Documentation 2026-04-10 21:09 UTC to 2026-04-11 00:11 UTC

326export CLAUDE_CODE_USE_BEDROCK=1326export CLAUDE_CODE_USE_BEDROCK=1

327export AWS_REGION=us-east-1 # or your preferred region327export AWS_REGION=us-east-1 # or your preferred region

328 328 

329# Optional: Override the region for the small/fast model (Haiku)329# Optional: Override the region for the small/fast model (Haiku).

330# Also applies to Bedrock Mantle.

330export ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION=us-west-2331export ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION=us-west-2

331 332 

332# Optional: Override the Bedrock endpoint URL for custom endpoints or gateways333# Optional: Override the Bedrock endpoint URL for custom endpoints or gateways

539These variables are specific to the Mantle endpoint. See [Environment variables](/en/env-vars) for the full list.540These variables are specific to the Mantle endpoint. See [Environment variables](/en/env-vars) for the full list.

540 541 

541| Variable | Purpose |542| Variable | Purpose |

542| :---------------------------------- | :------------------------------------------------ |543| :-------------------------------------- | :------------------------------------------------------------------ |

543| `CLAUDE_CODE_USE_MANTLE` | Enable the Mantle endpoint. Set to `1` or `true`. |544| `CLAUDE_CODE_USE_MANTLE` | Enable the Mantle endpoint. Set to `1` or `true`. |

544| `ANTHROPIC_BEDROCK_MANTLE_BASE_URL` | Override the default Mantle endpoint URL |545| `ANTHROPIC_BEDROCK_MANTLE_BASE_URL` | Override the default Mantle endpoint URL |

545| `CLAUDE_CODE_SKIP_MANTLE_AUTH` | Skip client-side authentication for proxy setups |546| `CLAUDE_CODE_SKIP_MANTLE_AUTH` | Skip client-side authentication for proxy setups |

547| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model (shared with Bedrock) |

546 548 

547## Troubleshooting549## Troubleshooting

548 550 

34| `/batch <instruction>` | **[Skill](/en/skills#bundled-skills).** Orchestrate large-scale changes across a codebase in parallel. Researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan. Once approved, spawns one background agent per unit in an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees). Each agent implements its unit, runs tests, and opens a pull request. Requires a git repository. Example: `/batch migrate src/ from Solid to React` |34| `/batch <instruction>` | **[Skill](/en/skills#bundled-skills).** Orchestrate large-scale changes across a codebase in parallel. Researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan. Once approved, spawns one background agent per unit in an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees). Each agent implements its unit, runs tests, and opens a pull request. Requires a git repository. Example: `/batch migrate src/ from Solid to React` |

35| `/btw <question>` | Ask a quick [side question](/en/interactive-mode#side-questions-with-btw) without adding to the conversation |35| `/btw <question>` | Ask a quick [side question](/en/interactive-mode#side-questions-with-btw) without adding to the conversation |

36| `/chrome` | Configure [Claude in Chrome](/en/chrome) settings |36| `/chrome` | Configure [Claude in Chrome](/en/chrome) settings |

37| `/claude-api` | **[Skill](/en/skills#bundled-skills).** Load Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL). Covers tool use, streaming, batches, structured outputs, Managed Agents, and common pitfalls. Also activates automatically when your code imports `anthropic` or `@anthropic-ai/sdk` |37| `/claude-api` | **[Skill](/en/skills#bundled-skills).** Load Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL) and Managed Agents reference. Covers tool use, streaming, batches, structured outputs, and common pitfalls. Also activates automatically when your code imports `anthropic` or `@anthropic-ai/sdk` |

38| `/clear` | Clear conversation history and free up context. Aliases: `/reset`, `/new` |38| `/clear` | Clear conversation history and free up context. Aliases: `/reset`, `/new` |

39| `/color [color\|default]` | Set the prompt bar color for the current session. Available colors: `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, `cyan`. Use `default` to reset |39| `/color [color\|default]` | Set the prompt bar color for the current session. Available colors: `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, `cyan`. Use `default` to reset |

40| `/compact [instructions]` | Compact conversation with optional focus instructions |40| `/compact [instructions]` | Compact conversation with optional focus instructions |

47| `ANTHROPIC_FOUNDRY_RESOURCE` | Foundry resource name (for example, `my-resource`). Required if `ANTHROPIC_FOUNDRY_BASE_URL` is not set (see [Microsoft Foundry](/en/microsoft-foundry)) |47| `ANTHROPIC_FOUNDRY_RESOURCE` | Foundry resource name (for example, `my-resource`). Required if `ANTHROPIC_FOUNDRY_BASE_URL` is not set (see [Microsoft Foundry](/en/microsoft-foundry)) |

48| `ANTHROPIC_MODEL` | Name of the model setting to use (see [Model Configuration](/en/model-config#environment-variables)) |48| `ANTHROPIC_MODEL` | Name of the model setting to use (see [Model Configuration](/en/model-config#environment-variables)) |

49| `ANTHROPIC_SMALL_FAST_MODEL` | \[DEPRECATED] Name of [Haiku-class model for background tasks](/en/costs) |49| `ANTHROPIC_SMALL_FAST_MODEL` | \[DEPRECATED] Name of [Haiku-class model for background tasks](/en/costs) |

50| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock |50| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock or Bedrock Mantle |

51| `ANTHROPIC_VERTEX_BASE_URL` | Override the Vertex AI endpoint URL. Use for custom Vertex endpoints or when routing through an [LLM gateway](/en/llm-gateway). See [Google Vertex AI](/en/google-vertex-ai) |51| `ANTHROPIC_VERTEX_BASE_URL` | Override the Vertex AI endpoint URL. Use for custom Vertex endpoints or when routing through an [LLM gateway](/en/llm-gateway). See [Google Vertex AI](/en/google-vertex-ai) |

52| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI. Required when using [Google Vertex AI](/en/google-vertex-ai) |52| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI. Required when using [Google Vertex AI](/en/google-vertex-ai) |

53| `API_TIMEOUT_MS` | Timeout for API requests in milliseconds (default: 600000, or 10 minutes; maximum: 2147483647). Increase this when requests time out on slow networks or when routing through a proxy. Values above the maximum overflow the underlying timer and cause requests to fail immediately |53| `API_TIMEOUT_MS` | Timeout for API requests in milliseconds (default: 600000, or 10 minutes; maximum: 2147483647). Increase this when requests time out on slow networks or when routing through a proxy. Values above the maximum overflow the underlying timer and cause requests to fail immediately |

61| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only |61| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only |

62| `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` | Set the percentage of context capacity (1-100) at which auto-compaction triggers. By default, auto-compaction triggers at approximately 95% capacity. Use lower values like `50` to compact earlier. Values above the default threshold have no effect. Applies to both main conversations and subagents. This percentage aligns with the `context_window.used_percentage` field available in [status line](/en/statusline) |62| `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` | Set the percentage of context capacity (1-100) at which auto-compaction triggers. By default, auto-compaction triggers at approximately 95% capacity. Use lower values like `50` to compact earlier. Values above the default threshold have no effect. Applies to both main conversations and subagents. This percentage aligns with the `context_window.used_percentage` field available in [status line](/en/statusline) |

63| `CLAUDE_AUTO_BACKGROUND_TASKS` | Set to `1` to force-enable automatic backgrounding of long-running agent tasks. When enabled, subagents are moved to the background after running for approximately two minutes |63| `CLAUDE_AUTO_BACKGROUND_TASKS` | Set to `1` to force-enable automatic backgrounding of long-running agent tasks. When enabled, subagents are moved to the background after running for approximately two minutes |

64| `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` | Return to the original working directory after each Bash command |64| `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` | Return to the original working directory after each Bash or PowerShell command in the main session |

65| `CLAUDE_CODE_ACCESSIBILITY` | Set to `1` to keep the native terminal cursor visible and disable the inverted-text cursor indicator. Allows screen magnifiers like macOS Zoom to track cursor position |65| `CLAUDE_CODE_ACCESSIBILITY` | Set to `1` to keep the native terminal cursor visible and disable the inverted-text cursor indicator. Allows screen magnifiers like macOS Zoom to track cursor position |

66| `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD` | Set to `1` to load CLAUDE.md files from directories specified with `--add-dir`. By default, additional directories do not load memory files |66| `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD` | Set to `1` to load CLAUDE.md files from directories specified with `--add-dir`. By default, additional directories do not load memory files |

67| `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` | Interval in milliseconds at which credentials should be refreshed (when using [`apiKeyHelper`](/en/settings#available-settings)) |67| `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` | Interval in milliseconds at which credentials should be refreshed (when using [`apiKeyHelper`](/en/settings#available-settings)) |

68| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the context capacity in tokens used for auto-compaction calculations. Defaults to the model's context window: 200K for standard models or 1M for [extended context](/en/model-config#extended-context) models. Use a lower value like `500000` on a 1M model to treat the window as 500K for compaction purposes. The value is capped at the model's actual context window. `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` is applied as a percentage of this value. Setting this variable decouples the compaction threshold from the status line's `used_percentage`, which always uses the model's full context window |68| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the context capacity in tokens used for auto-compaction calculations. Defaults to the model's context window: 200K for standard models or 1M for [extended context](/en/model-config#extended-context) models. Use a lower value like `500000` on a 1M model to treat the window as 500K for compaction purposes. The value is capped at the model's actual context window. `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` is applied as a percentage of this value. Setting this variable decouples the compaction threshold from the status line's `used_percentage`, which always uses the model's full context window |

69| `CLAUDE_CODE_AUTO_CONNECT_IDE` | Override automatic [IDE connection](/en/vs-code). By default, Claude Code connects automatically when launched inside a supported IDE's integrated terminal. Set to `false` to prevent this. Set to `true` to force a connection attempt when auto-detection fails, such as when tmux obscures the parent terminal |69| `CLAUDE_CODE_AUTO_CONNECT_IDE` | Override automatic [IDE connection](/en/vs-code). By default, Claude Code connects automatically when launched inside a supported IDE's integrated terminal. Set to `false` to prevent this. Set to `true` to force a connection attempt when auto-detection fails, such as when tmux obscures the parent terminal |

70| `CLAUDE_CODE_CERT_STORE` | Comma-separated list of CA certificate sources for TLS connections. `bundled` is the Mozilla CA set shipped with Claude Code. `system` is the operating system trust store. Default is `bundled,system`. The native binary distribution is required for system store integration. On the Node.js runtime, only the bundled set is used regardless of this value |

70| `CLAUDE_CODE_CLIENT_CERT` | Path to client certificate file for mTLS authentication |71| `CLAUDE_CODE_CLIENT_CERT` | Path to client certificate file for mTLS authentication |

71| `CLAUDE_CODE_CLIENT_KEY` | Path to client private key file for mTLS authentication |72| `CLAUDE_CODE_CLIENT_KEY` | Path to client private key file for mTLS authentication |

72| `CLAUDE_CODE_CLIENT_KEY_PASSPHRASE` | Passphrase for encrypted CLAUDE\_CODE\_CLIENT\_KEY (optional) |73| `CLAUDE_CODE_CLIENT_KEY_PASSPHRASE` | Passphrase for encrypted CLAUDE\_CODE\_CLIENT\_KEY (optional) |

179| [Plugin](/en/plugins) `hooks/hooks.json` | When plugin is enabled | Yes, bundled with the plugin |179| [Plugin](/en/plugins) `hooks/hooks.json` | When plugin is enabled | Yes, bundled with the plugin |

180| [Skill](/en/skills) or [agent](/en/sub-agents) frontmatter | While the component is active | Yes, defined in the component file |180| [Skill](/en/skills) or [agent](/en/sub-agents) frontmatter | While the component is active | Yes, defined in the component file |

181 181 

182For details on settings file resolution, see [settings](/en/settings). Enterprise administrators can use `allowManagedHooksOnly` to block user, project, and plugin hooks. See [Hook configuration](/en/settings#hook-configuration).182For details on settings file resolution, see [settings](/en/settings). Enterprise administrators can use `allowManagedHooksOnly` to block user, project, and plugin hooks. Hooks from plugins force-enabled in managed settings `enabledPlugins` are exempt, so administrators can distribute vetted hooks through an organization marketplace. See [Hook configuration](/en/settings#hook-configuration).

183 183 

184### Matcher patterns184### Matcher patterns

185 185 

128 128 

129Spans redact user prompt text and tool content by default. Set `OTEL_LOG_USER_PROMPTS=1` and `OTEL_LOG_TOOL_CONTENT=1` to include them.129Spans redact user prompt text and tool content by default. Set `OTEL_LOG_USER_PROMPTS=1` and `OTEL_LOG_TOOL_CONTENT=1` to include them.

130 130 

131When tracing is active, Bash subprocesses automatically inherit a `TRACEPARENT` environment variable containing the W3C trace context of the active tool execution span. This lets any subprocess that reads `TRACEPARENT` parent its own spans under the same trace, enabling end-to-end distributed tracing through scripts and commands that Claude runs.131When tracing is active, Bash and PowerShell subprocesses automatically inherit a `TRACEPARENT` environment variable containing the W3C trace context of the active tool execution span. This lets any subprocess that reads `TRACEPARENT` parent its own spans under the same trace, enabling end-to-end distributed tracing through scripts and commands that Claude runs.

132 132 

133### Dynamic headers133### Dynamic headers

134 134 

63 For proxies requiring advanced authentication (NTLM, Kerberos, etc.), consider using an LLM Gateway service that supports your authentication method.63 For proxies requiring advanced authentication (NTLM, Kerberos, etc.), consider using an LLM Gateway service that supports your authentication method.

64</Tip>64</Tip>

65 65 

66## CA certificate store

67 

68By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Enterprise TLS-inspection proxies such as CrowdStrike Falcon and Zscaler work without additional configuration when their root certificate is installed in the OS trust store.

69 

70<Note>

71 System CA store integration requires the native Claude Code binary distribution. When running on the Node.js runtime, the system CA store is not merged automatically. In that case, set `NODE_EXTRA_CA_CERTS=/path/to/ca-cert.pem` to trust an enterprise root CA.

72</Note>

73 

74`CLAUDE_CODE_CERT_STORE` accepts a comma-separated list of sources. Recognized values are `bundled` for the Mozilla CA set shipped with Claude Code and `system` for the operating system trust store. The default is `bundled,system`.

75 

76To trust only the bundled Mozilla CA set:

77 

78```bash theme={null}

79export CLAUDE_CODE_CERT_STORE=bundled

80```

81 

82To trust only the OS certificate store:

83 

84```bash theme={null}

85export CLAUDE_CODE_CERT_STORE=system

86```

87 

88<Note>

89 `CLAUDE_CODE_CERT_STORE` has no dedicated `settings.json` schema key. Set it via the `env` block in `~/.claude/settings.json` or directly in the process environment.

90</Note>

91 

66## Custom CA certificates92## Custom CA certificates

67 93 

68If your enterprise environment uses custom CAs for HTTPS connections (whether through a proxy or direct API access), configure Claude Code to trust them:94If your enterprise environment uses a custom CA, configure Claude Code to trust it directly:

69 95 

70```bash theme={null}96```bash theme={null}

71export NODE_EXTRA_CA_CERTS=/path/to/ca-cert.pem97export NODE_EXTRA_CA_CERTS=/path/to/ca-cert.pem

269| Setting | Description |269| Setting | Description |

270| :--------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |270| :--------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

271| `allowedChannelPlugins` | Allowlist of channel plugins that may push messages. Replaces the default Anthropic allowlist when set. Requires `channelsEnabled: true`. See [Restrict which channel plugins can run](/en/channels#restrict-which-channel-plugins-can-run) |271| `allowedChannelPlugins` | Allowlist of channel plugins that may push messages. Replaces the default Anthropic allowlist when set. Requires `channelsEnabled: true`. See [Restrict which channel plugins can run](/en/channels#restrict-which-channel-plugins-can-run) |

272| `allowManagedHooksOnly` | When `true`, prevents loading of user, project, and plugin hooks. Only managed hooks and SDK hooks are allowed |272| `allowManagedHooksOnly` | When `true`, only managed hooks, SDK hooks, and hooks from plugins force-enabled in managed settings `enabledPlugins` are loaded. User, project, and all other plugin hooks are blocked |

273| `allowManagedMcpServersOnly` | When `true`, only `allowedMcpServers` from managed settings are respected. `deniedMcpServers` still merges from all sources. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) |273| `allowManagedMcpServersOnly` | When `true`, only `allowedMcpServers` from managed settings are respected. `deniedMcpServers` still merges from all sources. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) |

274| `allowManagedPermissionRulesOnly` | When `true`, prevents user and project settings from defining `allow`, `ask`, or `deny` permission rules. Only rules in managed settings apply |274| `allowManagedPermissionRulesOnly` | When `true`, prevents user and project settings from defining `allow`, `ask`, or `deny` permission rules. Only rules in managed settings apply |

275| `blockedMarketplaces` | Blocklist of marketplace sources. Blocked sources are checked before downloading, so they never touch the filesystem. See [managed marketplace restrictions](/en/plugin-marketplaces#managed-marketplace-restrictions) |275| `blockedMarketplaces` | Blocklist of marketplace sources. Blocked sources are checked before downloading, so they never touch the filesystem. See [managed marketplace restrictions](/en/plugin-marketplaces#managed-marketplace-restrictions) |

170| `allowedChannelPlugins` | (Managed settings only) Allowlist of channel plugins that may push messages. Replaces the default Anthropic allowlist when set. Undefined = fall back to the default, empty array = block all channel plugins. Requires `channelsEnabled: true`. See [Restrict which channel plugins can run](/en/channels#restrict-which-channel-plugins-can-run) | `[{ "marketplace": "claude-plugins-official", "plugin": "telegram" }]` |170| `allowedChannelPlugins` | (Managed settings only) Allowlist of channel plugins that may push messages. Replaces the default Anthropic allowlist when set. Undefined = fall back to the default, empty array = block all channel plugins. Requires `channelsEnabled: true`. See [Restrict which channel plugins can run](/en/channels#restrict-which-channel-plugins-can-run) | `[{ "marketplace": "claude-plugins-official", "plugin": "telegram" }]` |

171| `allowedHttpHookUrls` | Allowlist of URL patterns that HTTP hooks may target. Supports `*` as a wildcard. When set, hooks with non-matching URLs are blocked. Undefined = no restriction, empty array = block all HTTP hooks. Arrays merge across settings sources. See [Hook configuration](#hook-configuration) | `["https://hooks.example.com/*"]` |171| `allowedHttpHookUrls` | Allowlist of URL patterns that HTTP hooks may target. Supports `*` as a wildcard. When set, hooks with non-matching URLs are blocked. Undefined = no restriction, empty array = block all HTTP hooks. Arrays merge across settings sources. See [Hook configuration](#hook-configuration) | `["https://hooks.example.com/*"]` |

172| `allowedMcpServers` | When set in managed-settings.json, allowlist of MCP servers users can configure. Undefined = no restrictions, empty array = lockdown. Applies to all scopes. Denylist takes precedence. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) | `[{ "serverName": "github" }]` |172| `allowedMcpServers` | When set in managed-settings.json, allowlist of MCP servers users can configure. Undefined = no restrictions, empty array = lockdown. Applies to all scopes. Denylist takes precedence. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) | `[{ "serverName": "github" }]` |

173| `allowManagedHooksOnly` | (Managed settings only) Prevent loading of user, project, and plugin hooks. Only allows managed hooks and SDK hooks. See [Hook configuration](#hook-configuration) | `true` |173| `allowManagedHooksOnly` | (Managed settings only) Only managed hooks, SDK hooks, and hooks from plugins force-enabled in managed settings `enabledPlugins` are loaded. User, project, and all other plugin hooks are blocked. See [Hook configuration](#hook-configuration) | `true` |

174| `allowManagedMcpServersOnly` | (Managed settings only) Only `allowedMcpServers` from managed settings are respected. `deniedMcpServers` still merges from all sources. Users can still add MCP servers, but only the admin-defined allowlist applies. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) | `true` |174| `allowManagedMcpServersOnly` | (Managed settings only) Only `allowedMcpServers` from managed settings are respected. `deniedMcpServers` still merges from all sources. Users can still add MCP servers, but only the admin-defined allowlist applies. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) | `true` |

175| `allowManagedPermissionRulesOnly` | (Managed settings only) Prevent user and project settings from defining `allow`, `ask`, or `deny` permission rules. Only rules in managed settings apply. See [Managed-only settings](/en/permissions#managed-only-settings) | `true` |175| `allowManagedPermissionRulesOnly` | (Managed settings only) Prevent user and project settings from defining `allow`, `ask`, or `deny` permission rules. Only rules in managed settings apply. See [Managed-only settings](/en/permissions#managed-only-settings) | `true` |

176| `alwaysThinkingEnabled` | Enable [extended thinking](/en/common-workflows#use-extended-thinking-thinking-mode) by default for all sessions. Typically configured via the `/config` command rather than editing directly | `true` |176| `alwaysThinkingEnabled` | Enable [extended thinking](/en/common-workflows#use-extended-thinking-thinking-mode) by default for all sessions. Typically configured via the `/config` command rather than editing directly | `true` |

428**Behavior when `allowManagedHooksOnly` is `true`:**428**Behavior when `allowManagedHooksOnly` is `true`:**

429 429 

430* Managed hooks and SDK hooks are loaded430* Managed hooks and SDK hooks are loaded

431* User hooks, project hooks, and plugin hooks are blocked431* Hooks from plugins force-enabled in managed settings `enabledPlugins` are loaded. This lets administrators distribute vetted hooks through an organization marketplace while blocking everything else. Trust is granted by full `plugin@marketplace` ID, so a plugin with the same name from a different marketplace stays blocked

432* User hooks, project hooks, and all other plugin hooks are blocked

432 433 

433**Restrict HTTP hook URLs:**434**Restrict HTTP hook URLs:**

434 435 

1037 1037 

1038**Notifications share the status line row**1038**Notifications share the status line row**

1039 1039 

1040* System notifications like MCP server errors, auto-updates, and token warnings display on the right side of the same row as your status line1040* System notifications like MCP server errors and auto-updates display on the right side of the same row as your status line. Transient notifications such as the context-low warning also cycle through this area.

1041* Enabling verbose mode adds a token counter to this area1041* Enabling verbose mode adds a token counter to this area

1042* On narrow terminals, these notifications may truncate your status line output1042* On narrow terminals, these notifications may truncate your status line output

232 232 

233The frontmatter defines the subagent's metadata and configuration. The body becomes the system prompt that guides the subagent's behavior. Subagents receive only this system prompt (plus basic environment details like working directory), not the full Claude Code system prompt.233The frontmatter defines the subagent's metadata and configuration. The body becomes the system prompt that guides the subagent's behavior. Subagents receive only this system prompt (plus basic environment details like working directory), not the full Claude Code system prompt.

234 234 

235A subagent starts in the main conversation's current working directory. Within a subagent, `cd` commands do not persist between Bash or PowerShell tool calls and do not affect the main conversation's working directory. To give the subagent an isolated copy of the repository instead, set [`isolation: worktree`](#supported-frontmatter-fields).

236 

235#### Supported frontmatter fields237#### Supported frontmatter fields

236 238 

237The following fields can be used in the YAML frontmatter. Only `name` and `description` are required.239The following fields can be used in the YAML frontmatter. Only `name` and `description` are required.

64 64 

65The Bash tool runs each command in a separate process with the following persistence behavior:65The Bash tool runs each command in a separate process with the following persistence behavior:

66 66 

67* When Claude runs `cd`, the new working directory carries over to later Bash commands as long as it stays inside the project directory or an [additional working directory](/en/permissions#working-directories) you added with `--add-dir`, `/add-dir`, or `additionalDirectories` in settings.67* When Claude runs `cd` in the main session, the new working directory carries over to later Bash commands as long as it stays inside the project directory or an [additional working directory](/en/permissions#working-directories) you added with `--add-dir`, `/add-dir`, or `additionalDirectories` in settings. Subagent sessions never carry over working directory changes.

68 * If `cd` lands outside those directories, Claude Code resets to the project directory and appends `Shell cwd was reset to <dir>` to the tool result.68 * If `cd` lands outside those directories, Claude Code resets to the project directory and appends `Shell cwd was reset to <dir>` to the tool result.

69 * To disable this carry-over so every Bash command starts in the project directory, set `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR=1`.69 * To disable this carry-over so every Bash command starts in the project directory, set `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR=1`.

70* Environment variables do not persist. An `export` in one command will not be available in the next.70* Environment variables do not persist. An `export` in one command will not be available in the next.

127* `"shell": "powershell"` on individual [command hooks](/en/hooks#command-hook-fields): runs that hook in PowerShell. Hooks spawn PowerShell directly, so this works regardless of `CLAUDE_CODE_USE_POWERSHELL_TOOL`.127* `"shell": "powershell"` on individual [command hooks](/en/hooks#command-hook-fields): runs that hook in PowerShell. Hooks spawn PowerShell directly, so this works regardless of `CLAUDE_CODE_USE_POWERSHELL_TOOL`.

128* `shell: powershell` in [skill frontmatter](/en/skills#frontmatter-reference): runs `` !`command` `` blocks in PowerShell. Requires the PowerShell tool to be enabled.128* `shell: powershell` in [skill frontmatter](/en/skills#frontmatter-reference): runs `` !`command` `` blocks in PowerShell. Requires the PowerShell tool to be enabled.

129 129 

130The same main-session working-directory reset behavior described under the Bash tool section applies to PowerShell commands, including the `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` environment variable.

131 

130### Preview limitations132### Preview limitations

131 133 

132The PowerShell tool has the following known limitations during the preview:134The PowerShell tool has the following known limitations during the preview: