2026年5月20日 03:37

23 ファイル変更+392-50

この更新の概要

ツール実行の許可・拒否を制御するパーミッションの仕組みが強化され、特定のツール名のみを指定してコンテキストから完全に削除する設定が可能になりました。TypeScript SDKにはエージェントの進行状況サマリーやタイムアウト設定、プロンプト生成の新しいオプションなど、多数のフィールドが追加されています。新しく「コミュニティマーケットプレイス」が導入され、サードパーティ製プラグインのインストールと利用手順が整理されました。また、プロンプトキャッシュに関する詳細な解説ドキュメントが新設され、コスト最適化やキャッシュの有効期限に関する仕様が明確化されています。

agent-sdk/custom-tools+3-3

ツールの可用性と実行許可の2つのレイヤーについて解説が更新され、特定のツール名を指定してコンテキストから完全に削除する方法が明記されました。

@@ -308,16 +308,16 @@ When MCP tools are exposed to Claude, their names follow a specific format:

### Configure allowed tools

The `tools` option and the allowed/disallowed lists operate on separate layers. `tools` controls which built-in tools appear in Claude's context. Allowed and disallowed tool lists control whether calls are approved or denied once Claude attempts them.

The `tools` option and the allowed/disallowed lists affect two layers: availability, which controls whether a tool appears in Claude's context, and permission, which controls whether a call is approved once Claude attempts it. `tools` and bare-name `disallowedTools` entries change availability. `allowedTools` and scoped `disallowedTools` rules change permission only.

| Option | Layer | Effect |

| :- | :- | :- |

| `tools: ["Read", "Grep"]` | Availability | Only the listed built-ins are in Claude's context. Unlisted built-ins are removed. MCP tools are unaffected. |

| `tools: []` | Availability | All built-ins are removed. Claude can only use your MCP tools. |

| allowed tools | Permission | Listed tools run without a permission prompt. Unlisted tools remain available; calls go through the [permission flow](/en/agent-sdk/permissions). |

| disallowed tools | Permission | Every call to a listed tool is denied. The tool stays in Claude's context, so Claude may still attempt it before the call is rejected. |

| disallowed tools | Both | A bare tool name such as `"Bash"` removes the tool from Claude's context, the same as omitting it from `tools`. A scoped rule such as `"Bash(rm *)"` leaves the tool in context and denies only matching calls. |

To limit which built-ins Claude can use, prefer `tools` over disallowed tools. Omitting a tool from `tools` removes it from context so Claude never attempts it; listing it in `disallowedTools` (Python: `disallowed_tools`) blocks the call but leaves the tool visible, so Claude may waste a turn trying it. See [Configure permissions](/en/agent-sdk/permissions) for the full evaluation order.

To remove a built-in entirely, omit it from `tools` or list its bare name in `disallowedTools` (Python: `disallowed_tools`); both keep the tool out of context so Claude never attempts it. A scoped `disallowedTools` rule blocks matching calls but leaves the tool visible, so Claude may waste a turn trying it. See [Configure permissions](/en/agent-sdk/permissions) for the full evaluation order.

## Handle errors

agent-sdk/modifying-system-prompts+2-2

TypeScript SDKにおける出力スタイルの設定方法が変更され、query関数の設定オブジェクト内で行うよう修正されています。

@@ -135,7 +135,7 @@ Once created, activate output styles via:

- **CLI**: run `/config` and select an output style

- **Settings**: set `outputStyle` in `.claude/settings.local.json`

- **TypeScript SDK**: set `options.outputStyle` to the style's name

- **TypeScript SDK**: set `outputStyle` inside the inline `settings` object passed to `query()`, or point `settings` at a settings file that sets it. `outputStyle` is not a top-level `Options` field

The Python SDK does not have an option to select an output style programmatically. For code-only deployments where you can't write to `.claude/settings.local.json`, use `append` or a custom prompt string instead.

@@ -418,6 +418,6 @@ async for message in query(

- [Output styles](/en/output-styles): create, manage, and share output styles for the CLI, including the file format and storage locations

- [How Claude remembers your project](/en/memory): what to put in CLAUDE.md, where to place it, and how to write effective project instructions

- [TypeScript SDK reference](/en/agent-sdk/typescript): the full `Options` type, including `systemPrompt`, `settingSources`, and `outputStyle`

- [TypeScript SDK reference](/en/agent-sdk/typescript): the full `Options` type, including `systemPrompt`, `settingSources`, and `settings`

- [Python SDK reference](/en/agent-sdk/python): the full `ClaudeAgentOptions` type, including `system_prompt` and `setting_sources`

- [Settings](/en/settings): the `settings.json` reference, including where output styles and other configuration are stored

agent-sdk/permissions+4-3

拒否ルールの挙動が詳細化され、ツール名のみの指定はコンテキストからの削除、スコープ指定は特定の実行パターンの拒否として機能するよう説明が追加されました。

@@ -17,7 +17,7 @@ When Claude requests a tool, the SDK checks permissions in this order:

Run [hooks](/en/agent-sdk/hooks) first. A hook can deny the call outright or pass it on. A hook that returns `allow` does not skip the deny and ask rules below; those are evaluated regardless of the hook result.

Check `deny` rules (from `disallowed_tools` and [settings.json](/en/settings#permission-settings)). If a deny rule matches, the tool is blocked, even in `bypassPermissions` mode.

Check `deny` rules (from `disallowed_tools` and [settings.json](/en/settings#permission-settings)). If a deny rule matches, the tool is blocked, even in `bypassPermissions` mode. Bare-name `disallowed_tools` entries like `Bash` remove the tool from Claude's context before this evaluation begins, so only scoped rules like `Bash(rm *)` are checked at this step.

Apply the active [permission mode](#permission-modes). `bypassPermissions` approves everything that reaches this step. `acceptEdits` approves file operations. Other modes fall through.

@@ -32,12 +32,13 @@ This page focuses on **allow and deny rules** and **permission modes**. For the

## Allow and deny rules

`allowed_tools` and `disallowed_tools` (TypeScript: `allowedTools` / `disallowedTools`) add entries to the allow and deny rule lists in the evaluation flow above. They control whether a tool call is approved, not whether the tool is available to Claude.

`allowed_tools` and `disallowed_tools` (TypeScript: `allowedTools` / `disallowedTools`) add entries to the allow and deny rule lists in the evaluation flow above. Allow rules only affect approval: a tool not listed in `allowed_tools` is still available to Claude and falls through to the permission mode. Deny rules behave differently depending on whether they name a tool or scope a pattern within one.

| Option | Effect |

| :- | :- |

| `allowed_tools=["Read", "Grep"]` | `Read` and `Grep` are auto-approved. Tools not listed here still exist and fall through to the permission mode and `canUseTool`. |

| `disallowed_tools=["Bash"]` | `Bash` is always denied. Deny rules are checked first and hold in every permission mode, including `bypassPermissions`. |

| `disallowed_tools=["Bash"]` | The `Bash` tool definition is removed from the request. Claude does not see the tool and cannot attempt it. |

| `disallowed_tools=["Bash(rm *)"]` | `Bash` stays available. Calls matching `rm *` are denied in every permission mode, including `bypassPermissions`. Other `Bash` calls fall through to the permission mode. |

For a locked-down agent, pair `allowedTools` with `permissionMode: "dontAsk"`. Listed tools are approved; anything else is denied outright instead of prompting:

agent-sdk/python+1-1

Python SDKのツール拒否設定において、単純なツール名指定とパターン指定による挙動の違いが反映されました。

@@ -785,7 +785,7 @@ class ClaudeAgentOptions:

| `max_budget_usd` | `float \| None` | `None` | Stop the query when the client-side cost estimate reaches this USD value. Compared against the same estimate as `total_cost_usd`; see [Track cost and usage](/en/agent-sdk/cost-tracking) for accuracy caveats |

| `disallowed_tools` | `list[str]` | `[]` | Tools to always deny. Deny rules are checked first and override `allowed_tools` and `permission_mode` (including `bypassPermissions`) |

| `disallowed_tools` | `list[str]` | `[]` | Tools to deny. A bare name such as `"Bash"` removes the tool from Claude's context. A scoped rule such as `"Bash(rm *)"` leaves the tool available and denies matching calls in every permission mode, including `bypassPermissions`. See [Permissions](/en/agent-sdk/permissions#allow-and-deny-rules) |

agent-sdk/typescript+49-10

進行状況のサマリー生成やタイムアウト、ツールエイリアスなど、SDKで利用可能な多数の新しいオプションとメッセージ型が追加されています。

@@ -366,6 +366,7 @@ Configuration object for the `query()` function.

| `agentProgressSummaries` | `boolean` | `false` | When `true`, generate one-line progress summaries for subagents and forward them on [`task_progress`](#sdktaskprogressmessage) events via the `summary` field. Applies to foreground and background subagents |

| `allowedTools` | `string[]` | `[]` | Tools to auto-approve without prompting. This does not restrict Claude to only these tools; unlisted tools fall through to `permissionMode` and `canUseTool`. Use `disallowedTools` to block tools. See [Permissions](/en/agent-sdk/permissions#allow-and-deny-rules) |

@@ -374,7 +375,7 @@ Configuration object for the `query()` function.

| `disallowedTools` | `string[]` | `[]` | Tools to deny. A bare name such as `"Bash"` removes the tool from Claude's context. A scoped rule such as `"Bash(rm *)"` leaves the tool available and denies matching calls in every permission mode, including `bypassPermissions`. See [Permissions](/en/agent-sdk/permissions#allow-and-deny-rules) |

| `env` | `Record<string, string \| undefined>` | `process.env` | Environment variables. See [Environment variables](/en/env-vars) for variables the underlying CLI reads, and [Handle slow or stalled API responses](#handle-slow-or-stalled-api-responses) for timeout-related variables. Set `CLAUDE_AGENT_SDK_CLIENT_APP` to identify your app in the User-Agent header |

@@ -383,20 +384,25 @@ Configuration object for the `query()` function.

| `extraArgs` | `Record<string, string \| null>` | `{}` | Additional arguments |

| `forwardSubagentText` | `boolean` | `false` | Forward subagent text and thinking blocks as assistant and user messages with `parent_tool_use_id` set, so consumers can render a nested transcript. By default only `tool_use` and `tool_result` blocks from subagents are emitted |

| `hooks` | `Partial<Record<`[`HookEvent`](#hookevent)`, `[`HookCallbackMatcher`](#hookcallbackmatcher)`[]>>` | `{}` | Hook callbacks for events |

| `includeHookEvents` | `boolean` | `false` | Include hook lifecycle events in the message stream as [`SDKHookStartedMessage`](#sdkhookstartedmessage), [`SDKHookProgressMessage`](#sdkhookprogressmessage), and [`SDKHookResponseMessage`](#sdkhookresponsemessage) |

| `loadTimeoutMs` | `number` | `60000` | *Alpha.* Timeout in milliseconds for each `sessionStore.load()` and `sessionStore.listSubkeys()` call during resume materialization. If the adapter doesn't settle within this window, the query fails instead of hanging. Ignored when `sessionStore` is not set |

| `managedSettings` | `Settings` | `undefined` | Policy-tier settings supplied by the spawning parent process. Dropped when an IT-controlled managed-settings tier already exists on the machine, unless that admin opts in with `parentSettingsBehavior: 'merge'`. Filtered to restrictive-only keys regardless |

| `maxBudgetUsd` | `number` | `undefined` | Stop the query when the client-side cost estimate reaches this USD value. Compared against the same estimate as `total_cost_usd`; see [Track cost and usage](/en/agent-sdk/cost-tracking) for accuracy caveats |

| `mcpServers` | `Record<string, [`McpServerConfig`](#mcpserverconfig)>` | `{}` | MCP server configurations |

| `onElicitation` | `(request: ElicitationRequest, options: { signal: AbortSignal }) => Promise<ElicitationResult>` | `undefined` | Callback for handling MCP elicitation requests. Called when an MCP server requests user input and no hook handles it first. When not provided, unhandled elicitation requests are declined automatically |

| `outputFormat` | `{ type: 'json_schema', schema: JSONSchema }` | `undefined` | Define output format for agent results. See [Structured outputs](/en/agent-sdk/structured-outputs) for details |

| `outputStyle` | `string` | `undefined` | Name of an [output style](/en/output-styles) to activate for the session. The style must exist in a loaded `settingSources` location, such as `.claude/output-styles/`. See [Activate an output style](/en/agent-sdk/modifying-system-prompts#activate-an-output-style) |

| `outputStyle` | `string` | `undefined` | Not an `Options` field. Set `outputStyle` in the inline [`settings`](/en/settings) object or a settings file instead. See [Activate an output style](/en/agent-sdk/modifying-system-prompts#activate-an-output-style) |

| `pathToClaudeCodeExecutable` | `string` | Auto-resolved from bundled native binary | Path to Claude Code executable. Only needed if optional dependencies were skipped during install or your platform isn't in the supported set |

| `planModeInstructions` | `string` | `undefined` | Custom workflow instructions for plan mode. When `permissionMode` is `'plan'`, this string replaces the default plan-mode workflow body. The CLI still wraps it with the read-only enforcement preamble and the ExitPlanMode protocol footer |

@@ -404,6 +410,7 @@ Configuration object for the `query()` function.

| `sessionStore` | [`SessionStore`](/en/agent-sdk/session-storage#the-sessionstore-interface) | `undefined` | Mirror session transcripts to an external backend so any host can resume them. See [Persist sessions to external storage](/en/agent-sdk/session-storage) |

| `settings` | `string \| Settings` | `undefined` | Inline [settings](/en/settings) object or path to a settings file. Populates the flag-settings layer in the [precedence order](/en/settings#settings-precedence). Change at runtime with [`applyFlagSettings()`](#applyflagsettings) |

| `settingSources` | [`SettingSource`](#settingsource)`[]` | CLI defaults (all sources) | Control which filesystem settings to load. Pass `[]` to disable user, project, and local settings. Managed policy settings load regardless. See [Use Claude Code features](/en/agent-sdk/claude-code-features#what-settingsources-does-not-control) |

| `skills` | `string[] \| 'all'` | `undefined` | Skills available to the session. Pass `'all'` to enable every discovered skill, or a list of skill names. When set, the SDK enables the Skill tool automatically without listing it in `allowedTools`. See [Skills](/en/agent-sdk/skills) |

@@ -411,7 +418,10 @@ Configuration object for the `query()` function.

| `systemPrompt` | `string \| { type: 'preset'; preset: 'claude_code'; append?: string; excludeDynamicSections?: boolean }` | `undefined` (minimal prompt) | System prompt configuration. Pass a string for custom prompt, or `{ type: 'preset', preset: 'claude_code' }` to use Claude Code's system prompt. When using the preset object form, add `append` to extend it with additional instructions, and set `excludeDynamicSections: true` to move per-session context into the first user message for [better prompt-cache reuse across machines](/en/agent-sdk/modifying-system-prompts#improve-prompt-caching-across-users-and-machines) |

| `taskBudget` | `{ total: number }` | `undefined` | *Alpha.* API-side task budget in tokens. When set, the model is told its remaining token budget so it can pace tool use and wrap up before the limit |

| `thinking` | [`ThinkingConfig`](#thinkingconfig) | `{ type: 'adaptive' }` for supported models | Controls Claude's thinking/reasoning behavior. See [`ThinkingConfig`](#thinkingconfig) for options |

| `title` | `string` | `undefined` | Display title for the session. When resuming via `resume` or `continue`, the resumed session's persisted title takes precedence; use [`renameSession()`](#renamesession) to retitle an existing session |

| `toolAliases` | `Record<string, string>` | `undefined` | Map built-in tool names to MCP tool names so Claude calls your MCP implementation in place of the built-in. For example, `{ Bash: 'mcp__workspace__bash' }` |

| `tools` | `string[] \| { type: 'preset'; preset: 'claude_code' }` | `undefined` | Tool configuration. Pass an array of tool names or use the preset to get Claude Code's default tools |

@@ -907,11 +917,17 @@ type SDKMessage =

| SDKTaskStartedMessage

| SDKTaskProgressMessage

| SDKTaskUpdatedMessage

| SDKSessionStateChangedMessage

| SDKNotificationMessage

| SDKFilesPersistedEvent

| SDKToolUseSummaryMessage

| SDKMemoryRecallMessage

| SDKRateLimitEvent

| SDKElicitationCompleteMessage

| SDKPermissionDeniedMessage

| SDKPromptSuggestionMessage;

| SDKPromptSuggestionMessage

| SDKAPIRetryMessage

| SDKMirrorErrorMessage;

```

### `SDKAssistantMessage`

@@ -989,12 +1005,15 @@ type SDKResultMessage =

num_turns: number;

result: string;

stop_reason: string | null;

ttft_ms?: number;

total_cost_usd: number;

usage: NonNullableUsage;

modelUsage: { [modelName: string]: ModelUsage };

permission_denials: SDKPermissionDenial[];

structured_output?: unknown;

deferred_tool_use?: { id: string; name: string; input: Record<string, unknown> };

terminal_reason?: TerminalReason;

fast_mode_state?: FastModeState;

origin?: SDKMessageOrigin;

}

| {

@@ -1016,11 +1035,18 @@ type SDKResultMessage =

modelUsage: { [modelName: string]: ModelUsage };

permission_denials: SDKPermissionDenial[];

errors: string[];

terminal_reason?: TerminalReason;

fast_mode_state?: FastModeState;

origin?: SDKMessageOrigin;

};

```

The `api_error_status` field carries the HTTP status code of the API error that terminated the conversation. It is absent or `null` when the turn ended without an API error.

Several fields on the result carry diagnostic detail beyond `subtype`:

- `api_error_status`: the HTTP status code of the API error that terminated the conversation. Absent or `null` when the turn ended without an API error.

- `ttft_ms`: time to first token in milliseconds. Present on the success arm only.

- `terminal_reason`: why the loop ended. One of `"completed"`, `"max_turns"`, `"tool_deferred"`, `"aborted_streaming"`, `"aborted_tools"`, `"hook_stopped"`, `"stop_hook_prevented"`, `"blocking_limit"`, `"rapid_refill_breaker"`, `"prompt_too_long"`, `"image_error"`, or `"model_error"`.

- `fast_mode_state`: one of `"on"`, `"off"`, or `"cooldown"`.

The `origin` field forwards the [`SDKMessageOrigin`](#sdkmessageorigin) of the user message that triggered this result. When a background task finishes and the SDK injects a synthetic follow-up turn, the resulting `SDKResultMessage` carries `origin: { kind: "task-notification" }`. Check this field to distinguish results that answer your prompt from results emitted for background-task follow-ups, so you can route or suppress the latter. The field is absent for results emitted before any user turn, such as startup errors.

@@ -2698,17 +2724,28 @@ type NonNullableUsage = {

### `Usage`

Token usage statistics (from `@anthropic-ai/sdk`).

Token usage statistics. This is the `BetaUsage` type from `@anthropic-ai/sdk`.

```typescript

type Usage = {

input_tokens: number | null;

output_tokens: number | null;

cache_creation_input_tokens?: number | null;

cache_read_input_tokens?: number | null;

input_tokens: number;

output_tokens: number;

cache_creation_input_tokens: number | null;

cache_read_input_tokens: number | null;

cache_creation: {

ephemeral_5m_input_tokens: number;

ephemeral_1h_input_tokens: number;

} | null;

server_tool_use: BetaServerToolUsage | null;

service_tier: "standard" | "priority" | "batch" | null;

speed: "standard" | "fast" | null;

inference_geo: string | null;

iterations: BetaIterationsUsage | null;

};

```

`BetaServerToolUsage` and `BetaIterationsUsage` are defined in `@anthropic-ai/sdk`.

### `CallToolResult`

MCP tool result type (from `@modelcontextprotocol/sdk/types.js`). `structuredContent` is a JSON object that can be returned alongside `content`, including image blocks. See [Return structured data](/en/agent-sdk/custom-tools#return-structured-data).

@@ -2967,7 +3004,7 @@ type SDKTaskStartedMessage = {

### `SDKTaskProgressMessage`

Emitted periodically while a background task is running.

Emitted periodically while a subagent or background task is running. The `summary` field is populated only when [`agentProgressSummaries`](#options) is enabled.

```typescript

type SDKTaskProgressMessage = {

@@ -2976,12 +3013,14 @@ type SDKTaskProgressMessage = {

task_id: string;

tool_use_id?: string;

description: string;

subagent_type?: string;

usage: {

total_tokens: number;

tool_uses: number;

duration_ms: number;

};

last_tool_name?: string;

summary?: string;

uuid: UUID;

session_id: string;

};

agent-view+3-3

バックグラウンドセッションに名前を付けた際の表示形式や、セッションがアクティブと見なされる条件にサブエージェント等の実行が含まれることが追記されました。

@@ -275,10 +275,10 @@ Pass `--name` to set the session's display name in agent view instead of the aut

claude --bg --name "flaky-test-fix" "investigate the flaky SettingsChangeDetector test"

```

After backgrounding, Claude prints the session's short ID and the commands for managing it:

After backgrounding, Claude prints the session's short ID and the commands for managing it. When you pass `--name`, the name appears after the short ID:

```text

backgrounded · 7c5dcf5d

backgrounded · 7c5dcf5d · flaky-test-fix

claude agents list sessions

claude attach 7c5dcf5d open in this terminal

claude logs 7c5dcf5d show recent output

@@ -395,7 +395,7 @@ Background sessions are hosted by a per-user supervisor process, separate from y

The supervisor and its sessions authenticate with the same credentials as your interactive sessions and make no additional network connections beyond the model API.

Each background session is its own Claude Code process, managed by the supervisor rather than tied to your terminal. A session that's actively working, waiting for your input, or has a terminal attached keeps its process running. A running background shell command, subagent, workflow, or monitor counts as active work, so a long-running process such as a dev server keeps the session alive.

Once a session finishes and sits unattached for about an hour, the supervisor stops its process to free resources. The transcript and state stay on disk, and the next time you attach, peek, or reply, the supervisor starts a fresh process from where it left off. When every session has finished and no terminal is connected, the supervisor itself exits and starts again the next time you need it.

amazon-bedrock+3-1

Amazon Bedrockにおけるプロンプトキャッシュの有効期限と課金体系、およびリージョンごとの制限事項に関する注釈が更新されました。

@@ -255,7 +255,9 @@ export DISABLE_PROMPT_CACHING=1

export ENABLE_PROMPT_CACHING_1H=1

```

<Note>[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) may not be available in all regions. Cache writes with a 1-hour TTL are billed at a higher rate than 5-minute writes.</Note>

The 1-hour cache TTL is billed at a higher rate than the 5-minute default. See [cache lifetime](/en/prompt-caching#cache-lifetime).

<Note>Prompt caching may not be available in all Bedrock regions. If cache token counts stay at zero, check [supported models, regions, and limits](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html#prompt-caching-models) in the Bedrock documentation.</Note>

#### Map each model version to an inference profile

channels-reference+3-1

公式マーケットプレイスとコミュニティマーケットプレイスの区分が明確化され、チャンネルの承認プロセスに関する説明が修正されています。

@@ -710,7 +710,9 @@ The three channel-specific pieces in this file:

To make your channel installable and shareable, wrap it in a [plugin](/en/plugins) and publish it to a [marketplace](/en/plugin-marketplaces). Users install it with `/plugin install`, then enable it per session with `--channels plugin:<name>@<marketplace>`.

A channel published to your own marketplace still needs `--dangerously-load-development-channels` to run, since it isn't on the [approved allowlist](/en/channels#supported-channels). To get it added, [submit it to the official marketplace](/en/plugins#submit-your-plugin-to-the-official-marketplace). Channel plugins go through security review before being approved. On Team and Enterprise plans, an admin can instead include your plugin in the organization's own [`allowedChannelPlugins`](/en/channels#restrict-which-channel-plugins-can-run) list, which replaces the default Anthropic allowlist.

A channel published to your own marketplace still needs `--dangerously-load-development-channels` to run, since it isn't on the [approved allowlist](/en/channels#supported-channels). The default allowlist is the channel plugins in `claude-plugins-official`, which Anthropic curates at its discretion. The [in-app submission forms](/en/plugins#submit-your-plugin-to-the-community-marketplace) add plugins to the community marketplace, which is not on the channel allowlist.

If you are working with an Anthropic partner contact, reach out to them to coordinate an official-marketplace listing. On Team and Enterprise plans, an admin can instead include your plugin in the organization's own [`allowedChannelPlugins`](/en/channels#restrict-which-channel-plugins-can-run) list, which replaces the default Anthropic allowlist.

## See also

claude-platform-on-aws+1-1

プロンプトキャッシュの有効期限設定に関する環境変数の説明と、価格設定ページへのリンクが更新されました。

@@ -151,7 +151,7 @@ export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-haiku-4-5

For the full list of model IDs and aliases, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). For other model-related variables, see [Model configuration](/en/model-config).

[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) is enabled automatically. 1-hour cache writes are billed at a higher rate than 5-minute writes. To request a 1-hour cache TTL instead of the 5-minute default, set `ENABLE_PROMPT_CACHING_1H=1`.

[Prompt caching](/en/prompt-caching) is enabled automatically. To request a 1-hour cache TTL instead of the 5-minute default, set `ENABLE_PROMPT_CACHING_1H=1`. The API bills 1-hour cache writes at a higher rate. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing) for the rates.

## Use the Agent SDK

cli-reference+1-1

コマンドライン引数でのツール拒否設定において、特定のツールをコンテキストから削除する動作について具体例が追加されました。

@@ -66,7 +66,7 @@ Customize Claude Code's behavior with these command-line flags. `claude --help`

| `--debug` | Enable debug mode with optional category filtering (for example, `"api,hooks"` or `"!statsig,!file"`) | `claude --debug "api,mcp"` |

| `--debug-file <path>` | Write debug logs to a specific file path. Implicitly enables debug mode. Takes precedence over `CLAUDE_CODE_DEBUG_LOGS_DIR` | `claude --debug-file /tmp/claude-debug.log` |

| `--disable-slash-commands` | Disable all skills and commands for this session | `claude --disable-slash-commands` |

| `--disallowedTools` | Tools that are removed from the model's context and cannot be used | `"Bash(git log *)" "Bash(git diff *)" "Edit"` |

| `--disallowedTools` | Deny rules. A bare tool name removes that tool from the model's context. A scoped rule such as `Bash(rm *)` leaves the tool available and denies only matching calls | `"Bash(git log *)" "Bash(git diff *)" "Edit"` |

| `--effort` | Set the [effort level](/en/model-config#adjust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. Overrides the [`effortLevel`](/en/settings#available-settings) setting for this session and does not persist | `claude --effort high` |

| `--enable-auto-mode` | Removed in v2.1.111. Auto mode is now in the `Shift+Tab` cycle by default; use `--permission-mode auto` to start in it | `claude --permission-mode auto` |

| `--exclude-dynamic-system-prompt-sections` | Move per-machine sections from the system prompt (working directory, environment info, memory paths, git-repo flag) into the first user message. Improves prompt-cache reuse across different users and machines running the same task. Only applies with the default system prompt; ignored when `--system-prompt` or `--system-prompt-file` is set. Use with `-p` for scripted, multi-user workloads | `claude -p --exclude-dynamic-system-prompt-sections "query"` |

context-window+1-0

プロンプトキャッシュが無効化されるアクションについての解説項目が追加されました。

@@ -48,4 +48,5 @@ For deeper coverage of the features shown in the timeline, see these pages:

- [Store instructions and memories](/en/memory): CLAUDE.md hierarchy and auto memory

- [Subagents](/en/sub-agents): delegate research to a separate context window

- [Best practices](/en/best-practices): managing context as your primary constraint

- [Prompt caching](/en/prompt-caching): which actions invalidate the cached prefix

- [Reduce token usage](/en/costs#reduce-token-usage): strategies for keeping context usage low

costs+1-1

コスト最適化の手段として新設されたプロンプトキャッシュの説明ページへの参照が追加されました。

@@ -71,7 +71,7 @@ To keep agent team costs manageable:

## Reduce token usage

Token costs scale with context size: the more context Claude processes, the more tokens you use. Claude Code automatically optimizes costs through prompt caching (which reduces costs for repeated content like system prompts) and auto-compaction (which summarizes conversation history when approaching context limits).

Token costs scale with context size: the more context Claude processes, the more tokens you use. Claude Code automatically optimizes costs through [prompt caching](/en/prompt-caching), which reduces costs for repeated content like system prompts, and auto-compaction, which summarizes conversation history when approaching context limits.

The following strategies help you keep context small and reduce per-message costs.

discover-plugins+17-6

新設されたコミュニティマーケットプレイスの利用方法と、プラグインの追加手順が詳しく説明されています。

@@ -33,12 +33,7 @@ To install a plugin from the official marketplace, use `/plugin install <name>@c

If Claude Code reports that the plugin is not found in any marketplace, your marketplace is either missing or outdated. Run `/plugin marketplace update claude-plugins-official` to refresh it, or `/plugin marketplace add anthropics/claude-plugins-official` if you haven't added it before. Then retry the install.

The official marketplace is maintained by Anthropic. To submit a plugin to the official marketplace, use one of the in-app submission forms:

- **Claude.ai**: [claude.ai/settings/plugins/submit](https://claude.ai/settings/plugins/submit)

- **Console**: [platform.claude.com/plugins/submit](https://platform.claude.com/plugins/submit)

To distribute plugins independently, [create your own marketplace](/en/plugin-marketplaces) and share it with users.

The official marketplace is curated by Anthropic, and inclusion is at Anthropic's discretion. The in-app submission forms add plugins to the [community marketplace](#community-marketplace), not the official one. To distribute plugins independently, [create your own marketplace](/en/plugin-marketplaces) and share it with users.

The official marketplace includes several categories of plugins:

@@ -102,6 +97,22 @@ Customize how Claude responds:

- **explanatory-output-style**: Educational insights about implementation choices

- **learning-output-style**: Interactive learning mode for skill building

## Community marketplace

The community marketplace at [`anthropics/claude-plugins-community`](https://github.com/anthropics/claude-plugins-community) hosts third-party plugins that have passed Anthropic's automated validation and safety screening. Each plugin is pinned to a specific commit SHA in the catalog. Unlike the official marketplace, you add it manually:

```shell

/plugin marketplace add anthropics/claude-plugins-community

```

Then install plugins from it using the `claude-community` marketplace name:

```shell

/plugin install <plugin-name>@claude-community

```

To submit your own plugin to the community marketplace, see [Submit your plugin to the community marketplace](/en/plugins#submit-your-plugin-to-the-community-marketplace) in the create-plugins guide.

## Try it: add the demo marketplace

Anthropic also maintains a [demo plugins marketplace](https://github.com/anthropics/claude-code/tree/main/plugins) (`claude-code-plugins`) with example plugins that show what's possible with the plugin system. Unlike the official marketplace, you need to add this one manually.

env-vars+75-6

環境変数の設定方法や優先順位、各変数の詳細なリファレンスが大幅に加筆・整理されました。

@@ -5,9 +5,78 @@ source: https://code.claude.com/docs/en/env-vars.md

# Environment variables

> Complete reference for environment variables that control Claude Code behavior.

> Reference for environment variables that control Claude Code behavior.

Claude Code supports the following environment variables to control its behavior. Set them in your shell before launching `claude`, or configure them in [`settings.json`](/en/settings#available-settings) under the `env` key to apply them to every session or roll them out across your team.

Environment variables can control Claude Code behavior such as model selection, authentication, request routing, and feature toggles. Many of the same behaviors can also be configured through a [settings file](/en/settings) field, a [CLI flag](/en/cli-reference), or an in-session command like `/model`.

This page covers how to:

- [Set environment variables](#set-environment-variables) in your shell or in a settings file

- [Check which value applies](#precedence) when a behavior can be set more than one way

- [Look up the variables Claude Code reads](#variables)

## Set environment variables

A variable you set in your shell lasts for that terminal session, while a variable in a settings file applies every time `claude` runs.

### In your shell

Set the variable before launching `claude`:

```bash theme={null}

export API_TIMEOUT_MS="1200000"

claude

```

To set it for every session, add the `export` line to `~/.bashrc`, `~/.zshrc`, or your shell's profile file.

```powershell theme={null}

$env:API_TIMEOUT_MS = "1200000"

claude

```

To set it for every session, run `[Environment]::SetEnvironmentVariable("API_TIMEOUT_MS", "1200000", "User")` and open a new terminal.

```batch theme={null}

set API_TIMEOUT_MS=1200000

claude

```

To set it for every session, run `setx API_TIMEOUT_MS "1200000"` and open a new terminal.

### In settings files

Add variables under the `env` key in a `settings.json` file. Claude Code reads them directly from the file at startup, so they take effect no matter how `claude` was launched.

```json ~/.claude/settings.json theme={null}

{

"env": {

"API_TIMEOUT_MS": "1200000",

"BASH_DEFAULT_TIMEOUT_MS": "300000"

}

```

The file you choose controls who the variables apply to:

| File | Applies to |

| :- | :- |

| `~/.claude/settings.json` | You, in every project |

| `.claude/settings.json` | Everyone working in the project, checked into source control |

| `.claude/settings.local.json` | You, in this project only, not checked in |

| Managed settings | Everyone in your organization, deployed by an admin |

See [Settings files](/en/settings#settings-files) for where each file lives and [Settings precedence](/en/settings#settings-precedence) for how they combine when more than one sets the same variable.

## Precedence

Where the same behavior has both an environment variable and a settings field, the environment variable takes precedence. For example, `ANTHROPIC_MODEL` overrides the `model` setting, and `CLAUDE_CODE_AUTO_CONNECT_IDE` overrides `autoConnectIde`. The settings field applies when the environment variable is not set.

How an environment variable interacts with CLI flags and in-session commands varies per feature: `--model` and `/model` override `ANTHROPIC_MODEL`, while `CLAUDE_CODE_EFFORT_LEVEL` overrides `/effort`. When a variable interacts with another configuration source, its row in the [Variables](#variables) list states the precedence or links to the page that documents it.

Claude Code reads environment variables at startup, so changes take effect the next time you launch `claude`.

## Variables

| Variable | Purpose |

| :- | :- |

@@ -98,7 +167,7 @@ Claude Code supports the following environment variables to control its behavior

| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in [fullscreen rendering](/en/fullscreen) and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appear |

| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`, `xhigh`, `max`, or `auto` to use the model default. Available levels depend on the model. Takes precedence over `/effort` and the `effortLevel` setting. See [Adjust effort level](/en/model-config#adjust-effort-level) |

| `CLAUDE_CODE_ENABLE_AWAY_SUMMARY` | Override [session recap](/en/interactive-mode#session-recap) availability. Set to `0` to force recaps off regardless of the `/config` toggle. Set to `1` to force recaps on when [`awaySummaryEnabled`](/en/settings#available-settings) is `false`. Takes precedence over the setting and `/config` toggle |

| `CLAUDE_CODE_ENABLE_BACKGROUND_PLUGIN_REFRESH` | Set to `1` to refresh plugin state at turn boundaries in [non-interactive mode](/en/headless) after a background install completes. Off by default because the refresh changes the system prompt mid-session, which invalidates [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for that turn |

| `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` | Set to `1` to route the "How is Claude doing?" session quality survey to your own [OpenTelemetry collector](/en/monitoring-usage) when Anthropic-bound nonessential traffic is blocked. Survey ratings are emitted only as OTEL events to your configured collector. No survey data is sent to Anthropic in this mode. Applies when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`, `DISABLE_TELEMETRY`, or `DO_NOT_TRACK` is set, and has no effect otherwise. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` and the organization product feedback policy take precedence |

| `CLAUDE_CODE_ENABLE_FINE_GRAINED_TOOL_STREAMING` | Controls whether tool call inputs stream from the API as Claude generates them. With this off, a large tool input such as a long file write arrives only after Claude finishes generating it, which can look like it's hanging. Enabled by default on the Anthropic API. On Bedrock and Vertex, enabled per model where the deployed container supports it. Set to `0` to opt out. Set to `1` to force on when routing through a proxy via `ANTHROPIC_BASE_URL`, `ANTHROPIC_VERTEX_BASE_URL`, or `ANTHROPIC_BEDROCK_BASE_URL`. Off by default on Foundry and [gateway](/en/llm-gateway) connections |

| `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY` | Set to `1` to populate the `/model` picker from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway such as LiteLLM, Kong, or an internal proxy. Off by default because gateways backed by a shared API key would otherwise show every user every model the key can access. Discovered models are still filtered by the [`availableModels`](/en/settings#available-settings) allowlist |

@@ -204,7 +273,7 @@ Claude Code supports the following environment variables to control its behavior

| `DISABLE_INTERLEAVED_THINKING` | Set to `1` to prevent sending the interleaved-thinking beta header. Useful when your LLM gateway or provider does not support [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#interleaved-thinking) |

| `DISABLE_LOGIN_COMMAND` | Set to `1` to hide the `/login` command. Useful when authentication is handled externally via API keys or `apiKeyHelper` |

| `DISABLE_LOGOUT_COMMAND` | Set to `1` to hide the `/logout` command |

| `DISABLE_PROMPT_CACHING` | Set to `1` to disable prompt caching for all models (takes precedence over per-model settings) |

| `DISABLE_PROMPT_CACHING` | Set to `1` to disable [prompt caching](/en/prompt-caching#disable-prompt-caching) for all models (takes precedence over per-model settings) |

| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for Haiku models |

| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for Opus models |

| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models |

@@ -213,7 +282,7 @@ Claude Code supports the following environment variables to control its behavior

| `DISABLE_UPGRADE_COMMAND` | Set to `1` to hide the `/upgrade` command |

| `DO_NOT_TRACK` | Set to `1` to opt out of telemetry. Equivalent to setting `DISABLE_TELEMETRY`. Honored as the [standard cross-tool convention](https://consoledonottrack.com/) |

| `ENABLE_CLAUDEAI_MCP_SERVERS` | Set to `false` to disable [claude.ai MCP servers](/en/mcp#use-mcp-servers-from-claude-ai) in Claude Code. Enabled by default for logged-in users |

| `ENABLE_PROMPT_CACHING_1H` | Set to `1` to request a 1-hour prompt cache TTL instead of the default 5 minutes. Intended for API key, [Bedrock](/en/amazon-bedrock), [Vertex](/en/google-vertex-ai), [Foundry](/en/microsoft-foundry), and [Claude Platform on AWS](/en/claude-platform-on-aws) users. Subscription users receive 1-hour TTL automatically. 1-hour cache writes are billed at a higher rate |

| `ENABLE_PROMPT_CACHING_1H` | Set to `1` to request a 1-hour [prompt cache TTL](/en/prompt-caching#cache-lifetime) instead of the default 5 minutes. Intended for API key, [Bedrock](/en/amazon-bedrock), [Vertex](/en/google-vertex-ai), [Foundry](/en/microsoft-foundry), and [Claude Platform on AWS](/en/claude-platform-on-aws) users. Subscription users within included usage receive 1-hour TTL automatically. 1-hour cache writes are billed at a higher rate |

| `ENABLE_PROMPT_CACHING_1H_BEDROCK` | Deprecated. Use `ENABLE_PROMPT_CACHING_1H` instead |

| `ENABLE_TOOL_SEARCH` | Controls [MCP tool search](/en/mcp#scale-with-mcp-tool-search). Unset: all MCP tools deferred by default, but loaded upfront on Vertex AI or when `ANTHROPIC_BASE_URL` points to a non-first-party host. Values: `true` (always defer and send the beta header, requests fail on Vertex AI models earlier than Sonnet 4.5 or Opus 4.5, or on proxies that do not support `tool_reference`), `auto` (threshold mode: load upfront if tools fit within 10% of context), `auto:N` (custom threshold, e.g., `auto:5` for 5%), `false` (load all upfront) |

| `FALLBACK_FOR_ALL_PRIMARY_MODELS` | Set to any non-empty value to trigger fallback to [`--fallback-model`](/en/cli-reference#cli-flags) after repeated overload errors on any primary model. By default, only Opus models trigger the fallback |

@@ -261,7 +330,7 @@ Standard OpenTelemetry exporter variables (`OTEL_METRICS_EXPORTER`, `OTEL_LOGS_E

## See also

- [Settings](/en/settings): configure environment variables in `settings.json` so they apply to every session

- [Settings](/en/settings): all `settings.json` configuration, including the `env` key

- [CLI reference](/en/cli-reference): launch-time flags

- [Network configuration](/en/network-config): proxy and TLS setup

- [Monitoring](/en/monitoring-usage): OpenTelemetry configuration

google-vertex-ai+1-1

プロンプトキャッシュの詳細説明へのリンクが追加されました。

@@ -185,7 +185,7 @@ export VERTEX_REGION_CLAUDE_4_6_SONNET=europe-west1

Most model versions have a corresponding `VERTEX_REGION_CLAUDE_*` variable. See the [Environment variables reference](/en/env-vars) for the full list. Check [Vertex Model Garden](https://console.cloud.google.com/vertex-ai/model-garden) to determine which models support global endpoints versus regional only.

[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) is enabled automatically. To disable it, set `DISABLE_PROMPT_CACHING=1`. To request a 1-hour cache TTL instead of the 5-minute default, set `ENABLE_PROMPT_CACHING_1H=1`; cache writes with a 1-hour TTL are billed at a higher rate. For heightened rate limits, contact Google Cloud support. When using Vertex AI, the `/login` and `/logout` commands are disabled since authentication is handled through Google Cloud credentials.

[Prompt caching](/en/prompt-caching) is enabled automatically. To disable it, set `DISABLE_PROMPT_CACHING=1`. To request a 1-hour cache TTL instead of the 5-minute default, set `ENABLE_PROMPT_CACHING_1H=1`; cache writes with a 1-hour TTL are billed at a higher rate. For heightened rate limits, contact Google Cloud support. When using Vertex AI, the `/login` and `/logout` commands are disabled since authentication is handled through Google Cloud credentials.

Claude Code disables [MCP tool search](/en/mcp#scale-with-mcp-tool-search) by default on Vertex AI, so MCP tool definitions load upfront. Vertex AI supports tool search for Claude Sonnet 4.5 and later and Claude Opus 4.5 and later. Set `ENABLE_TOOL_SEARCH=true` to enable it on those models. Earlier models on Vertex AI do not accept the required beta header, and requests fail if you enable tool search with them.

mcp+2-0

Model Context Protocolに関するリファレンス情報が補完されました。

@@ -677,6 +677,8 @@ In Claude Code, use the command:

Claude.ai servers appear in the list with indicators showing they come from Claude.ai.

Claude.ai connectors are fetched only when your active [authentication method](/en/authentication#authentication-precedence) is your Claude.ai subscription. They are not loaded when `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, `apiKeyHelper`, or a third-party provider such as Bedrock or Vertex is active, even if you previously ran `/login`. If `/mcp` does not list a connector you added, run `/status` to confirm which authentication method is active, unset that environment variable or remove the `apiKeyHelper` setting, then run `/login` to select your Claude.ai account.

A server you've added in Claude Code takes [precedence](#scope-hierarchy-and-precedence) over a claude.ai connector that points at the same URL. When this happens, `/mcp` lists the connector as hidden and shows how to remove the duplicate if you'd rather use the connector.

To disable claude.ai MCP servers in Claude Code, set the `ENABLE_CLAUDEAI_MCP_SERVERS` environment variable to `false`:

microsoft-foundry+1-1

プラットフォーム固有の環境におけるプロンプトキャッシュ関連のリンクが更新されました。

@@ -152,7 +152,7 @@ Background tasks such as session title generation use the small/fast model, norm

For current and legacy model IDs, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). See [Model configuration](/en/model-config#pin-models-for-third-party-deployments) for the full list of environment variables.

[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) is enabled automatically. To request a 1-hour cache TTL instead of the 5-minute default, set the following variable; cache writes with a 1-hour TTL are billed at a higher rate:

[Prompt caching](/en/prompt-caching) is enabled automatically. To request a 1-hour cache TTL instead of the 5-minute default, set the following variable; cache writes with a 1-hour TTL are billed at a higher rate:

```bash

export ENABLE_PROMPT_CACHING_1H=1

model-config+3-3

モデル構成に関する設定項目の記述が微調整されました。

@@ -394,13 +394,13 @@ Overrides replace the built-in model IDs that back each entry in the `/model` pi

### Prompt caching configuration

Claude Code automatically uses [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) to optimize performance and reduce costs. You can disable prompt caching globally or for specific model tiers:

Claude Code automatically uses [prompt caching](/en/prompt-caching) to optimize performance and reduce costs. You can disable prompt caching globally or for specific model tiers:

| Environment variable | Description |

| - | - |

| `DISABLE_PROMPT_CACHING` | Set to `1` to disable prompt caching for all models (takes precedence over per-model settings) |

| `DISABLE_PROMPT_CACHING` | Set to `1` to disable prompt caching for all models. Takes precedence over the per-model settings |

| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for Haiku models only |

| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models only |

| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for Opus models only |

These environment variables give you fine-grained control over prompt caching behavior. The global `DISABLE_PROMPT_CACHING` setting takes precedence over the model-specific settings, allowing you to quickly disable all caching when needed. The per-model settings are useful for selective control, such as when debugging specific models or working with cloud providers that may have different caching implementations.

To change the cache TTL or learn what triggers a cache miss, see [How Claude Code uses prompt caching](/en/prompt-caching).

output-styles+2-2

出力スタイルの適用に関する内部リンクが修正されました。

@@ -37,7 +37,7 @@ To set a style without the menu, edit the `outputStyle` field directly in a sett

}

```

Because the output style is set in the system prompt at session start, changes take effect the next time you start a new session. This keeps the system prompt stable throughout a conversation so prompt caching can reduce latency and cost.

Output style is part of the system prompt, which Claude Code reads once at session start. Changes take effect after `/clear` or a new session. See [How Claude Code uses prompt caching](/en/prompt-caching#changing-output-style) for what an output style change does to the cache.

## Create a custom output style

@@ -67,7 +67,7 @@ When explaining code, architecture, or data flow, start with a Mermaid diagram s

Use `flowchart TD` for control flow and `sequenceDiagram` for request paths. Keep diagrams under 15 nodes.

```

Run `/config` and select your style under **Output style**. It takes effect the next time you start a session.

Run `/config` and select your style under **Output style**. It takes effect after `/clear` or the next time you start a session.

[Plugins](/en/plugins-reference) can also ship output styles in an `output-styles/` directory.

plugins+14-3

コミュニティマーケットプレイスへのプラグイン提出方法に関するセクションが追加されました。

@@ -327,14 +327,25 @@ When your plugin is ready to share:

Once your plugin is in a marketplace, others can install it using the instructions in [Discover and install plugins](/en/discover-plugins). To keep a plugin internal to your team, host the marketplace in a [private repository](/en/plugin-marketplaces#private-repositories).

### Submit your plugin to the official marketplace

### Submit your plugin to the community marketplace

To submit a plugin to the official Anthropic marketplace, use one of the in-app submission forms:

Anthropic maintains two public marketplaces for Claude Code plugins:

- **`claude-plugins-official`**: a curated set of plugins maintained by Anthropic. Available automatically in every Claude Code installation.

- **`claude-community`**: the public community marketplace where third-party submissions land after review. Users add it with `/plugin marketplace add anthropics/claude-plugins-community` and install from it as `@claude-community`.

To submit your plugin for community-marketplace review, use one of the in-app forms:

- **Claude.ai**: [claude.ai/settings/plugins/submit](https://claude.ai/settings/plugins/submit)

- **Console**: [platform.claude.com/plugins/submit](https://platform.claude.com/plugins/submit)

Once your plugin is listed, you can have your own CLI prompt Claude Code users to install it. See [Recommend your plugin from your CLI](/en/plugin-hints).

Run `claude plugin validate` locally before you submit. The review pipeline runs the same check on every submission, along with automated safety screening.

Approved plugins are pinned to a specific commit SHA in the [`anthropics/claude-plugins-community`](https://github.com/anthropics/claude-plugins-community) catalog, and CI bumps the pin automatically as you push new commits to your repository. The public catalog syncs nightly from the review pipeline, so there can be a delay between approval and your plugin appearing in `marketplace.json`. To check whether your plugin is installable yet, search for its name in the [community catalog](https://github.com/anthropics/claude-plugins-community/blob/main/.claude-plugin/marketplace.json).

The official marketplace, `claude-plugins-official`, is curated separately. Anthropic decides which plugins to include at its discretion. There is no application process, and the submission form does not add plugins to the official marketplace.

If Anthropic lists your plugin in the official marketplace, your CLI can prompt Claude Code users to install it. See [Recommend your plugin from your CLI](/en/plugin-hints).

For complete technical specifications, debugging techniques, and distribution strategies, see [Plugins reference](/en/plugins-reference).

prompt-caching+202-0

プロンプトキャッシュの仕組み、コストメリット、有効期限、手動での無効化方法などを網羅した新規ガイドが作成されました。

(差分が大きいため省略しています)

statusline+2-0

ステータスラインの表示項目に関連する情報が追加されました。

@@ -275,6 +275,8 @@ The `current_usage` object contains:

- `cache_creation_input_tokens`: tokens written to cache

- `cache_read_input_tokens`: tokens read from cache

For what the cache fields mean and how they're billed, see [check cache performance](/en/prompt-caching#check-cache-performance).

The `used_percentage` field is calculated from input tokens only: `input_tokens + cache_creation_input_tokens + cache_read_input_tokens`. It does not include `output_tokens`.

If you calculate context percentage manually from `current_usage`, use the same input-only formula to match `used_percentage`.

sub-agents+1-1

サブエージェントの挙動に関する記述が最新の仕様に合わせて微調整されました。

@@ -810,7 +810,7 @@ A fork inherits everything the main session has at the moment it spawns. A named

| Permissions | Prompts surface in your terminal | [Auto-denied](#run-subagents-in-foreground-or-background) when running in the background |

| Prompt cache | Shared with main session | Separate cache |

Because a fork's system prompt and tool definitions are identical to the parent, its first request reuses the parent's prompt cache. This makes forking cheaper than spawning a fresh subagent for tasks that need the same context.

Because a fork's system prompt and tool definitions are identical to the parent, its first request reuses the parent's [prompt cache](/en/prompt-caching#subagents-and-the-cache). This makes forking cheaper than spawning a fresh subagent for tasks that need the same context.

When Claude spawns a fork through the Agent tool, it can pass `isolation: "worktree"` so the fork's file edits are written to a separate git worktree instead of your checkout.