversation) wherever [fork mode](/docs/en/sub-agents#turn-fork-mode-on-or-off) is on. A
+5 −5 lines
Recorded here 14 Aug 2026 19:23 UTC
claude-code
sub-agents
±changed
+15−9
claude-codechanged
sub-agents
* Where [fork mode](#turn-fork-mode-on-or-off) is on, as it is by default in an interactive session, Claude Code runs the subagent in the background, forks and named subagents alik
* Where [fork mode](#turn-fork-mode-on-or-off) is on, as it is by default in an interactive session, Claude Code runs the subagent in the background, forks and non-fork subagents a
### Subagent names
+15 −9 lines
Recorded here 14 Aug 2026 19:23 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
Multiple independent Claude Code sessions coordinated by a team lead, with a shared task list and peer-to-peer messaging. Unlike [subagents](#subagent), which run within a single s
Multiple independent Claude Code sessions coordinated by a team lead, with a shared task list and peer-to-peer messaging. Unlike [subagents](#subagent), which run within a single s
+1 −1 lines
Recorded here 14 Aug 2026 19:23 UTC
claude-code
agent-teams
±changed
+36−5
claude-codechanged
agent-teams
Enabling agent teams also changes ordinary delegation. Claude may [name a subagent](/docs/en/sub-agents#subagent-names) on its own, and while agent teams are enabled, a subagent th
Spawning teammates also requires an interactive session. In [non-interactive mode](/docs/en/headless) with the `-p` flag, including Agent SDK sessions, Claude doesn't spawn teammat
An agent team forms when the first teammate is spawned, with the main session acting as the lead. There are two ways teammates get spawned:
+36 −5 lines
Recorded here 14 Aug 2026 19:23 UTC
claude-code
best-practices
±changed
+3−29
claude-codechanged
best-practices
The `/init` command analyzes your codebase to detect build systems, test frameworks, and code patterns, giving you a solid foundation to refine.
CLAUDE.md files can import additional files using `@path/to/import` syntax:
```markdown CLAUDE.md theme={null}
+3 −29 lines
Recorded here 14 Aug 2026 19:15 UTC
claude-code
troubleshoot-install
±changed
+1−38
claude-codechanged
troubleshoot-install
The installer couldn't reach the download server. This typically means `downloads.claude.ai` is blocked on your network.
**Solutions:**
1. **Test connectivity directly**:
+1 −38 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
| `TodoWrite` | Manages the session task checklist. Disabled by default as of v2.1.142 in favor of `TaskCreate`, `TaskGet`, `TaskList`, and `TaskUpdate`. Set `CLAUDE_COD
| `TodoWrite` | Manages the session task checklist. Disabled by default in favor of `TaskCreate`, `TaskGet`, `TaskList`, and `TaskUpdate`. Set `CLAUDE_CODE_ENABLE_TASKS=
+1 −1 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
sessions
±changed
+0−2
claude-codechanged
sessions
These pages cover related session and parallelism mechanics:
+0 −2 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
plugins-reference
±changed
+1−1
claude-codechanged
plugins-reference
A plugin that has a `SKILL.md` at its root, no `skills/` subdirectory, and no `skills` manifest field is automatically loaded as a single-skill plugin in Claude Code v2.1.142 and l
A plugin that has a `SKILL.md` at its root, no `skills/` subdirectory, and no `skills` manifest field is automatically loaded as a single-skill plugin. You do not need to set `"ski
+1 −1 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
jetbrains
±changed
+0−4
claude-codechanged
jetbrains
<Note>
After installing the plugin, you may need to restart your IDE completely for it to take effect.
</Note>
+0 −4 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
how-claude-code-works
±changed
+0−2
claude-codechanged
how-claude-code-works
This guide focuses on the terminal. Claude Code also runs in [VS Code](/docs/en/vs-code), [JetBrains IDEs](/docs/en/jetbrains), and other environments.
+0 −2 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
features-overview
±changed
+0−2
claude-codechanged
features-overview
Example: An MCP server connects Claude to your database. A skill teaches Claude your data model, common query patterns, and which tables to use for different tasks.
+0 −2 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
errors
±changed
+1−6
claude-codechanged
errors
Depending on how far the response had progressed, Claude Code retries the request, keeps what Claude produced, or ends the turn:
* If Claude hasn't completed any part of the response yet, including its thinking, Claude Code treats the failure as a dropped connection and [retries the request automatically](#a
* If Claude has finished thinking but hasn't started any text or tool call, Claude Code re-issues the request up to two times in quick succession, then ends the turn with `Connecti
* If Claude has completed a block of text or a tool call, or has started one after finishing its thinking, but hasn't finished the response, Claude Code keeps what Claude completed
+1 −6 lines
Recorded here 14 Aug 2026 19:13 UTC
claude-code
env-vars
±changed
+2−2
claude-codechanged
env-vars
| `CLAUDE_CODE_ENABLE_TASKS` | Controls whether sessions use the structured Task tools (`TaskCreate`, `TaskUpdate`, `TaskGet`, `TaskList`) or the legac
| `CLAUDE_CODE_ENABLE_TASKS` | Controls whether sessions use the structured Task tools (`TaskCreate`, `TaskUpdate`, `TaskGet`, `TaskList`) or the legac
| `MCP_CONNECTION_NONBLOCKING` | Controls whether startup waits for MCP servers to connect before the first query. MCP startup is non-blocking by default
| `MCP_CONNECTION_NONBLOCKING` | Controls whether startup waits for MCP servers to connect before the first query. MCP startup is non-blocking by default
+2 −2 lines
Recorded here 14 Aug 2026 19:13 UTC
api
managed-agents/skills
±changed
+16−12
apichanged
managed-agents/skills
```text wrap
your-repo/
├── .claude/
│ └── skills/
│ ├── code-review/
+16 −12 lines
Recorded here 14 Aug 2026 19:03 UTC
api
manage-claude/inference-hooks-endpoint
±changed
+2−2
apichanged
manage-claude/inference-hooks-endpoint
The smallest working integration is a server that reads each request and allows it. Run one of the following servers, expose it at a public `https://` URL (for example, behind a TL
The smallest working integration is a server that reads each request and allows it. Run one of the following servers, expose it at a public `https://` URL (for example, behind a TL
Host your AI security server where Anthropic can reach it: an `https://` URL on port 443, on a publicly routable host (private, loopback, and carrier-grade NAT ranges are refused a
Host your AI security server where Anthropic can reach it: an `https://` URL on port 443, on a publicly routable host (private, loopback, and carrier-grade NAT ranges are refused a
+2 −2 lines
Recorded here 14 Aug 2026 19:03 UTC
api
manage-claude/inference-hooks-configuration
±changed
+1−1
apichanged
manage-claude/inference-hooks-configuration
* An AI security server HTTPS endpoint that accepts verdict requests: an `https://` URL on port 443, on a publicly routable host, reachable without redirects. For the full [hosting
* An AI security server HTTPS endpoint that accepts verdict requests: an `https://` URL on port 443, on a publicly routable host, reachable without redirects. Reverse-tunnel hosts
+1 −1 lines
Recorded here 14 Aug 2026 19:03 UTC
api
manage-claude/cmek
±changed
+12−13
apichanged
manage-claude/cmek
* In Claude Managed Agents, [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) and [dreams](https://platform.claude.com/docs/en/managed-agents/dreams) are d
| APIs | Tools and features |
| -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |
| Messages | Web search |
| Models | Web fetch |
+12 −13 lines
Recorded here 14 Aug 2026 19:03 UTC
api
build-with-claude/prompt-engineering/prompting-claude-opus-5
±changed
+2−0
apichanged
build-with-claude/prompt-engineering/prompting-claude-opus-5
If your harness is Claude Code or the Claude Agent SDK, the deterministic caps are the `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` and `CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS` environment
+2 −0 lines
Recorded here 14 Aug 2026 19:03 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+14−2
apichanged
agents-and-tools/tool-use/code-execution-tool
When Claude creates files during code execution, each created file's ID appears in the code execution tool result, and you can download it with the [Files API](https://platform.cla
When Claude saves files to its output directory during code execution (see [How generated files are captured](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-exe
#### How generated files are captured
Each `bash_code_execution` call gets a new, empty directory, available to the command as `$OUTPUT_DIR`. When the command finishes, the files at the top level of that directory are
+14 −2 lines
Recorded here 14 Aug 2026 19:03 UTC
api
agents-and-tools/tool-use/advisor-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/advisor-tool
This pattern fits long-horizon agentic workloads (coding agents, computer use, multistep research pipelines) where most turns are mechanical but having an excellent plan is crucial
This pattern fits long-horizon agentic workloads (coding agents, computer use, multistep research pipelines) where most turns are mechanical but having an excellent plan is crucial
+1 −1 lines
Recorded here 14 Aug 2026 19:03 UTC
api
agents-and-tools/agent-skills/overview
±changed
+7−8
apichanged
agents-and-tools/agent-skills/overview
```text
pdf-processing/
├── SKILL.md (main instructions)
├── FORMS.md (form-filling guide)
├── REFERENCE.md (detailed API reference)
+7 −8 lines
Recorded here 14 Aug 2026 19:03 UTC
api
agents-and-tools/agent-skills/best-practices
±changed
+34−28
apichanged
agents-and-tools/agent-skills/best-practices
```text
pdf/
├── SKILL.md # Main instructions (loaded when triggered)
├── FORMS.md # Form-filling guide (loaded as needed)
├── reference.md # API reference (loaded as needed)
+34 −28 lines
Recorded here 14 Aug 2026 19:03 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.