Documentation 2026-11-11 22:59 UTC to 2026-11-12 23:02 UTC

254| Source | When it loads | Impact |254| Source | When it loads | Impact |

255| :- | :- | :- |255| :- | :- | :- |

256| **System prompt** | Every request | Small fixed cost, always present |256| **System prompt** | Every request | Small fixed cost, always present |

257| **CLAUDE.md files** | Session start, via [`settingSources`](https://code.claude.com/docs/en/agent-sdk/claude-code-features) | Full content in every request (but prompt-cached, so only the first request pays full cost) |257| **CLAUDE.md files** | Session start, via [`settingSources`](https://code.claude.com/docs/en/agent-sdk/claude-code-features) | Full content in every request (but prompt-cached) |

258| **Tool definitions** | Every request for core built-in tools such as Bash, Read, and Edit; on demand for MCP tools and other built-in tools, which [tool search](https://code.claude.com/docs/en/agent-sdk/mcp.md#mcp-tool-search) defers by default | Every schema loads upfront in the cases under [Configure tool search](https://code.claude.com/docs/en/agent-sdk/tool-search.md#configure-tool-search) |258| **Tool definitions** | Every request for core built-in tools such as Bash, Read, and Edit; on demand for MCP tools and other built-in tools, which [tool search](https://code.claude.com/docs/en/agent-sdk/mcp.md#mcp-tool-search) defers by default | Every schema loads upfront in the cases under [Configure tool search](https://code.claude.com/docs/en/agent-sdk/tool-search.md#configure-tool-search) |

259| **Conversation history** | Accumulates over turns | Grows with each turn: prompts, responses, tool inputs, tool outputs |259| **Conversation history** | Accumulates over turns | Grows with each turn: prompts, responses, tool inputs, tool outputs |

260| **Skill descriptions** | Session start, via setting sources | Short summaries; full content loads only when invoked |260| **Skill descriptions** | Session start, via setting sources | Short summaries; full content loads only when invoked |

298 298 

299### Mirror writes are best-effort299### Mirror writes are best-effort

300 300 

301If `append()` rejects, the SDK retries the batch up to two more times with a short backoff, for at most three attempts in total. A call that times out isn't retried, since the original call may still land. If the batch still fails, the SDK logs the error, emits a `{ type: "system", subtype: "mirror_error" }` message into the iterator, drops the batch, and continues the query. Because a retried batch can re-deliver entries that already landed, deduplicate by `entry.uuid` in your `append()` implementation.301If `append()` rejects, the SDK retries the batch up to two more times with a short backoff, for at most three attempts in total. A call that times out isn't retried, since the original call may still land. Because a retried batch can re-deliver entries that already landed, deduplicate by `entry.uuid` in your `append()` implementation, and keep every entry that has no `uuid`.

302 302 

303A store outage doesn't interrupt the agent, since the subprocess writes locally first. Monitor for `mirror_error` if you need to detect store data loss. On a run [resumed from the store](#resume-from-the-store), a dropped batch has no surviving copy once the run ends.303If the batch still fails, the SDK logs the error, emits a `{ type: "system", subtype: "mirror_error" }` message into the iterator, drops the batch, and continues the query. A store outage doesn't interrupt the agent, since the subprocess writes locally first. Monitor for `mirror_error` to detect store data loss. On a run [resumed from the store](#resume-from-the-store), a dropped batch has no surviving copy once the run ends.

304 304 

305### `getSessionMessages` returns the post-compaction chain305### `getSessionMessages` returns the post-compaction chain

306 306 

512 512 

513### Run Mantle alongside the Invoke API513### Run Mantle alongside the Invoke API

514 514 

515The models available to you on Mantle may not include every model you use today. Setting both `CLAUDE_CODE_USE_BEDROCK` and `CLAUDE_CODE_USE_MANTLE` lets Claude Code call both endpoints from the same session. Model IDs that match the Mantle format are routed to Mantle, and all other model IDs go to the Amazon Bedrock Invoke API.515The models available to you on Mantle may not include every model you use today. If you connect without a gateway, set both `CLAUDE_CODE_USE_BEDROCK` and `CLAUDE_CODE_USE_MANTLE` to call Mantle and the Invoke API from the same session. Model IDs that match the Mantle format are routed to Mantle, and all other model IDs go to the Amazon Bedrock Invoke API.

516 516 

517```bash theme={null}517```bash theme={null}

518export CLAUDE_CODE_USE_BEDROCK=1518export CLAUDE_CODE_USE_BEDROCK=1

618* If the error names a `bedrock-mantle:` action, grant your IAM identity that action.618* If the error names a `bedrock-mantle:` action, grant your IAM identity that action.

619* If the error names no action and your credentials are valid, your AWS account has not been granted access to the model you requested. Contact your AWS account team to request access.619* If the error names no action and your credentials are valid, your AWS account has not been granted access to the model you requested. Contact your AWS account team to request access.

620 620 

621A `400` that names the model ID means that model isn't served on Mantle. Mantle has its own model lineup separate from the standard Amazon Bedrock catalog, so inference profile IDs such as `us.anthropic.claude-sonnet-4-6` don't work. Use a Mantle-format ID, or enable [both endpoints](#run-mantle-alongside-the-invoke-api) so Claude Code sends inference profile IDs to the Invoke API.621A `400` that names the model ID means that model isn't served on Mantle. Mantle has its own model lineup separate from the standard Amazon Bedrock catalog, so inference profile IDs such as `us.anthropic.claude-sonnet-4-6` don't work.

622 

623To clear the error:

624 

625* **Without a gateway**: use a [Mantle-format ID](#select-a-mantle-model) that Mantle serves, or [run Mantle alongside the Invoke API](#run-mantle-alongside-the-invoke-api) to send IDs in other formats to that API.

626* **Through a gateway**: ask its operator which model IDs to use.

622 627 

623## Additional resources628## Additional resources

624 629 

315 {315 {

316 "matcher": "Edit|Write",316 "matcher": "Edit|Write",

317 "hooks": [317 "hooks": [

318 { "type": "command", "command": "npx prettier --write --ignore-unknown \"$(jq -r '.tool_input.file_path')\"" }318 { "type": "command", "command": "f=$(jq -r '.tool_input.file_path') && npx prettier --write --ignore-unknown \"$f\"" }

319 ]319 ]

320 }320 }

321 ]321 ]

92 92 

93Beyond the binary, the image needs:93Beyond the binary, the image needs:

94 94 

95* **A glibc-based image**: the glibc build's only dynamic dependencies are glibc libraries. Musl-based images need the `linux-x64-musl` or `linux-arm64-musl` build plus additional packages; see [Alpine Linux setup](https://code.claude.com/docs/en/setup.md#alpine-linux-and-musl-based-distributions).95* **A glibc-based image**: the glibc build's only dynamic dependencies are glibc libraries. Musl-based images need the `linux-x64-musl` or `linux-arm64-musl` build, whose only dynamic dependency is musl.

96* **A writable state directory**: the gateway runs as any user, but minimal images have no writable home. Set `CLAUDE_CONFIG_DIR` to a writable path such as `/tmp/.claude`.96* **A writable state directory**: the gateway runs as any user, but minimal images have no writable home. Set `CLAUDE_CONFIG_DIR` to a writable path such as `/tmp/.claude`.

97* **The container command**: `claude gateway --config /etc/claude/gateway.yaml`, with the config file mounted read-only and secrets supplied as environment variables; the gateway listens on `listen.port`, default `8080`.97* **The container command**: `claude gateway --config /etc/claude/gateway.yaml`, with the config file mounted read-only and secrets supplied as environment variables; the gateway listens on `listen.port`, default `8080`.

98 98 

148 148 

149#### Turn off scripts in SSH and WSL previews for your organization149#### Turn off scripts in SSH and WSL previews for your organization

150 150 

151To keep [HTML previews in SSH and WSL sessions](#preview-html-files-in-ssh-and-wsl-sessions) from running scripts, set the [`disableBrowserExternalNavigation` managed setting](#managed-settings) to `true`. With this setting, users also can't [browse external sites](#restrict-external-browsing-for-your-organization) in the Browser pane.151To keep [HTML previews in SSH and WSL sessions](#preview-html-files-in-ssh-and-wsl-sessions) from running scripts, set the [`disableRemotePreviewScripts` managed setting](#managed-settings) to `true`. Users can still browse external sites. Requires Claude Desktop v5.1231.0 or later.

152 152 

153Set it in your [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md), or in a [Claude Code MDM policy or managed settings file](https://code.claude.com/docs/en/managed-settings.md#where-each-mechanism-stores-the-policy) on the computer that runs Desktop. Desktop doesn't read it from the remote machine or the WSL distribution. With a [third-party provider](https://code.claude.com/docs/en/third-party-integrations.md), use the MDM policy or the file.153> [!NOTE]

154>

155> Earlier versions ignore `disableRemotePreviewScripts`. To stop the scripts there, update Desktop, or also set `disableBrowserExternalNavigation` to `true`. Users then [can't browse external sites](#restrict-external-browsing-for-your-organization) on any computer that receives `disableBrowserExternalNavigation`.

156 

157Set each key in your [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md), or in a [Claude Code MDM policy or managed settings file](https://code.claude.com/docs/en/managed-settings.md#where-each-mechanism-stores-the-policy) on the computer that runs Desktop. Desktop doesn't read these keys from the remote machine, the WSL distribution, a [`policyHelper`](https://code.claude.com/docs/en/settings-reference#policyhelper), or [Desktop's own policies](#device-management-policies). With a [third-party provider](https://code.claude.com/docs/en/third-party-integrations.md), use the MDM policy or the file.

154 158 

155> [!WARNING]159> [!WARNING]

156>160>

160 164 

161Then have users restart Desktop to make sure that the setting applies, and tell them what to expect:165Then have users restart Desktop to make sure that the setting applies, and tell them what to expect:

162 166 

163* **Files they open**: the preview doesn't run scripts, so charts and tables that scripts draw stay empty167* **Files they open**: the preview doesn't run scripts, so charts and tables that scripts draw stay empty. Its notice starts with `This preview doesn't run scripts`.

164* **Previews that are running scripts**: if Desktop picks up the setting before the restart, they close. Users see `This preview closed because scripts are turned off for previews. Open the file again to view it without scripts.`168* **Previews that are running scripts**: if Desktop picks up the setting before the restart, they close. Users see `This preview closed because scripts are turned off for previews. Open the file again to view it without scripts.`

165* **Files they export**: if a user [exports a file](#preview-html-files-in-ssh-and-wsl-sessions) and opens it in a browser, its scripts run there, with or without this setting169* **Files they export**: if a user [exports a file](#preview-html-files-in-ssh-and-wsl-sessions) and opens it in a browser, its scripts run there, with or without this setting

166 170 

171##### Check a computer for scripts that still run

172 

173After the restart, open an HTML file from an SSH or WSL session on that computer. If the notice above the preview starts with `This preview doesn't load anything from the web`, scripts still run there. Check [Desktop's version](#check-your-version), where you put the key, and that its value is the JSON Boolean `true`.

174 

167### Browse external sites175### Browse external sites

168 176 

169The Browser pane is a tabbed browser, so you can open documentation, issue trackers, or any other site next to your running app. To open the Browser, press **Cmd+Shift+B** on macOS or **Ctrl+Shift+B** on Windows, or click **Browser** in the session's title bar. You can sign in to sites in the pane, including popup sign-in flows such as Google OAuth.177The Browser pane is a tabbed browser, so you can open documentation, issue trackers, or any other site next to your running app. To open the Browser, press **Cmd+Shift+B** on macOS or **Ctrl+Shift+B** on Windows, or click **Browser** in the session's title bar. You can sign in to sites in the pane, including popup sign-in flows such as Google OAuth.

2037| `browserExternalPageTools` | set to `"disabled"` to prevent Claude from using tools to read or act on external pages in the [Browser pane](#browse-external-sites). Users can still navigate to external sites themselves, and local dev server previews are unaffected. |2045| `browserExternalPageTools` | set to `"disabled"` to prevent Claude from using tools to read or act on external pages in the [Browser pane](#browse-external-sites). Users can still navigate to external sites themselves, and local dev server previews are unaffected. |

2038| `disableMobileSimulatorTools` | set to `true` to block Claude's tools for controlling and capturing devices in the [iOS Simulator pane](https://code.claude.com/docs/en/desktop-ios-simulator.md#turn-off-simulator-access). The pane stays usable for the user's own taps; only Claude's access is removed. The value must be the JSON boolean `true`; the string `"true"` is ignored. |2046| `disableMobileSimulatorTools` | set to `true` to block Claude's tools for controlling and capturing devices in the [iOS Simulator pane](https://code.claude.com/docs/en/desktop-ios-simulator.md#turn-off-simulator-access). The pane stays usable for the user's own taps; only Claude's access is removed. The value must be the JSON boolean `true`; the string `"true"` is ignored. |

2039| `disableBrowserExternalNavigation` | set to `true` to turn off external browsing in the [Browser pane](#browse-external-sites) entirely. Neither users nor Claude can navigate to external sites, and localhost dev server previews are unaffected. HTML previews in SSH and WSL sessions [don't run scripts](#turn-off-scripts-in-ssh-and-wsl-previews-for-your-organization). The value must be the JSON boolean `true`; the string `"true"` is ignored. |2047| `disableBrowserExternalNavigation` | set to `true` to turn off external browsing in the [Browser pane](#browse-external-sites) entirely. Neither users nor Claude can navigate to external sites, and localhost dev server previews are unaffected. HTML previews in SSH and WSL sessions [don't run scripts](#turn-off-scripts-in-ssh-and-wsl-previews-for-your-organization). The value must be the JSON boolean `true`; the string `"true"` is ignored. |

2048| `disableRemotePreviewScripts` | set to `true` to [turn off only the scripts in HTML previews](#turn-off-scripts-in-ssh-and-wsl-previews-for-your-organization) in SSH and WSL sessions. Desktop doesn't read it from the remote machine or the WSL distribution. The value must be the JSON boolean `true`; the string `"true"` is ignored. Requires Claude Desktop v5.1231.0 or later. |

2040| `sshConfigs` | pre-configure [SSH connections](#pre-configure-ssh-connections-for-your-team) that appear in the environment selector. Users can't delete managed connections or edit anything but their own **Worktree folder**. |2049| `sshConfigs` | pre-configure [SSH connections](#pre-configure-ssh-connections-for-your-team) that appear in the environment selector. Users can't delete managed connections or edit anything but their own **Worktree folder**. |

2041| `sshHostCommands` | give users [SSH connections whose host comes from a command](#distribute-commands-to-your-team), alongside their own. Desktop reads it from the managed settings file or MDM policy on the computer, and ignores it in [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md). Requires Claude Desktop v3.6556.0 or later on macOS or Linux, or v4.16336.0 or later on Windows, signed in with a Claude account. On Windows, Desktop also has to [connect through the OpenSSH client](#use-your-ssh-configuration). |2050| `sshHostCommands` | give users [SSH connections whose host comes from a command](#distribute-commands-to-your-team), alongside their own. Desktop reads it from the managed settings file or MDM policy on the computer, and ignores it in [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md). Requires Claude Desktop v3.6556.0 or later on macOS or Linux, or v4.16336.0 or later on Windows, signed in with a Claude account. On Windows, Desktop also has to [connect through the OpenSSH client](#use-your-ssh-configuration). |

2042| `sshHostAllowlist` | restrict [SSH sessions](#restrict-which-ssh-hosts-users-can-connect-to) to hosts whose resolved hostname matches one of these patterns. Read from managed settings only. |2051| `sshHostAllowlist` | restrict [SSH sessions](#restrict-which-ssh-hosts-users-can-connect-to) to hosts whose resolved hostname matches one of these patterns. Read from managed settings only. |

2044| `disableSshSavedPasswords` | set to `true` to stop Desktop from offering to remember SSH passwords and from using or showing the ones it saved earlier. Turning it on doesn't delete them. Read from managed settings only. Requires Claude Desktop v1.49585.0 or later. |2053| `disableSshSavedPasswords` | set to `true` to stop Desktop from offering to remember SSH passwords and from using or showing the ones it saved earlier. Turning it on doesn't delete them. Read from managed settings only. Requires Claude Desktop v1.49585.0 or later. |

2045| `managedMcpServers` | push MCP server configurations to all users. Available in third-party (3P) Desktop deployments only. In each entry, set a transport of `"http"`, `"sse"`, or `"stdio"`, connection details, and optionally a `toolPolicy` map to restrict which of that server's tools users can invoke. Deliver it through the managed settings file, MDM, or a Claude apps gateway policy's [`desktop` block](https://code.claude.com/docs/en/claude-apps-gateway-config#claude-desktop-overlay), since 3P deployments don't receive admin-console settings. To deliver it through the gateway, you need Claude Code v2.1.232 or later on the gateway server. This is the desktop app's own key; Claude Code reads a [same-named managed setting](https://code.claude.com/docs/en/managed-mcp.md#provide-servers-through-managed-settings) of its own, with a different entry shape. |2054| `managedMcpServers` | push MCP server configurations to all users. Available in third-party (3P) Desktop deployments only. In each entry, set a transport of `"http"`, `"sse"`, or `"stdio"`, connection details, and optionally a `toolPolicy` map to restrict which of that server's tools users can invoke. Deliver it through the managed settings file, MDM, or a Claude apps gateway policy's [`desktop` block](https://code.claude.com/docs/en/claude-apps-gateway-config#claude-desktop-overlay), since 3P deployments don't receive admin-console settings. To deliver it through the gateway, you need Claude Code v2.1.232 or later on the gateway server. This is the desktop app's own key; Claude Code reads a [same-named managed setting](https://code.claude.com/docs/en/managed-mcp.md#provide-servers-through-managed-settings) of its own, with a different entry shape. |

2046 2055 

2047If you turn a feature off with `browserExternalPageTools`, `disableMobileSimulatorTools`, or `disableBrowserExternalNavigation` in a computer's [highest-ranked MDM policy or managed settings file](https://code.claude.com/docs/en/managed-settings.md#how-claude-code-combines-managed-sources), the feature stays off there. It stays off even when your [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md) leave that key unset or allow the feature. Don't use a user-level `HKCU` registry value for this. To turn the feature back on, remove the value wherever you set it. Requires Claude Desktop v4.4212.0 or later.2056If you turn a feature off with one of these four keys in a computer's [highest-ranked MDM policy or managed settings file](https://code.claude.com/docs/en/managed-settings.md#how-claude-code-combines-managed-sources), the feature stays off there:

2057 

2058* **`browserExternalPageTools`, `disableMobileSimulatorTools`, `disableBrowserExternalNavigation`**: requires Claude Desktop v4.4212.0 or later

2059* **`disableRemotePreviewScripts`**: requires Claude Desktop v5.1231.0 or later

2060 

2061It stays off even when your [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md) leave that key unset or allow the feature. Don't use a user-level `HKCU` registry value for this. To turn the feature back on, remove the value wherever you set it.

2048 2062 

2049Which managed settings reach a Desktop session depends on where that session runs. Model restrictions such as [`availableModels`](https://code.claude.com/docs/en/model-config#restrict-model-selection) are enforced in Desktop's Claude Code sessions the same way as in the terminal CLI; see [surface coverage](https://code.claude.com/docs/en/model-config.md#surface-coverage).2063Which managed settings reach a Desktop session depends on where that session runs. Model restrictions such as [`availableModels`](https://code.claude.com/docs/en/model-config#restrict-model-selection) are enforced in Desktop's Claude Code sessions the same way as in the terminal CLI; see [surface coverage](https://code.claude.com/docs/en/model-config.md#surface-coverage).

2050 2064 

2109>2123>

2110> Check the `forceLoginOrgUUID` value before you deploy it. If the ID isn't your organization's, people in your organization can't use Claude Desktop unless they also belong to an organization with that ID. To recover, deploy the correct ID and have them restart Claude Desktop.2124> Check the `forceLoginOrgUUID` value before you deploy it. If the ID isn't your organization's, people in your organization can't use Claude Desktop unless they also belong to an organization with that ID. To recover, deploy the correct ID and have them restart Claude Desktop.

2111 2125 

2112If you set `forceLoginMethod` and `forceLoginOrgUUID` in Claude Code's [managed settings](https://code.claude.com/docs/en/managed-settings.md), you don't change the Claude Desktop sign-in screen.2126If you set `forceLoginMethod` and `forceLoginOrgUUID` in Claude Code's [managed settings](https://code.claude.com/docs/en/managed-settings.md), you don't change the Claude Desktop sign-in screen. A person can still use Claude Desktop with their own Claude API key or [Claude Console account](https://claude.com/docs/third-party/claude-desktop/claude-api#which-devices-offer-the-claude-api-account-sign-in), and run Code tab sessions that way.

2127 

2128To stop that, also deploy `forceLoginOrgUUID` in the Claude Desktop policy (in `HKLM` on Windows), with your claude.ai organization ID. Unless the policy itself [selects the Claude API](https://claude.com/docs/third-party/claude-desktop/claude-api#choose-an-authentication-approach), Claude Desktop stops using a person's own API key or Console account at the app's next launch.

2129 

2130Check two cases before you deploy it:

2131 

2132* **Claude Console organizations**: don't deploy `forceLoginOrgUUID` on its own with a Claude Console organization's ID, or you'd lock your people out of Claude Desktop. See [Which devices offer the Claude API account sign-in](https://claude.com/docs/third-party/claude-desktop/claude-api#which-devices-offer-the-claude-api-account-sign-in) instead.

2133* **Enterprise Admin Console**: if it delivers your computers' Claude Desktop configuration, update them to Claude Desktop v2.37337.0 or later first, because earlier versions ignore it once this key is set. See [Keep a device on its managed profile](https://claude.com/docs/third-party/claude-desktop/admin-console#keep-a-device-on-its-managed-profile).

2113 2134 

2114### Network access requirements2135### Network access requirements

2115 2136 

5466This conversation is already open in another running Claude session — use that one, or close it and try again5466This conversation is already open in another running Claude session — use that one, or close it and try again

5467```5467```

5468 5468 

5469* **`running in another terminal`**: a terminal holds the conversation, for example one where you resumed it with `claude --resume` or `/resume`. The row also shows `Open in a terminal`.5469* **`running in another terminal`**: a process other than a background session holds the conversation, for example a `claude -p` run, or a terminal where you resumed it with `claude --resume` or `/resume`. The row also shows `Open in a terminal`.

5470* **`already open in another running Claude session`**: another non-interactive Claude Code process holds it, for example a [background session](https://code.claude.com/docs/en/agent-view.md#the-supervisor-process) process for the same conversation that hasn't exited yet.5470* **`already open in another running Claude session`**: another [background session](https://code.claude.com/docs/en/agent-view.md#the-supervisor-process) holds it.

5471 5471 

5472**What to do:**5472**What to do:**

5473 5473 

5474* Continue the conversation in the process that has it open, or exit that process and open the row again5474* For `running in another terminal`: continue in that terminal, or exit that process or let it finish, and then try again

5475* For `already open in another running Claude session`: use that session, or stop it and then try again

5475 5476 

5476Before v2.1.248, only the `already open in another running Claude session` refusal existed: a conversation resumed in a terminal didn't count as open, and opening the row started a second Claude Code process writing to the same conversation.5477Before v2.1.248, only the `already open in another running Claude session` refusal existed: a conversation resumed in a terminal didn't count as open, and opening the row started a second Claude Code process writing to the same conversation.

5477 5478 

98 98 

99* **Pro, Max, and Ultra**: you pay for fast mode from your usage credits. Go to [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, where the **Usage credits** section shows how much you've spent in usage credits this month. That figure includes fast mode but doesn't break it out separately.99* **Pro, Max, and Ultra**: you pay for fast mode from your usage credits. Go to [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, where the **Usage credits** section shows how much you've spent in usage credits this month. That figure includes fast mode but doesn't break it out separately.

100* **Team and Enterprise**: your organization pays for your fast mode usage from its usage credits. To see your own usage-credits spend, run [`/usage`](https://code.claude.com/docs/en/costs#check-your-usage-credits-spend). For where your organization sees that spend, see [Claude for Teams and Enterprise](https://code.claude.com/docs/en/costs.md#claude-for-teams-and-enterprise).100* **Team and Enterprise**: your organization pays for your fast mode usage from its usage credits. To see your own usage-credits spend, run [`/usage`](https://code.claude.com/docs/en/costs#check-your-usage-credits-spend). For where your organization sees that spend, see [Claude for Teams and Enterprise](https://code.claude.com/docs/en/costs.md#claude-for-teams-and-enterprise).

101* **Claude Console**: your organization pays for fast mode with the rest of its API usage. On the Console [Usage](https://platform.claude.com/usage) and [Cost](https://platform.claude.com/cost) pages, select **Speed (research preview)** in the **Group by** menu to separate fast mode from standard-speed usage. You see that option only when the selected date range includes fast mode usage.101* **Claude Console**: your organization pays for fast mode with the rest of its API usage. On the Console [Usage](https://platform.claude.com/usage) and [Cost](https://platform.claude.com/cost) pages, select **Speed** in the **Group by** menu to separate fast mode from standard-speed usage. You see that option only when the selected date range includes fast mode usage.

102 102 

103## Decide when to use fast mode103## Decide when to use fast mode

104 104 

3335 "hooks": [3335 "hooks": [

3336 {3336 {

3337 "type": "command",3337 "type": "command",

3338 "command": "bash -c 'jq -r .worktree_path | xargs rm -rf'"3338 "command": "bash -c 'p=$(jq -er .worktree_path) && rm -rf -- \"$p\"'"

3339 }3339 }

3340 ]3340 ]

3341 }3341 }

50 "PostToolUse": [50 "PostToolUse": [

51 {51 {

52 "matcher": "Edit|Write",52 "matcher": "Edit|Write",

53 "hooks": [{ "type": "command", "command": "jq -r '.tool_input.file_path' | xargs npx prettier --write" }]53 "hooks": [{ "type": "command", "command": "f=$(jq -r '.tool_input.file_path') && npx prettier --write --ignore-unknown \"$f\"" }]

54 }54 }

55 ],55 ],

56 "Notification": [56 "Notification": [

221 "hooks": [221 "hooks": [

222 {222 {

223 "type": "command",223 "type": "command",

224 "command": "jq -r '.tool_input.file_path' | xargs npx prettier --write"224 "command": "f=$(jq -r '.tool_input.file_path') && npx prettier --write --ignore-unknown \"$f\""

225 }225 }

226 ]226 ]

227 }227 }

36| `Esc` | Interrupt Claude, or close a dialog | Stop the current response or tool call mid-turn so you can redirect. Claude keeps the work done so far. If you have [messages queued](#queue-messages-while-claude-works), Claude Code sends them next. When a dialog is open, `Esc` closes the dialog. While a footer item is selected, such as a row in the [subagent panel](https://code.claude.com/docs/en/sub-agents.md#run-subagents-in-foreground-or-background) below the prompt, `Esc` [deselects it](https://code.claude.com/docs/en/keybindings.md#footer-actions) instead of interrupting. On a permission prompt, `Esc` declines the action, the same as [**No** without a comment](https://code.claude.com/docs/en/permissions.md#add-a-comment-when-you-answer-a-permission-prompt) |36| `Esc` | Interrupt Claude, or close a dialog | Stop the current response or tool call mid-turn so you can redirect. Claude keeps the work done so far. If you have [messages queued](#queue-messages-while-claude-works), Claude Code sends them next. When a dialog is open, `Esc` closes the dialog. While a footer item is selected, such as a row in the [subagent panel](https://code.claude.com/docs/en/sub-agents.md#run-subagents-in-foreground-or-background) below the prompt, `Esc` [deselects it](https://code.claude.com/docs/en/keybindings.md#footer-actions) instead of interrupting. On a permission prompt, `Esc` declines the action, the same as [**No** without a comment](https://code.claude.com/docs/en/permissions.md#add-a-comment-when-you-answer-a-permission-prompt) |

37| `Esc` + `Esc` | Clear input draft, or rewind | When the prompt input contains text, double `Esc` clears it and saves the draft to history so `Up` recalls it. When the input is empty, double `Esc` opens the [rewind menu](https://code.claude.com/docs/en/checkpointing.md) to restore or summarize code and conversation from a previous point |37| `Esc` + `Esc` | Clear input draft, or rewind | When the prompt input contains text, double `Esc` clears it and saves the draft to history so `Up` recalls it. When the input is empty, double `Esc` opens the [rewind menu](https://code.claude.com/docs/en/checkpointing.md) to restore or summarize code and conversation from a previous point |

38| `Ctrl+Enter` or `Ctrl+X Ctrl+S` | Send queued messages now | Sends your [queued messages](#queue-messages-while-claude-works), and your draft with them, right away. [When Claude Code sends what you queued](#when-claude-code-sends-what-you-queued) covers what happens to the turn Claude is working on. In [shell mode](#shell-mode-with-prefix), the key only queues your command. In terminals that don't report extended keys, `Ctrl+Enter` arrives as plain `Enter`; `Ctrl+X Ctrl+S` works in any terminal. Requires Claude Code v2.1.275 or later |38| `Ctrl+Enter` or `Ctrl+X Ctrl+S` | Send queued messages now | Sends your [queued messages](#queue-messages-while-claude-works), and your draft with them, right away. [When Claude Code sends what you queued](#when-claude-code-sends-what-you-queued) covers what happens to the turn Claude is working on. In [shell mode](#shell-mode-with-prefix), the key only queues your command. In terminals that don't report extended keys, `Ctrl+Enter` arrives as plain `Enter`; `Ctrl+X Ctrl+S` works in any terminal. Requires Claude Code v2.1.275 or later |

39| `Shift+Tab`, or `Alt+M` on Windows when the Node or Bun runtime doesn't enable VT input mode | Cycle permission modes | Cycle through `default` (labeled Manual in the mode indicator), `acceptEdits`, `plan`, and, when available, `bypassPermissions` and then `auto`. From `auto`, the first press switches to `default`. See [permission modes](https://code.claude.com/docs/en/permission-modes.md). On a file permission prompt, the same key closes an open [comment field](https://code.claude.com/docs/en/permissions.md#add-a-comment-when-you-answer-a-permission-prompt). With no field open, it selects the option that allows the action for the rest of the session, when the prompt offers that option |39| `Shift+Tab`, or `Alt+M` on Windows when the Node or Bun runtime doesn't enable VT input mode | Cycle permission modes | Cycle through `default` (labeled Manual in the mode indicator), `acceptEdits`, and `plan`, then `bypassPermissions` and `auto` where available. See [permission modes](https://code.claude.com/docs/en/permission-modes.md). On a file permission prompt, the same key closes an open [comment field](https://code.claude.com/docs/en/permissions.md#add-a-comment-when-you-answer-a-permission-prompt). With no field open, it selects the option that allows the action for the rest of the session, when the prompt offers that option. At the plan approval prompt, it approves the plan |

40| `Option+P` (macOS) or `Alt+P` (Windows/Linux) | Switch model | Switch models without clearing your prompt |40| `Option+P` (macOS) or `Alt+P` (Windows/Linux) | Switch model | Switch models without clearing your prompt |

41| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fable models, which always use extended thinking. Works on macOS without configuring Option as Meta |41| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fable models, which always use extended thinking. Works on macOS without configuring Option as Meta |

42| `Option+O` (macOS) or `Alt+O` (Windows/Linux) | Toggle fast mode | Enable or disable [fast mode](https://code.claude.com/docs/en/fast-mode.md) |42| `Option+O` (macOS) or `Alt+O` (Windows/Linux) | Toggle fast mode | Enable or disable [fast mode](https://code.claude.com/docs/en/fast-mode.md) |

304claude --permission-mode plan304claude --permission-mode plan

305```305```

306 306 

307Press `Shift+Tab` again to leave plan mode without approving a plan.307With no approval prompt open, press `Shift+Tab` again to leave plan mode. At the approval prompt, press `Esc` first, since pressing `Shift+Tab` there approves the plan.

308 308 

309### Review and approve a plan309### Review and approve a plan

310 310 

344 "PostToolUse": [344 "PostToolUse": [

345 {345 {

346 "matcher": "Write|Edit",346 "matcher": "Write|Edit",

347 "hooks": [{ "type": "command", "command": "jq -r '.tool_input.file_path' | xargs npm run lint:fix" }]347 "hooks": [{ "type": "command", "command": "f=$(jq -r '.tool_input.file_path') && npm run lint:fix -- \"$f\"" }]

348 }348 }

349 ]349 ]

350 }350 }

218 218 

219## Mods built into Claude Code219## Mods built into Claude Code

220 220 

221Some of Claude Code's own features are mods. To see the ones your session has, run `/plugin` at the Claude Code prompt and go to the **Installed** tab, which lists them under **Built-in**. You can't update or uninstall a built-in mod, and the table's last column says how to turn each one off. The [`mods active` line](#see-which-mods-a-session-loaded) omits built-in mods.221Some of Claude Code's own features are mods. To see the ones your session has, run `/plugin` at the Claude Code prompt and go to the **Installed** tab, which lists them under **Built-in**. You can't update or uninstall a built-in mod. The [`mods active` line](#see-which-mods-a-session-loaded) omits built-in mods.

222 222 

223This table lists each entry by the name `/plugin` shows:223This table lists some of the **Built-in** entries by the name `/plugin` shows:

224 224 

225| Name in `/plugin` | What it does | Where it's on | How to turn it off |225| Name in `/plugin` | What it does | Where it's on | How to turn it off |

226| :- | :- | :- | :- |226| :- | :- | :- | :- |

231| `cc-plugin-telemetry` | Sends the analytics records that Claude Code and its built-in mods log | Wherever Claude Code's own analytics are on | Disable it in `/plugin`, or turn analytics off, for example with [`DISABLE_TELEMETRY`](https://code.claude.com/docs/en/env-vars) |231| `cc-plugin-telemetry` | Sends the analytics records that Claude Code and its built-in mods log | Wherever Claude Code's own analytics are on | Disable it in `/plugin`, or turn analytics off, for example with [`DISABLE_TELEMETRY`](https://code.claude.com/docs/en/env-vars) |

232| `cc-plugin-you-should-know` | [You should know](https://code.claude.com/docs/en/interactive-mode.md#you-should-know-suggestions): a side agent shows a note above the prompt when it finds something you might have missed | Off until you [turn it on](https://code.claude.com/docs/en/interactive-mode.md#you-should-know-suggestions) | Disable it in `/plugin` |232| `cc-plugin-you-should-know` | [You should know](https://code.claude.com/docs/en/interactive-mode.md#you-should-know-suggestions): a side agent shows a note above the prompt when it finds something you might have missed | Off until you [turn it on](https://code.claude.com/docs/en/interactive-mode.md#you-should-know-suggestions) | Disable it in `/plugin` |

233 233 

234For a **Built-in** plugin that isn't in the table, [open its details in `/plugin`](https://code.claude.com/docs/en/plugins/install#manage-installed-plugins) to read what it does or to disable it.

235 

234The settings and flags that stop installed mods, such as `disableAllHooks`, `--bare`, and `--safe-mode`, don't stop built-in mods.236The settings and flags that stop installed mods, such as `disableAllHooks`, `--bare`, and `--safe-mode`, don't stop built-in mods.

235 237 

236### Read the source of built-in mods238### Read the source of built-in mods

194| `session.receive` | `($, e) => ({ text: e.text })`. Fire it with `$.session.receive({ origin: { kind: 'peer-send-message' }, text })`. |194| `session.receive` | `($, e) => ({ text: e.text })`. Fire it with `$.session.receive({ origin: { kind: 'peer-send-message' }, text })`. |

195| `ui.render` | `() => ({ type: 'Text', props: {}, children: ['...'] })` |195| `ui.render` | `() => ({ type: 'Text', props: {}, children: ['...'] })` |

196 196 

197`expect` has the assertions `toBe`, `toEqual`, `toMatch`, `toMatchObject`, `toContain`, `toBeDefined`, `toBeUndefined`, and `toThrow`, and `.not` before any of them.197### Check a result with `expect`

198 

199The kit has these assertions, and the one you pick goes after the value you're checking, as in `expect(answer.text).toBe('ok')`:

200 

201* **Equality**: `toBe` for the same value or object, `toEqual` for structure, `toStrictEqual` for structure plus `undefined` fields and the prototype, and `toMatchObject` for the fields you name

202* **Text**: `toMatch`, which takes a regular expression or a substring, `toStartWith`, and `toEndWith`

203* **Numbers**: `toBeGreaterThan`, `toBeGreaterThanOrEqual`, `toBeLessThan`, `toBeLessThanOrEqual`

204* **Contents**: `toContain` for a substring or a member, `toContainEqual` for a member compared by structure, `toHaveLength`, and `toHaveProperty`

205* **Presence and type**: `toBeDefined`, `toBeUndefined`, `toBeNull`, `toBeTruthy`, `toBeFalsy`, `toBeNaN`, `toBeInstanceOf`

206* **Throwing**: `toThrow`, for a function `expect` calls, or for a promise you check with `.rejects`

207 

208Put `.not` in front of an assertion to check the opposite, and `.resolves` or `.rejects` to check what a promise settles with.

198 209 

199When an `expect` fails inside a stub or hook that you passed to `on` as a plain function rather than an async generator, the test fails. The engine skips that hook, and the failure output names it, such as `in the test's store.set hook`.210When an `expect` fails inside a stub or hook that you passed to `on` as a plain function rather than an async generator, the test fails. The engine skips that hook, and the failure output names it, such as `in the test's store.set hook`.

200 211 

26| Project context | CLAUDE.md, auto memory, unscoped rules | Session starts, or after `/clear` or `/compact` |26| Project context | CLAUDE.md, auto memory, unscoped rules | Session starts, or after `/clear` or `/compact` |

27| Conversation | Your messages, Claude's responses, tool results | Every turn |27| Conversation | Your messages, Claude's responses, tool results | Every turn |

28 28 

29A change to the conversation layer leaves the system prompt and project context cached. A change to the system prompt invalidates everything, because all later content now sits behind a different prefix. The third column gives common triggers rather than an exhaustive list, and the sections below cover the full set.29An addition to the conversation layer leaves the system prompt and project context cached. A change to the system prompt invalidates everything, because all later content now sits behind a different prefix. The third column gives common triggers rather than an exhaustive list, and the sections below cover the full set.

30 30 

31The prefix-match rule explains most of the behaviors on this page. [Plan mode](https://code.claude.com/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode) and [skill loading](https://code.claude.com/docs/en/skills.md), for example, append their instructions as conversation messages, so the cached prefix stays intact.31The prefix-match rule explains most of the behaviors on this page. [Plan mode](https://code.claude.com/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode) and [skill loading](https://code.claude.com/docs/en/skills.md), for example, append their instructions as conversation messages, so the cached prefix stays intact.

32 32 

174 174 

175### Compacting the conversation175### Compacting the conversation

176 176 

177[Compaction](https://code.claude.com/docs/en/context-window.md#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer: the next request has a new, shorter history that doesn't share a prefix with the old one. The system prompt and project context layers can stay cached:177[Compaction](https://code.claude.com/docs/en/context-window.md#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer: the next request has a new, shorter history that doesn't share a prefix with the old one.

178 178 

179* **System prompt**: the next request reads this layer from the cache, unless a [resumed conversation](#resuming-a-session) kept a system prompt that is now out of date. The first time that conversation is compacted, Claude Code switches it to the current prompt, and the next request rebuilds this layer's cache once.179* **System prompt**: the next request reads this layer from the cache, unless a [resumed conversation](#resuming-a-session) kept a system prompt that is now out of date. The first time that conversation is compacted, Claude Code switches it to the current prompt, and the next request rebuilds this layer's cache once.

180* **Project context**: Claude Code reloads this layer from disk. The next request reads it from the cache only if CLAUDE.md and memory are unchanged since the session started.180* **Project context**: Claude Code reloads this layer from disk. It's cached together with the conversation, so after `/compact` or automatic compaction its cache is rebuilt even if its files are unchanged.

181 181 

182To produce the summary, Claude Code sends a separate request. The request repeats your conversation's system prompt, tools, and the history being summarized. It ends with a summarization instruction. While the cache is warm, that request reads your prefix from the cache. A mid-session `/compact` then costs a fraction of what the context size suggests and spends most of its time generating the summary.182To produce the summary, Claude Code sends a separate request. The request repeats your conversation's system prompt, tools, and the history being summarized. It ends with a summarization instruction. While the cache is warm, that request reads your prefix from the cache. A mid-session `/compact` then costs a fraction of what the context size suggests and spends most of its time generating the summary.

183 183 

184After a break longer than the [cache lifetime](#cache-lifetime), there is no cache left to read, so the summarization request reprocesses that history as uncached input. This is why `/compact` costs the most when you [resume an old session](https://code.claude.com/docs/en/sessions.md#resume-a-session). In both the warm and cold cases, the turn after compaction rebuilds the conversation cache for only the much shorter summary, so that turn isn't the slow part.184After a break longer than the [cache lifetime](#cache-lifetime), there is no cache left to read, so the summarization request reprocesses that history as uncached input. This is why `/compact` costs the most when you [resume an old session](https://code.claude.com/docs/en/sessions.md#resume-a-session). In both the warm and cold cases, the turn after compaction rebuilds the conversation cache for only the much shorter history, so that turn isn't the slow part.

185 185 

186> [!TIP]186> [!TIP]

187>187>

31>31>

32> **macOS, Linux, WSL:**32> **macOS, Linux, WSL:**

33>33>

34> ```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} 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} 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} 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} 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} 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} 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} 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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}34> ```bash theme={null}

35> curl -fsSL https://claude.ai/install.sh | bash35> curl -fsSL https://claude.ai/install.sh | bash

36> ```36> ```

37>37>

39>39>

40> **Windows PowerShell:**40> **Windows PowerShell:**

41>41>

42> ```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={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} 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} 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} 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} 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} 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} 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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}42> ```powershell theme={null}

43> irm https://claude.ai/install.ps1 | iex43> irm https://claude.ai/install.ps1 | iex

44> ```44> ```

45>45>

46> **Windows CMD:**46> **Windows CMD:**

47>47>

48> ```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} 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} 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} 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} 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} 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} 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} 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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}48> ```batch theme={null}

49> curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd49> curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd

50> ```50> ```

51>51>

63 63 

64> [tab] Homebrew64> [tab] Homebrew

65>65>

66> ```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} 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} 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} 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} 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} 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} 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} 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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}66> ```bash theme={null}

67> brew install --cask claude-code67> brew install --cask claude-code

68> ```68> ```

69>69>

75 75 

76> [tab] WinGet76> [tab] WinGet

77>77>

78> ```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={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} 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} 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} 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} 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} 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} 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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}78> ```powershell theme={null}

79> winget install Anthropic.ClaudeCode79> winget install Anthropic.ClaudeCode

80> ```80> ```

81>81>

86| [`disabledMcpjsonServers`](#disabledmcpjsonservers) | Reject specific servers from a project's [`.mcp.json`](https://code.claude.com/docs/en/mcp#project-scope) | MCP | Any file |86| [`disabledMcpjsonServers`](#disabledmcpjsonservers) | Reject specific servers from a project's [`.mcp.json`](https://code.claude.com/docs/en/mcp#project-scope) | MCP | Any file |

87| [`disableMobileSimulatorTools`](#disablemobilesimulatortools) | Block Claude's tools in the [desktop](https://code.claude.com/docs/en/desktop.md) iOS Simulator pane | Tools | Managed |87| [`disableMobileSimulatorTools`](#disablemobilesimulatortools) | Block Claude's tools in the [desktop](https://code.claude.com/docs/en/desktop.md) iOS Simulator pane | Tools | Managed |

88| [`disableRemoteControl`](#disableremotecontrol) | Turn off [Remote Control](https://code.claude.com/docs/en/remote-control.md) everywhere it can start | Remote, desktop, and notifications | Any file |88| [`disableRemoteControl`](#disableremotecontrol) | Turn off [Remote Control](https://code.claude.com/docs/en/remote-control.md) everywhere it can start | Remote, desktop, and notifications | Any file |

89| [`disableRemotePreviewScripts`](#disableremotepreviewscripts) | Turn off scripts in the [desktop](https://code.claude.com/docs/en/desktop.md#preview-html-files-in-ssh-and-wsl-sessions) app's HTML previews in SSH and WSL sessions | Remote, desktop, and notifications | Managed |

89| [`disableSideloadFlags`](#disablesideloadflags) | Reject the CLI flags that sideload [plugins](https://code.claude.com/docs/en/plugins/overview.md), [subagents](https://code.claude.com/docs/en/sub-agents.md), and [MCP servers](https://code.claude.com/docs/en/mcp.md) | Enterprise and managed settings | Managed |90| [`disableSideloadFlags`](#disablesideloadflags) | Reject the CLI flags that sideload [plugins](https://code.claude.com/docs/en/plugins/overview.md), [subagents](https://code.claude.com/docs/en/sub-agents.md), and [MCP servers](https://code.claude.com/docs/en/mcp.md) | Enterprise and managed settings | Managed |

90| [`disableSkillShellExecution`](#disableskillshellexecution) | Stop [skills](https://code.claude.com/docs/en/skills.md) and custom commands from running inline shell | Plugins and skills | Any file |91| [`disableSkillShellExecution`](#disableskillshellexecution) | Stop [skills](https://code.claude.com/docs/en/skills.md) and custom commands from running inline shell | Plugins and skills | Any file |

91| [`disableWorkflows`](#disableworkflows) | Turn [dynamic workflows](https://code.claude.com/docs/en/workflows.md) off for everyone; use `enableWorkflows` for yourself | Hooks and automation | Any file |92| [`disableWorkflows`](#disableworkflows) | Turn [dynamic workflows](https://code.claude.com/docs/en/workflows.md) off for everyone; use `enableWorkflows` for yourself | Hooks and automation | Any file |

1196* **Question and plan tools**: Claude Code leaves out [`AskUserQuestion`](https://code.claude.com/docs/en/tools-reference#askuserquestion-tool-behavior), `EnterPlanMode`, and `ExitPlanMode`, so a session in plan mode can't leave it on its own. A teammate in an agent team keeps `EnterPlanMode` and `ExitPlanMode`1197* **Question and plan tools**: Claude Code leaves out [`AskUserQuestion`](https://code.claude.com/docs/en/tools-reference#askuserquestion-tool-behavior), `EnterPlanMode`, and `ExitPlanMode`, so a session in plan mode can't leave it on its own. A teammate in an agent team keeps `EnterPlanMode` and `ExitPlanMode`

1197* **MCP elicitation**: Claude Code cancels an [elicitation request](https://code.claude.com/docs/en/mcp.md#respond-to-mcp-elicitation-requests) unless an [`Elicitation` hook](https://code.claude.com/docs/en/hooks#elicitation) answers it1198* **MCP elicitation**: Claude Code cancels an [elicitation request](https://code.claude.com/docs/en/mcp.md#respond-to-mcp-elicitation-requests) unless an [`Elicitation` hook](https://code.claude.com/docs/en/hooks#elicitation) answers it

1198* **Permission hosts**: Claude Code doesn't ask your [`canUseTool` callback](https://code.claude.com/docs/en/agent-sdk/user-input) or [`--permission-prompt-tool`](https://code.claude.com/docs/en/cli-reference#cli-flags). To approve calls from code, answer from a `PermissionRequest` hook. Some calls are denied before any hook is asked, such as a [critical-path removal](https://code.claude.com/docs/en/permission-modes.md#critical-path-removals-in-each-permission-mode) in `auto` mode that no ask rule covers.1199* **Permission hosts**: Claude Code doesn't ask your [`canUseTool` callback](https://code.claude.com/docs/en/agent-sdk/user-input) or [`--permission-prompt-tool`](https://code.claude.com/docs/en/cli-reference#cli-flags). To approve calls from code, answer from a `PermissionRequest` hook. Some calls are denied before any hook is asked, such as a [critical-path removal](https://code.claude.com/docs/en/permission-modes.md#critical-path-removals-in-each-permission-mode) in `auto` mode that no ask rule covers.

1199* **Classifier billing notice**: where the [notice about billed classifier requests](https://code.claude.com/docs/en/auto-mode-classifier-billing.md#actions-denied-in-place-of-the-notice) would open a dialog, Claude Code doesn't show it and denies the actions that need those requests1200* **Classifier billing notice**: where the [notice about billed classifier requests](https://code.claude.com/docs/en/auto-mode-classifier-billing.md) would open a dialog, Claude Code doesn't show it and denies the actions that need those requests

1200 1201 

1201A session can still wait on the [workspace trust dialog](https://code.claude.com/docs/en/permissions.md#project-allow-rules-and-workspace-trust) and on [project MCP server approval](https://code.claude.com/docs/en/mcp.md#project-server-approvals-and-workspace-trust). Answer both before you leave the session running.1202A session can still wait on the [workspace trust dialog](https://code.claude.com/docs/en/permissions.md#project-allow-rules-and-workspace-trust) and on [project MCP server approval](https://code.claude.com/docs/en/mcp.md#project-server-approvals-and-workspace-trust). Answer both before you leave the session running.

1202 1203 

5005}5006}

5006```5007```

5007 5008 

5009### `disableRemotePreviewScripts`

5010 

5011Keep scripts from running when people [preview an HTML file](https://code.claude.com/docs/en/desktop.md#preview-html-files-in-ssh-and-wsl-sessions) from an SSH or WSL session in the desktop app. External browsing in the Browser pane is unaffected.

5012 

5013The desktop app reads this key; the terminal CLI ignores it. Requires Claude Desktop v5.1231.0 or later. Earlier versions ignore the key: to stop the scripts there, also set [`disableBrowserExternalNavigation`](#disablebrowserexternalnavigation), which turns off external browsing too.

5014 

5015* **Scope**: [`Managed`](#scopes). The desktop app doesn't read the key from the remote machine or the WSL distribution.

5016* **Type**: Boolean; only the JSON Boolean `true` takes effect

5017 * `true`: HTML previews in SSH and WSL sessions don't run scripts

5018 * `false`: the key doesn't turn scripts off

5019* **Default**: unset, so the key has no effect

5020 

5021If the computer that runs the desktop app receives no other Claude Code managed settings, also set [`parentSettingsBehavior`](#parentsettingsbehavior) to `"merge"` in the managed settings that you create. On Windows, if you create a managed settings file, users also lose WSL sessions until you [allow them](https://code.claude.com/docs/en/admin-setup.md#wsl-sessions-in-claude-code-desktop). [Turn off scripts in SSH and WSL previews for your organization](https://code.claude.com/docs/en/desktop.md#turn-off-scripts-in-ssh-and-wsl-previews-for-your-organization) explains both and says where to set the key.

5022 

5023This example shows the key alone, as you'd add it to managed settings that a computer already receives:

5024 

5025```json managed-settings.json theme={null}

5026{

5027 "disableRemotePreviewScripts": true

5028}

5029```

5030 

5031The desktop app ignores any other value, and a value that isn't a Boolean, such as the string `"true"` or `1`, also logs a warning.

5032 

5008### `enableArtifact`5033### `enableArtifact`

5009 5034 

5010Turn off the [Artifact](https://code.claude.com/docs/en/artifacts.md) tool, which publishes session output as a private web page on claude.ai. When you turn the **Artifacts** row off in `/config`, Claude Code writes this key to your user settings, so you don't usually edit it by hand.5035Turn off the [Artifact](https://code.claude.com/docs/en/artifacts.md) tool, which publishes session output as a private web page on claude.ai. When you turn the **Artifacts** row off in `/config`, Claude Code writes this key to your user settings, so you don't usually edit it by hand.

141 141 

142### Alpine Linux and musl-based distributions142### Alpine Linux and musl-based distributions

143 143 

144Installing Claude Code on Alpine and other musl/uClibc-based distributions requires `bash` and `curl` for the install command, and `libgcc`, `libstdc++`, and `ripgrep` at runtime. Alpine doesn't include `bash` or `curl` by default, so the documented install command fails with a `not found` error until you install them. Install these packages using your distribution's package manager, then set `USE_BUILTIN_RIPGREP=0`.144On Alpine and other musl-based distributions, the [install command](#install-claude-code) requires `bash` and `curl`, and Claude Code itself requires `bash` or `zsh`. Alpine doesn't include `bash` or `curl` by default, so the documented install command fails with a `not found` error until you install them.

145 145 

146This example installs the required packages on Alpine:146This example installs the required packages on Alpine:

147 147 

148```bash theme={null}148```bash theme={null}

149apk add bash curl libgcc libstdc++ ripgrep149apk add bash curl

150```

151 

152On Alpine, `ripgrep` is in the community repository. If `apk` reports that the package is missing, add the community repository to `/etc/apk/repositories`, using your Alpine version:

153 

154```bash theme={null}

155echo "https://dl-cdn.alpinelinux.org/alpine/v3.22/community" >> /etc/apk/repositories

156```

157 

158Run `apk update` to refresh the package index, and retry the `apk add` command.

159 

160Then set `USE_BUILTIN_RIPGREP` to `0` in your [`settings.json`](https://code.claude.com/docs/en/settings-reference#all-settings) file:

161 

162```json theme={null}

163{

164 "env": {

165 "USE_BUILTIN_RIPGREP": "0"

166 }

167}

168```150```

169 151 

170## Verify your installation152## Verify your installation

443> wget -O /etc/apk/keys/claude-code.rsa.pub \425> wget -O /etc/apk/keys/claude-code.rsa.pub \

444> https://downloads.claude.ai/keys/claude-code.rsa.pub426> https://downloads.claude.ai/keys/claude-code.rsa.pub

445> echo "https://downloads.claude.ai/claude-code/apk/stable" >> /etc/apk/repositories427> echo "https://downloads.claude.ai/claude-code/apk/stable" >> /etc/apk/repositories

446> apk add claude-code428> apk add bash claude-code

447> ```429> ```

448>430>

449> To switch to the `latest` channel, remove the `stable` repository line and add the `latest` repository:431> To switch to the `latest` channel, remove the `stable` repository line and add the `latest` repository:

388> Get-Command claude | Select-Object Source388> Get-Command claude | Select-Object Source

389> ```389> ```

390 390 

391On Linux, check for missing shared libraries. If `ldd` shows missing libraries, you may need to install system packages. On Alpine Linux and other musl-based distributions, see [Alpine Linux setup](https://code.claude.com/docs/en/setup.md#alpine-linux-and-musl-based-distributions).391On Linux, check for missing shared libraries. If `ldd` shows missing libraries, you may need to install system packages. On Alpine Linux and other musl-based distributions, see [Linux musl or glibc binary mismatch](#linux-musl-or-glibc-binary-mismatch).

392 392 

393```bash theme={null}393```bash theme={null}

394ldd "$(command -v claude)" | grep "not found"394ldd "$(command -v claude)" | grep "not found"

906 906 

907### Linux musl or glibc binary mismatch907### Linux musl or glibc binary mismatch

908 908 

909If you see errors about missing shared libraries like `libstdc++.so.6` or `libgcc_s.so.1` after installation, the installer may have downloaded the wrong binary variant for your system.909If you see errors about missing shared libraries like `ld-linux-x86-64.so.2` or `ld-linux-aarch64.so.1` after installation, the installer may have downloaded the wrong binary variant for your system.

910 910 

911```text theme={null}911```text theme={null}

912Error loading shared library libstdc++.so.6: No such file or directory912Error loading shared library ld-linux-x86-64.so.2: No such file or directory

913```913```

914 914 

915This can happen on glibc-based systems that have musl cross-compilation packages installed, causing the installer to misdetect the system as musl.

916 

917**Solutions:**915**Solutions:**

918 916 

9191. **Check which libc your system uses**:9171. **Check which libc your system uses**:

924 922 

9252. **If you're on glibc but got the musl binary**, remove the installation and reinstall. You can also manually download the correct binary using the manifest at `https://downloads.claude.ai/claude-code-releases/{VERSION}/manifest.json`. File a [GitHub issue](https://github.com/anthropics/claude-code/issues) with the output of `ldd --version` and `ls /lib/libc.musl*`.9232. **If you're on glibc but got the musl binary**, remove the installation and reinstall. You can also manually download the correct binary using the manifest at `https://downloads.claude.ai/claude-code-releases/{VERSION}/manifest.json`. File a [GitHub issue](https://github.com/anthropics/claude-code/issues) with the output of `ldd --version` and `ls /lib/libc.musl*`.

926 924 

9273. **If you're actually on musl**, such as Alpine Linux, install the required packages:9253. **If you're on musl but got the glibc binary**, [remove the installation](https://code.claude.com/docs/en/setup.md#uninstall-claude-code). On Alpine Linux, first install the packages that [Alpine Linux setup](https://code.claude.com/docs/en/setup.md#alpine-linux-and-musl-based-distributions) names. Then run the [install command](https://code.claude.com/docs/en/setup.md#install-claude-code), which installs the musl binary.

928 ```bash theme={null}

929 apk add libgcc libstdc++ ripgrep

930 ```

931 On Alpine, `ripgrep` is in the community repository. If `apk` reports that the package is missing, see [Alpine Linux setup](https://code.claude.com/docs/en/setup.md#alpine-linux-and-musl-based-distributions).

932 926 

933### `Illegal instruction`927### `Illegal instruction`

934 928 

152> apk add ripgrep152> apk add ripgrep

153> ```153> ```

154>154>

155> `ripgrep` is in Alpine's community repository. If `apk` reports that the package is missing, see [Alpine Linux setup](https://code.claude.com/docs/en/setup.md#alpine-linux-and-musl-based-distributions).155> `ripgrep` is in Alpine's community repository.

156 156 

157> [tab] Arch157> [tab] Arch

158>158>