2026年5月19日 09:32

37 ファイル変更 +294 -158

この更新の概要

背景セッション管理ツールであるAgent Viewに、特定ディレクトリへのスコープ制限や詳細な起動オプションの継承、Gitワークツリーの挙動制御などの新機能が導入されました。Agent SDKでは、従来のタスク管理ツールTodoWriteが非推奨となり、TaskCreateなどの新しいTaskツール群へ刷新されています。あわせて、Claude Opus 4.7以降の推論思考プロセスの表示制御設定や、TypeScript SDKにおけるV2 APIの削除、および最新のセッション管理手法への移行ガイドが追加されました。

agent-sdk/agent-loop +1 -1

タスク管理ツールの定義をTodoWriteからTaskCreateやTaskUpdateに更新しています。

@@ -112,7 +112,7 @@ The SDK includes the same tools that power Claude Code:

| **Execution** | `Bash` | Run shell commands, scripts, git operations |

| **Web** | `WebSearch`, `WebFetch` | Search the web, fetch and parse pages |

| **Discovery** | `ToolSearch` | Dynamically find and load tools on-demand instead of preloading all of them |

| **Orchestration** | `Agent`, `Skill`, `AskUserQuestion`, `TodoWrite` | Spawn subagents, invoke skills, ask the user, track tasks |

| **Orchestration** | `Agent`, `Skill`, `AskUserQuestion`, `TaskCreate`, `TaskUpdate` | Spawn subagents, invoke skills, ask the user, track tasks |

Beyond built-in tools, you can:

agent-sdk/python +28 -8

思考深度を指定するEffortLevel型の定義や、思考プロセスの表示を制御するdisplayオプションの詳細が追加されました。また、TodoWriteが非推奨となり、新しいTaskツールへの移行が推奨されています。

@@ -767,7 +767,7 @@ class ClaudeAgentOptions:

plugins: list[SdkPluginConfig] = field(default_factory=list)

max_thinking_tokens: int | None = None # Deprecated: use thinking instead

thinking: ThinkingConfig | None = None

effort: Literal["low", "medium", "high", "xhigh", "max"] | None = None

effort: EffortLevel | None = None

enable_file_checkpointing: bool = False

session_store: SessionStore | None = None

session_store_flush: SessionStoreFlushMode = "batched"

@@ -814,7 +814,7 @@ class ClaudeAgentOptions:

| `skills` | `list[str] \| Literal["all"] \| None` | `None` | 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 `allowed_tools`. See [Skills](/en/agent-sdk/skills) |

| `session_store` | [`SessionStore`](/en/agent-sdk/session-storage#the-sessionstore-interface) ` \| None` | `None` | Mirror session transcripts to an external backend so any host can resume them. See [Persist sessions to external storage](/en/agent-sdk/session-storage) |

| `session_store_flush` | `Literal["batched", "eager"]` | `"batched"` | When to flush mirrored transcript entries to `session_store`. `"batched"` flushes once per turn or when the buffer fills; `"eager"` triggers a background flush after every frame. Ignored when `session_store` is `None` |

@@ -1014,7 +1014,7 @@ class AgentDefinition:

initialPrompt: str | None = None

maxTurns: int | None = None

background: bool | None = None

effort: Literal["low", "medium", "high", "xhigh", "max"] | int | None = None

effort: EffortLevel | int | None = None

permissionMode: PermissionMode | None = None

```

@@ -1031,7 +1031,7 @@ class AgentDefinition:

| `initialPrompt` | No | Auto-submitted as the first user turn when this agent runs as the main thread agent |

| `maxTurns` | No | Maximum number of agentic turns before the agent stops |

| `background` | No | Run this agent as a non-blocking background task when invoked |

| `effort` | No | Reasoning effort level for this agent. Accepts a named level or an integer |

| `effort` | No | Reasoning effort level for this agent. Accepts a named level or an integer. See [`EffortLevel`](#effortlevel) |

| `permissionMode` | No | Permission mode for tool execution within this agent. See [`PermissionMode`](#permissionmode) |

`AgentDefinition` field names use camelCase, such as `disallowedTools`, `permissionMode`, and `maxTurns`. These names map directly to the wire format shared with the TypeScript SDK. This differs from `ClaudeAgentOptions`, which uses Python snake\_case for the equivalent top-level fields such as `disallowed_tools` and `permission_mode`. Because `AgentDefinition` is a dataclass, passing a snake\_case keyword raises a `TypeError` at construction time.

@@ -1050,6 +1050,20 @@ PermissionMode = Literal[

]

```

### `EffortLevel`

Effort levels for guiding thinking depth.

```python

EffortLevel = Literal[

"low", # Minimal thinking, fastest responses

"medium", # Moderate thinking

"high", # Deep reasoning

"xhigh", # Extended reasoning (Opus 4.7 only; falls back to "high" on other models)

"max", # Maximum effort

]

```

### `CanUseTool`

Type alias for tool permission callback functions.

@@ -1197,12 +1211,16 @@ class ToolsPreset(TypedDict):

Controls extended thinking behavior. A union of three configurations:

```python

ThinkingDisplay = Literal["summarized", "omitted"]

class ThinkingConfigAdaptive(TypedDict):

type: Literal["adaptive"]

display: NotRequired[ThinkingDisplay]

class ThinkingConfigEnabled(TypedDict):

type: Literal["enabled"]

budget_tokens: int

display: NotRequired[ThinkingDisplay]

class ThinkingConfigDisabled(TypedDict):

type: Literal["disabled"]

@@ -1212,10 +1230,12 @@ ThinkingConfig = ThinkingConfigAdaptive | ThinkingConfigEnabled | ThinkingConfig

| Variant | Fields | Description |

| :- | :- | :- |

| `adaptive` | `type` | Claude adaptively decides when to think |

| `enabled` | `type`, `budget_tokens` | Enable thinking with a specific token budget |

| `adaptive` | `type`, `display` | Claude adaptively decides when to think |

| `enabled` | `type`, `budget_tokens`, `display` | Enable thinking with a specific token budget |

| `disabled` | `type` | Disable thinking |

The optional `display` field controls whether thinking text is returned `"summarized"` or `"omitted"`. On Claude Opus 4.7 and later, the API default is `"omitted"`, so set `"summarized"` to receive thinking content in [`ThinkingBlock`](#thinkingblock) outputs.

Because these are `TypedDict` classes, they're plain dicts at runtime. Either construct them as dict literals or call the class like a constructor; both produce a `dict`. Access fields with `config["budget_tokens"]`, not `config.budget_tokens`:

```python

@@ -2139,7 +2159,7 @@ class PostToolUseHookSpecificOutput(TypedDict):

hookEventName: Literal["PostToolUse"]

additionalContext: NotRequired[str]

updatedToolOutput: NotRequired[Any]

updatedMCPToolOutput: NotRequired[Any]

updatedMCPToolOutput: NotRequired[Any] # Deprecated: use updatedToolOutput, which works for all tools

class PostToolUseFailureHookSpecificOutput(TypedDict):

hookEventName: Literal["PostToolUseFailure"]

@@ -2596,7 +2616,7 @@ Runs a background script and delivers each stdout line to Claude as an event so

**Tool name:** `TodoWrite`

`TodoWrite` is deprecated and will be removed in a future release. Use `TaskCreate`, `TaskGet`, `TaskUpdate`, and `TaskList` instead. Set `CLAUDE_CODE_ENABLE_TASKS=1` to opt in. See [Migrate to Task tools](/en/agent-sdk/todo-tracking#migrate-to-task-tools) for how monitoring code changes.

As of Claude Code v2.1.142, `TodoWrite` is disabled by default. Use `TaskCreate`, `TaskGet`, `TaskUpdate`, and `TaskList` instead. See [Migrate to Task tools](/en/agent-sdk/todo-tracking#migrate-to-task-tools) to update your monitoring code, or set `CLAUDE_CODE_ENABLE_TASKS=0` to revert to `TodoWrite`.

**Input:**

agent-sdk/sessions +3 -3

TypeScript SDKにおけるV2セッションAPIの削除と、query関数を使用したV1形式のセッション継続方法について記載が更新されました。

@@ -45,7 +45,7 @@ Both SDKs offer an interface that tracks session state for you across calls, so

### Python: `ClaudeSDKClient`

[`ClaudeSDKClient`](/en/agent-sdk/python#claudesdkclient) handles session IDs internally. Each call to `client.query()` automatically continues the same session. Call [`client.receive_response()`](/en/agent-sdk/python#claudesdkclient) to iterate over the messages for the current query. The client must be used as an async context manager.

This example runs two queries against the same `client`. The first asks the agent to analyze a module; the second asks it to refactor that module. Because both calls go through the same client instance, the second query has full context from the first without any explicit `resume` or session ID:

@@ -96,7 +96,7 @@ See the [Python SDK reference](/en/agent-sdk/python#choosing-between-query-and-c

### TypeScript: `continue: true`

The stable TypeScript SDK (the `query()` function used throughout these docs, sometimes called V1) doesn't have a session-holding client object like Python's `ClaudeSDKClient`. Instead, pass `continue: true` on each subsequent `query()` call and the SDK picks up the most recent session in the current directory. No ID tracking required.

The TypeScript SDK doesn't have a session-holding client object like Python's `ClaudeSDKClient`. Instead, pass `continue: true` on each subsequent `query()` call and the SDK picks up the most recent session in the current directory. No ID tracking required.

This example makes two separate `query()` calls. The first creates a fresh session; the second sets `continue: true`, which tells the SDK to find and resume the most recent session on disk. The agent has full context from the first call:

@@ -127,7 +127,7 @@ for await (const message of query({

}

```

The experimental [V2 session API](/en/agent-sdk/typescript-v2-preview), which provided `createSession()` with a `send` / `stream` pattern, is deprecated. Use the V1 `query()` function and the session options described on this page instead.

The experimental [V2 session API](/en/agent-sdk/typescript-v2-preview), which provided `createSession()` with a `send` / `stream` pattern, was removed in TypeScript Agent SDK 0.3.142. Use the `query()` function and the session options described on this page instead.

## Use session options with `query()`

agent-sdk/todo-tracking +16 -9

タスク管理のデフォルトがTodoWriteから新しいTaskツール群に変更されたことに伴い、監視コードの移行手順や環境変数による旧動作の維持方法が説明されています。

@@ -9,7 +9,7 @@ source: https://code.claude.com/docs/en/agent-sdk/todo-tracking.md

Todo tracking provides a structured way to manage tasks and display progress to users. The Claude Agent SDK includes built-in todo functionality that helps organize complex workflows and keep users informed about task progression.

`TodoWrite` is the current default in the Agent SDK and the examples on this page use it. The replacement Task tools are available now behind `CLAUDE_CODE_ENABLE_TASKS=1` and will become the default in a future release. See [Migrate to Task tools](#migrate-to-task-tools) for how monitoring code changes.

As of TypeScript Agent SDK 0.3.142 and Claude Code v2.1.142, sessions use the structured Task tools `TaskCreate`, `TaskUpdate`, `TaskGet`, and `TaskList` instead of `TodoWrite`. See [Migrate to Task tools](#migrate-to-task-tools) for how monitoring code changes. The examples on this page set `CLAUDE_CODE_ENABLE_TASKS=0` to keep showing `TodoWrite` for sessions that have not migrated yet.

### Todo Lifecycle

@@ -38,7 +38,9 @@ import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({

prompt: "Optimize my React app performance and track progress with todos",

options: { maxTurns: 15 }

// Re-enable TodoWrite, which this example monitors. Without it, the SDK uses

// Task tools instead and these tool_use blocks never appear.

options: { maxTurns: 15, env: { ...process.env, CLAUDE_CODE_ENABLE_TASKS: "0" } }

})) {

// Todo updates are reflected in the message stream

if (message.type === "assistant") {

@@ -63,7 +65,9 @@ from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, ToolUs

async for message in query(

prompt="Optimize my React app performance and track progress with todos",

options=ClaudeAgentOptions(max_turns=15),

# Re-enable TodoWrite, which this example monitors. Without it, the SDK uses

# Task tools instead and these tool_use blocks never appear.

options=ClaudeAgentOptions(max_turns=15, env={"CLAUDE_CODE_ENABLE_TASKS": "0"}),

# Todo updates are reflected in the message stream

if isinstance(message, AssistantMessage):

@@ -112,7 +116,8 @@ class TodoTracker {

async trackQuery(prompt: string) {

for await (const message of query({

prompt,

options: { maxTurns: 20 }

// Re-enable TodoWrite, which this tracker watches for.

options: { maxTurns: 20, env: { ...process.env, CLAUDE_CODE_ENABLE_TASKS: "0" } }

})) {

if (message.type === "assistant") {

for (const block of message.message.content) {

@@ -166,7 +171,11 @@ class TodoTracker:

print(f"{i + 1}. {icon} {text}")

async def track_query(self, prompt: str):

async for message in query(prompt=prompt, options=ClaudeAgentOptions(max_turns=20)):

async for message in query(

prompt=prompt,

# Re-enable TodoWrite, which this tracker watches for.

options=ClaudeAgentOptions(max_turns=20, env={"CLAUDE_CODE_ENABLE_TASKS": "0"}),

if isinstance(message, AssistantMessage):

for block in message.content:

if isinstance(block, ToolUseBlock) and block.name == "TodoWrite":

@@ -180,7 +189,7 @@ await tracker.track_query("Build a complete authentication system with todos")

## Migrate to Task tools

The Task tools split the single `TodoWrite` call into `TaskCreate` for each new item and `TaskUpdate` for each status change, with `TaskList` and `TaskGet` available for the model to read back the current list. Your monitoring code still inspects `tool_use` blocks in the assistant stream, but maintains a map keyed by task ID instead of replacing the whole list on every call. To opt in before the Task tools become the default, set `CLAUDE_CODE_ENABLE_TASKS=1` in `options.env`.

The Task tools split the single `TodoWrite` call into `TaskCreate` for each new item and `TaskUpdate` for each status change, with `TaskList` and `TaskGet` available for the model to read back the current list. Your monitoring code still inspects `tool_use` blocks in the assistant stream, but maintains a map keyed by task ID instead of replacing the whole list on every call. The Task tools are the default as of TypeScript Agent SDK 0.3.142 and Claude Code v2.1.142, so no `options.env` change is needed.

| With `TodoWrite` | With Task tools |

| - | - |

@@ -196,7 +205,6 @@ import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({

prompt: "Optimize my React app performance",

options: { env: { ...process.env, CLAUDE_CODE_ENABLE_TASKS: "1" } },

})) {

if (message.type !== "assistant") continue;

for (const block of message.message.content) {

@@ -213,11 +221,10 @@ for await (const message of query({

```

```python Python theme={null}

from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, ToolUseBlock

from claude_agent_sdk import query, AssistantMessage, ToolUseBlock

async for message in query(

prompt="Optimize my React app performance",

options=ClaudeAgentOptions(env={"CLAUDE_CODE_ENABLE_TASKS": "1"}),

if not isinstance(message, AssistantMessage):

continue

agent-sdk/typescript-v2-preview +7 -5

非推奨だったTypeScript SDKのV2セッションAPIが削除されたことを明記し、V1 APIへの移行ガイドと旧バージョンへの固定方法を案内しています。

@@ -3,11 +3,13 @@ title: typescript-v2-preview

source: https://code.claude.com/docs/en/agent-sdk/typescript-v2-preview.md

---

# TypeScript SDK V2 session API (deprecated)

# TypeScript SDK V2 session API (removed)

> Reference for the deprecated V2 TypeScript Agent SDK session API, with session-based send/stream patterns for multi-turn conversations.

> Reference for the removed V2 TypeScript Agent SDK session API, with session-based send/stream patterns for multi-turn conversations.

The V2 session API functions `unstable_v2_createSession`, `unstable_v2_resumeSession`, and `unstable_v2_prompt` are deprecated and will be removed in a future release. Use the [V1 `query()` API](/en/agent-sdk/typescript) instead.

The V2 session API is no longer supported. TypeScript Agent SDK 0.3.142 removes `unstable_v2_createSession`, `unstable_v2_resumeSession`, `unstable_v2_prompt`, and the `SDKSession` and `SDKSessionOptions` types.

To migrate, use the [`query()` API](/en/agent-sdk/typescript) and the [session options](/en/agent-sdk/sessions) it accepts. Pass an `AsyncIterable<SDKUserMessage>` for multi-turn conversations, or `options.resume` to continue a saved session. This page is kept for reference if you maintain code on Agent SDK 0.2.x or earlier.

V2 was an experimental session API that removed the need for async generators and yield coordination. Instead of managing generator state across turns, each turn was a separate `send()`/`stream()` cycle. The API surface reduced to three concepts:

@@ -17,10 +19,10 @@ V2 was an experimental session API that removed the need for async generators an

## Installation

The V2 interface is included in the existing SDK package:

Agent SDK 0.2.x is the last version that includes the V2 interface. The package version jumped from 0.2.x directly to 0.3.142, so the removal version above and the install pin below describe the same boundary. To install the last V2-compatible release, pin the major and minor version:

```bash

npm install @anthropic-ai/claude-agent-sdk

npm install @anthropic-ai/claude-agent-sdk@0.2

```

The SDK bundles a native Claude Code binary for your platform as an optional dependency, so you don't need to install Claude Code separately.

agent-sdk/typescript +10 -6

strictMcpConfigオプションの挙動説明が詳細化され、思考プロセスの表示制御オプションが定義されました。

@@ -409,7 +409,7 @@ Configuration object for the `query()` function.

| `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) |

| `spawnClaudeCodeProcess` | `(options: SpawnOptions) => SpawnedProcess` | `undefined` | Custom function to spawn the Claude Code process. Use to run Claude Code in VMs, containers, or remote environments |

| `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) |

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

@@ -1839,7 +1839,7 @@ type TodoWriteInput = {

Creates and manages a structured task list for tracking progress.

As of TypeScript Agent SDK 0.3.142, `TodoWrite` is disabled by default. Use `TaskCreate`, `TaskGet`, `TaskUpdate`, and `TaskList` instead. See [Migrate to Task tools](/en/agent-sdk/todo-tracking#migrate-to-task-tools) to update your monitoring code, or set `CLAUDE_CODE_ENABLE_TASKS=0` to revert to `TodoWrite`.

### TaskCreate

@@ -2334,7 +2334,7 @@ type TodoWriteOutput = {

Returns the previous and updated task lists.

### TaskCreate

@@ -2726,12 +2726,16 @@ type CallToolResult = {

Controls Claude's thinking/reasoning behavior. Takes precedence over the deprecated `maxThinkingTokens`.

```typescript

type ThinkingDisplay = "summarized" | "omitted";

type ThinkingConfig =

| { type: "adaptive" } // The model determines when and how much to reason (Opus 4.6+)

| { type: "enabled"; budgetTokens?: number } // Fixed thinking token budget

| { type: "adaptive"; display?: ThinkingDisplay } // The model determines when and how much to reason (Opus 4.6+)

| { type: "enabled"; budgetTokens?: number; display?: ThinkingDisplay } // Fixed thinking token budget

| { type: "disabled" }; // No extended thinking

```

### `SpawnedProcess`

Interface for custom process spawning (used with `spawnClaudeCodeProcess` option). `ChildProcess` already satisfies this interface.

@@ -3146,7 +3150,7 @@ type SandboxNetworkConfig = {

| :- | :- | :- | :- |

| `allowManagedDomainsOnly` | `boolean` | `false` | Managed-settings only. When set in [managed settings](/en/permissions#managed-settings), only `allowedDomains` entries from managed settings are honored and entries from user, project, or local settings are ignored. Has no effect when set via SDK options |

agent-view +70 -21

cwdフラグによる表示スコープ制限やGitワークツリーの自動作成を無効化する設定、スリープ時のセッション維持などの新機能と改善が大幅に加筆されています。

@@ -55,9 +55,15 @@ You can use `claude agents` as your primary entry point instead of `claude`: dis

Run `claude agents` to open agent view. It takes over the full terminal and lists every session grouped by state, with pinned sessions and the ones that need you at the top. Each row shows the session's name, current activity, and how long ago it last changed.

The list shows every background session you've started, across all your projects. A session working in one repository and another in a different worktree both appear here, regardless of which directory you opened agent view from. Interactive sessions you have open in other terminals don't appear until you [background them](#from-inside-a-session). [Subagents](/en/sub-agents) and [teammates](/en/agent-teams) a session spawns aren't listed as separate rows.

By default the list shows every background session you've started, across all your projects. A session working in one repository and another in a different worktree both appear here, regardless of which directory you opened agent view from. To narrow the list to one project, pass `--cwd` (requires Claude Code v2.1.141 or later):

To scope the view to one project, launch with `claude agents --cwd <path>`. Only sessions started under that directory appear, including any running in a [worktree](/en/worktrees) dispatched from it.

```bash

claude agents --cwd ~/projects/my-app

```

This shows only sessions started under that directory. A session that has [moved into a worktree](#how-file-edits-are-isolated) under `~/projects/my-app/.claude/worktrees/` still counts as belonging to `~/projects/my-app`.

Interactive sessions you have open in other terminals don't appear until you [background them](#from-inside-a-session). [Subagents](/en/sub-agents) and [teammates](/en/agent-teams) a session spawns aren't listed as separate rows.

```text

Pinned

@@ -100,9 +106,11 @@ Separately, the icon's shape shows whether the underlying process is running:

| `∙` | The process has exited. You can still peek, reply, or attach, and Claude restarts from where it left off |

| `✢` | A [`/loop`](/en/scheduled-tasks) session sleeping between iterations. The row shows its run count and a countdown |

The `●` that can appear at the right edge of a row is the [pull request status](#pull-request-status) indicator, not part of the state icon. A number before it is the count of pull requests the session has opened.

Background sessions don't need any terminal open to keep working. A separate [supervisor process](#the-supervisor-process) runs them, so you can close agent view, close your shell, or start a new interactive session and your dispatched work keeps going.

Session state persists on disk through auto-updates and supervisor restarts. If your machine sleeps or shuts down, running sessions stop; restart them with `claude respawn --all`.

Session state persists on disk through auto-updates and supervisor restarts. Sessions are also preserved when your machine sleeps. Their processes resume on wake and the supervisor reconnects to them instead of treating the time gap as idle. Shutting down still stops running sessions; see [Sessions show as failed after shutdown](#sessions-show-as-failed-after-shutdown) for how to recover them.

### Row summaries

@@ -141,7 +149,7 @@ Press `←` on an empty prompt to detach and return to agent view. If a dialog h

Detaching never stops a background session: `←`, `Ctrl+C`, `Ctrl+D`, `Ctrl+Z`, and `/exit` all leave it running. To end a session from inside it, run `/stop`.

After you've dispatched or backgrounded a session, pressing `←` on an empty prompt works from any Claude Code session, not only ones you attached to from agent view. It backgrounds the current session and opens agent view with that row selected, so you can switch sessions without leaving the terminal. The row is created even from a fresh session with no conversation history, so `→` returns to it. When that row is the only one, agent view shows an onboarding hint below it. You can turn this shortcut off in `/config` (the `leftArrowOpensAgents` setting).

### Organize the list

@@ -156,7 +164,7 @@ Within a group:

To remove a session from the list, press `Ctrl+X` to stop it and `Ctrl+X` again within two seconds to delete it. Pressing `Ctrl+X` on a group header deletes every session in that group after confirmation.

Deleting removes the session from agent view and cleans up its [worktree](#how-file-edits-are-isolated), including any uncommitted changes in it, so push or commit work you want to keep before deleting. The conversation transcript stays on disk and remains available through `claude --resume`.

Deleting removes the session from agent view and removes its conversation transcript. If Claude [created a worktree](#how-file-edits-are-isolated) for the session, deleting removes that worktree too, including any uncommitted changes in it, so push or commit work you want to keep first. A worktree you created yourself and started the session inside is left in place.

Older completed sessions fold into a `… N more` row to keep the list short. Failures and sessions with an open pull request always stay visible.

@@ -181,12 +189,12 @@ Press `?` in agent view to see every shortcut in context. The table below summar

| `Space` | Open or close the peek panel for the selected session |

| `Shift+Enter` | Dispatch and attach immediately |

| `→` | Attach to the selected session |

| `Alt+1`..`Alt+9` | Attach to session 1–9 in the current group |

| `Alt+1`..`Alt+9` | Attach to session 1–9 in the focused session's directory |

| `Tab` | On an empty input, browse all subagents. Otherwise apply the highlighted suggestion |

| `Ctrl+S` | Switch grouping between state and directory |

| `Ctrl+T` | Pin or unpin the selected session |

| `Ctrl+R` | Rename the selected session |

| `Ctrl+G` | Open the dispatch prompt in your `$EDITOR` |

| `Ctrl+G` | Open the dispatch prompt in your `$VISUAL` or `$EDITOR` |

| `Ctrl+X` | Stop the session; press again within two seconds to delete it |

| `Shift+↑` / `Shift+↓` | Reorder the selected session |

| `Esc` | Close the peek panel, clear the input, or exit |

@@ -234,6 +242,17 @@ Run `/background` or its alias `/bg` to move the current conversation into a bac

Backgrounding from an interactive session starts a fresh process that resumes from the saved conversation, so running subagents, [monitors](/en/tools-reference#monitor-tool), and background commands do not transfer to it. Claude asks you to confirm before backgrounding when any are running. Once in the background, the session can start new subagents, monitors, and background commands, and those keep running across later detach and reattach.

Configuration flags from the original launch carry through to the backgrounded session, so its MCP servers, settings, and fallback model remain in effect:

- `--mcp-config` and `--strict-mcp-config`

- `--settings`

- `--add-dir`

- `--plugin-dir`

- `--fallback-model`

- `--allow-dangerously-skip-permissions`

Carrying `--allow-dangerously-skip-permissions` through keeps `bypassPermissions` reachable in the backgrounded session, but it does not grant anything new. The mode still requires the same one-time interactive acceptance described in [Permission mode, model, and effort](#permission-mode-model-and-effort) before any session can use it.

### From your shell

Pass `--bg` to start a session that goes straight to the background:

@@ -266,11 +285,31 @@ backgrounded · 7c5dcf5d

### How file edits are isolated

Every background session, whether started from agent view, `/bg`, or `claude --bg`, starts in your working directory. Before editing files, Claude moves the session into an isolated [git worktree](/en/worktrees) under `.claude/worktrees/`, so parallel sessions can read the same checkout but each writes to its own. Claude skips this when the session is already under `.claude/worktrees/`, when the working directory isn't a git repository, or for writes outside the working directory.

Claude skips the worktree when:

- The session is already inside a linked git worktree, whether Claude created it under `.claude/worktrees/` or you created it with `git worktree add` somewhere else

- The working directory isn't a git repository

- The write is outside the working directory

To turn off worktree isolation for a repository where git worktrees are impractical, set [`worktree.bgIsolation`](/en/settings#worktree-settings) to `"none"`. Background sessions then edit your working copy directly without moving into a worktree first. Add the setting to the project's `.claude/settings.json`:

```json

{

"worktree": {

"bgIsolation": "none"

}

```

The `worktree.bgIsolation` setting requires Claude Code v2.1.143 or later.

Outside a git repository, sessions write to the working directory directly and aren't isolated from each other, so avoid dispatching parallel sessions that edit the same files.

The worktree is removed when you delete the session, so merge or push the changes you want to keep before you delete. To find a session's worktree path, peek the session or attach and check its working directory.

Deleting a session in agent view (`Ctrl+X` twice) removes a worktree Claude created for it, including any uncommitted changes, so merge or push the changes you want to keep first. Deleting from the shell with [`claude rm`](#manage-sessions-from-the-shell) keeps a worktree that has uncommitted changes and prints its path so you can clean it up yourself. A worktree you created yourself and started the session inside is left in place either way.

To find a session's worktree path, peek the session or attach and check its working directory.

To make a subagent always run in its own worktree regardless of how it was started, set [`isolation: worktree`](/en/sub-agents#supported-frontmatter-fields) in its frontmatter.

@@ -290,13 +329,17 @@ A background session reads its [settings](/en/settings) from the directory it ru

The [permission mode](/en/permissions) depends on how you started the session. Backgrounding an existing session with `/bg` or `←` keeps the current permission mode, so a session you switched to `acceptEdits` or `auto` stays in that mode after detaching. Dispatching from the agent view input or running `claude --bg` from your shell uses the `defaultMode` from that directory's settings, or the `permissionMode` from the dispatched [subagent's frontmatter](/en/sub-agents#supported-frontmatter-fields).

The permission mode you start a background session with persists when the supervisor later [stops and restarts](#the-supervisor-process) the session's process. A session you launched with `claude --bg --dangerously-skip-permissions` or `claude --bg --permission-mode bypassPermissions` stays in `bypassPermissions` after that restart instead of falling back to the directory's `defaultMode`.

To set defaults for every session you dispatch from agent view, pass any of `--permission-mode`, `--model`, or `--effort` when opening it:

```bash

claude agents --permission-mode plan --model opus --effort high

```

Passing `--permission-mode`, `--model`, or `--effort` to `claude agents` requires Claude Code v2.1.142 or later. Earlier versions reject these flags with an unknown-option error.

`claude agents` also accepts `--dangerously-skip-permissions` as shorthand for `--permission-mode bypassPermissions`, and `--allow-dangerously-skip-permissions` to make `bypassPermissions` available in each dispatched session's `Shift+Tab` cycle without starting in that mode. Both match the [top-level CLI flags](/en/cli-reference).

Passing `--permission-mode`, `--model`, `--effort`, or `--dangerously-skip-permissions` to `claude agents` requires Claude Code v2.1.142 or later. `--allow-dangerously-skip-permissions` on `claude agents` requires v2.1.143 or later. Earlier versions reject these flags with an unknown-option error.

The active defaults appear in the footer below the dispatch input.

@@ -306,7 +349,7 @@ Using `bypassPermissions` or `auto` is refused until you have accepted that mode

### Settings, plugins, and MCP servers

Agent view accepts the same configuration flags as `claude` for loading settings, plugins, MCP servers, and additional directories. Each flag applies to agent view itself and is passed through to every session you dispatch from it, so a plugin or MCP server you load this way is available in those sessions too.

Agent view accepts the same configuration flags as `claude` for loading settings, plugins, MCP servers, and additional directories. These flags require Claude Code v2.1.142 or later. Each flag applies to agent view itself and is passed through to every session you dispatch from it, so a plugin or MCP server you load this way is available in those sessions too.

| Flag | Effect |

| :- | :- |

@@ -330,13 +373,15 @@ Every background session has a short ID you can use from the shell. The ID is pr

| Command | Purpose |

| :- | :- |

| `claude agents` | Open agent view. Pass `--cwd <path>` to list only sessions started under that directory |

| `claude agents` | Open agent view |

| `claude agents --cwd <path>` | Open agent view scoped to sessions started under `<path>` |

| `claude attach <id>` | Attach to a session in this terminal |

| `claude logs <id>` | Print the session's recent output |

| `claude stop <id>` | Stop a session. Also accepts `claude kill` |

| `claude respawn <id>` | Restart a stopped session with its conversation intact |

| `claude respawn --all` | Restart every stopped session |

| `claude rm <id>` | Remove a session from the list. Cleans up its worktree if there are no uncommitted changes |

| `claude respawn <id>` | Restart a session, running or stopped, with its conversation intact, e.g. to pick up an updated Claude Code binary |

| `claude respawn --all` | Restart every running session, e.g. to move all sessions onto an updated Claude Code binary at once |

| `claude rm <id>` | Remove a session and its transcript. Removes a worktree Claude created for the session if it has no uncommitted changes; otherwise prints the worktree path so you can clean it up. Leaves a worktree you created yourself in place |

| `claude daemon status` | Print the [supervisor's](#the-supervisor-process) state, version, socket directory, and worker count |

## How background sessions are hosted

@@ -364,6 +409,8 @@ Session state is stored under your Claude Code config directory. If you set [`CL

| `~/.claude/daemon/roster.json` | List of running background sessions, used to reconnect after a restart |

| `~/.claude/jobs/<id>/state.json` | Per-session state shown in agent view |

To inspect this state without reading the files directly, run `claude daemon status`. It reports whether the supervisor is reachable, its process ID and version, the socket directory, and how many background sessions are live. `/doctor` includes a summary of the same check. On Windows, `claude daemon status` surfaces the underlying file error when the daemon's pipe-key file is locked or unreadable instead of reporting a generic connection failure.

### Turn off agent view

To turn off background agents and agent view entirely, set the `disableAgentView` [setting](/en/settings) to `true` or set the `CLAUDE_CODE_DISABLE_AGENT_VIEW` environment variable. Administrators can enforce this through [managed settings](/en/permissions#managed-settings).

@@ -378,7 +425,7 @@ If agent view still does not open after updating, check whether it has been [tur

### Agent view opens with no sessions

Agent view is empty until you dispatch your first session. Type a prompt in the input at the bottom and press `Enter`.

Before you dispatch your first session, agent view shows a short onboarding hint with example prompts in place of the session list. Type a prompt in the input at the bottom and press `Enter` to dispatch your first session.

### Cannot open agents because background tasks are running

@@ -388,9 +435,11 @@ If pressing `←` to background the current session shows `Cannot open agents

The dispatch input expects a task description, not a conversational opener. A prompt shorter than four characters is rejected with a `Too short` hint so a stray keystroke doesn't start a session. Describe what you want the session to do, such as `investigate the flaky checkout test`.

### Sessions show as failed after waking your machine

### Sessions show as failed after shutdown

Shutting down or restarting your machine stops running background sessions, so they show as failed when you next open agent view. Attach, peek, or reply to any of them and the session restarts from where it left off.

Background sessions don't survive sleep or shutdown, so sessions that were running show as failed after you wake. Attach, peek, or reply to any of them and the session restarts from where it left off. To restart all of them at once, run `claude respawn --all`.

Sleep alone does not cause this. Sessions are preserved across sleep and the supervisor reconnects to them on wake.

### A session is slow to respond after attaching

@@ -398,15 +447,15 @@ Once a session has finished and sat unattached for about an hour, the supervisor

### `.claude/worktrees/` is filling up

Worktrees are removed when you delete the session that created them. If a session ended without cleaning up, list leftover entries with `git worktree list` in the project directory and remove each with `git worktree remove <path>`. See [Clean up worktrees](/en/worktrees#clean-up-worktrees).

Deleting a session in agent view removes the worktree Claude created for it. `claude rm` keeps a worktree that has uncommitted changes and prints its path. List leftover entries with `git worktree list` in the project directory and remove each with `git worktree remove <path>`. See [Clean up worktrees](/en/worktrees#clean-up-worktrees).

## Limitations

Agent view is in research preview with the following limitations:

- **Rate limits apply**: background sessions consume your subscription usage the same as interactive sessions, so running ten agents in parallel uses quota roughly ten times as fast as running one.

- **Sessions are local**: background sessions run on your machine and stop if it sleeps or shuts down.

- **Worktrees are deleted with the session**: merge or push changes before deleting a session that edited files in its own worktree.

- **Sessions are local**: background sessions run on your machine. They are preserved across sleep but stop if the machine shuts down.

- **Claude-created worktrees are deleted with the session in agent view**: merge or push changes before deleting a session that edited files in its own worktree. `claude rm` keeps a worktree that has uncommitted changes; a worktree you created yourself is left in place.

## Related resources

cli-reference +4 -3

claude agentsコマンドでの詳細設定オプションのサポートや、デーモンの稼働状況を確認するclaude daemon statusコマンドの説明が追加されました。

@@ -25,15 +25,16 @@ You can start sessions, pipe content, resume conversations, and manage updates w

| `claude auth login` | Sign in to your Anthropic account. Use `--email` to pre-fill your email address, `--sso` to force SSO authentication, and `--console` to sign in with Anthropic Console for API usage billing instead of a Claude subscription | `claude auth login --console` |

| `claude auth logout` | Log out from your Anthropic account | `claude auth logout` |

| `claude auth status` | Show authentication status as JSON. Use `--text` for human-readable output. Exits with code 0 if logged in, 1 if not | `claude auth status` |

| `claude agents` | Open [agent view](/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory | `claude agents` |

| `claude agents` | Open [agent view](/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory. Pass `--permission-mode`, `--model`, or `--effort` to set [defaults for dispatched sessions](/en/agent-view#permission-mode-model-and-effort). Accepts `--settings`, `--add-dir`, `--plugin-dir`, and `--mcp-config` like the top-level `claude` command. Requires an interactive terminal | `claude agents --cwd ~/projects/my-app` |

| `claude attach <id>` | Attach to a [background session](/en/agent-view#manage-sessions-from-the-shell) in this terminal | `claude attach 7c5dcf5d` |

| `claude auto-mode defaults` | Print the built-in [auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode) classifier rules as JSON. Use `claude auto-mode config` to see your effective config with settings applied | `claude auto-mode defaults > rules.json` |

| `claude daemon status` | Print the background-session [supervisor's](/en/agent-view#the-supervisor-process) state, version, socket directory, and worker count for diagnostics. Exits 1 if the supervisor isn't running | `claude daemon status` |

| `claude logs <id>` | Print recent output from a [background session](/en/agent-view#manage-sessions-from-the-shell) | `claude logs 7c5dcf5d` |

| `claude mcp` | Configure Model Context Protocol (MCP) servers | See the [Claude Code MCP documentation](/en/mcp). |

| `claude plugin` | Manage Claude Code [plugins](/en/plugins). Alias: `claude plugins`. See [plugin reference](/en/plugins-reference#cli-commands-reference) for subcommands | `claude plugin install code-review@claude-plugins-official` |

| `claude project purge [path]` | Delete all local Claude Code state for a project: transcripts, task lists, debug logs, file-edit history, prompt history lines, and the project's entry in `~/.claude.json`. Omit `[path]` to pick from an interactive list. Flags: `--dry-run` to preview, `-y`/`--yes` to skip confirmation, `-i`/`--interactive` to confirm each item, `--all` for every project. See [Clear local data](/en/claude-directory#clear-local-data) | `claude project purge ~/work/repo --dry-run` |

| `claude remote-control` | Start a [Remote Control](/en/remote-control) server to control Claude Code from Claude.ai or the Claude app. Runs in server mode (no local interactive session). See [Server mode flags](/en/remote-control#start-a-remote-control-session) | `claude remote-control --name "My Project"` |

| `claude respawn <id>` | Restart a stopped [background session](/en/agent-view#manage-sessions-from-the-shell) with its conversation intact. Use `--all` to restart every stopped session | `claude respawn 7c5dcf5d` |

| `claude respawn <id>` | Restart a [background session](/en/agent-view#manage-sessions-from-the-shell), running or stopped, with its conversation intact. Use `--all` to restart every running session, e.g. to pick up an updated Claude Code binary | `claude respawn 7c5dcf5d` |

| `claude rm <id>` | Remove a [background session](/en/agent-view#manage-sessions-from-the-shell) from the list | `claude rm 7c5dcf5d` |

| `claude setup-token` | Generate a long-lived OAuth token for CI and scripts. Prints the token to the terminal without saving it. Requires a Claude subscription. See [Generate a long-lived token](/en/authentication#generate-a-long-lived-token) | `claude setup-token` |

| `claude stop <id>` | Stop a [background session](/en/agent-view#manage-sessions-from-the-shell). Also accepts `claude kill` | `claude stop 7c5dcf5d` |

@@ -69,7 +70,7 @@ Customize Claude Code's behavior with these command-line flags. `claude --help`

| `--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"` |

| `--fallback-model` | Enable automatic fallback to specified model when default model is overloaded (print mode only) | `claude -p --fallback-model sonnet "query"` |

| `--fallback-model` | Enable automatic fallback to a specified model when the default model is overloaded. Takes effect in print mode (`-p`) and in [background sessions](/en/agent-view), which run non-interactively; ignored in an interactive session | `claude -p --fallback-model sonnet "query"` |

| `--fork-session` | When resuming, create a new session ID instead of reusing the original (use with `--resume` or `--continue`) | `claude --resume abc123 --fork-session` |

| `--from-pr` | Resume sessions linked to a specific pull request. Accepts a PR number, a GitHub or GitHub Enterprise PR URL, a GitLab merge request URL, or a Bitbucket pull request URL. Sessions are linked automatically when Claude creates the pull request | `claude --from-pr 123` |

| `--ide` | Automatically connect to IDE on startup if exactly one valid IDE is available | `claude --ide` |

code-review +2 -2

コードレビューで問題が見つからなかった場合のGitHub上での表示仕様の変更や、請求に関する用語の微調整が行われています。

@@ -28,7 +28,7 @@ This page covers:

Once an admin [enables Code Review](#set-up-code-review) for your organization, reviews trigger when a PR opens, on every push, or when manually requested, depending on the repository's configured behavior. Commenting `@claude review` [starts reviews on a PR](#manually-trigger-reviews) in any mode.

When a review runs, multiple agents analyze the diff and surrounding code in parallel on Anthropic infrastructure. Each agent looks for a different class of issue, then a verification step checks candidates against actual code behavior to filter out false positives. The results are deduplicated, ranked by severity, and posted as inline comments on the specific lines where issues were found, with a summary in the review body. If no issues are found, Claude posts a short confirmation comment on the PR.

When a review runs, multiple agents analyze the diff and surrounding code in parallel on Anthropic infrastructure. Each agent looks for a different class of issue, then a verification step checks candidates against actual code behavior to filter out false positives. The results are deduplicated, ranked by severity, and posted as inline comments on the specific lines where issues were found, with a summary in the review body. If no issues are found, Code Review updates the GitHub check run to show that no issues were detected. Claude may also post a short confirmation comment on the PR.

Reviews scale in cost with PR size and complexity, completing in 20 minutes on average. Admins can monitor review activity and spend via the [analytics dashboard](#view-usage).

@@ -219,7 +219,7 @@ The repositories table in admin settings also shows average cost per review for

## Pricing

Code Review is billed based on token usage. Each review averages $15-25 in cost, scaling with PR size, codebase complexity, and how many issues require verification. Code Review usage is billed separately through [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) and does not count against your plan's included usage.

Code Review is billed based on token usage. Each review averages $15-25 in cost, scaling with PR size, codebase complexity, and how many issues require verification. Code Review usage is billed separately through [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) and does not count against your plan's included usage.

The review trigger you choose affects total cost:

commands +2 -2

@@ -62,7 +62,6 @@ Not every command appears for every user. Availability depends on your platform,

| `/effort [level\|auto]` | Set the model [effort level](/en/model-config#adjust-effort-level). Accepts `low`, `medium`, `high`, `xhigh`, or `max`; available levels depend on the model and `max` is session-only. `auto` resets to the model default. Without an argument, opens an interactive slider; use left and right arrows to pick a level and `Enter` to apply. Takes effect immediately without waiting for the current response to finish |

| `/exit` | Exit the CLI. In an attached [background session](/en/agent-view#attach-to-a-session), this detaches and the session keeps running. Alias: `/quit` |

| `/export [filename]` | Export the current conversation as plain text. With a filename, writes directly to that file. Without, opens a dialog to copy to clipboard or save to a file |

| `/extra-usage` | Configure extra usage to keep working when rate limits are hit |

| `/fast [on\|off]` | Toggle [fast mode](/en/fast-mode) on or off |

| `/feedback [report]` | Submit feedback about Claude Code. Alias: `/bug` |

| `/fewer-permission-prompts` | **[Skill](/en/skills#bundled-skills).** Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project `.claude/settings.json` to reduce permission prompts |

@@ -121,9 +120,10 @@ Not every command appears for every user. Availability depends on your platform,

| `/theme` | Change the color theme. Includes an `auto` option that matches your terminal's light or dark background, light and dark variants, colorblind-accessible (daltonized) themes, ANSI themes that use your terminal's color palette, and any [custom themes](/en/terminal-config#create-a-custom-theme) from `~/.claude/themes/` or plugins. Select **New custom theme…** to create one |

| `/tui [default\|fullscreen]` | Set the terminal UI renderer and relaunch into it with your conversation intact. `fullscreen` enables the [flicker-free alt-screen renderer](/en/fullscreen). With no argument, prints the active renderer |

| `/ultraplan <prompt>` | Draft a plan in an [ultraplan](/en/ultraplan) session, review it in your browser, then execute remotely or send it back to your terminal |

| `/ultrareview [PR]` | Run a deep, multi-agent code review in a cloud sandbox with [ultrareview](/en/ultrareview). Includes 3 free runs on Pro and Max, then requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| `/ultrareview [PR]` | Run a deep, multi-agent code review in a cloud sandbox with [ultrareview](/en/ultrareview). Includes 3 free runs on Pro and Max, then requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| `/upgrade` | Open the upgrade page to switch to a higher plan tier |

| `/usage` | Show session cost, plan usage limits, and activity stats. See the [cost tracking guide](/en/costs#using-the-%2Fusage-command) for subscription-specific details. `/cost` and `/stats` are aliases |

| `/usage-credits` | Configure usage credits to keep working when you hit a limit. Previously `/extra-usage` |

| `/vim` | Removed in v2.1.92. To toggle between Vim and Normal editing modes, use `/config` → Editor mode |

| `/voice [hold\|tap\|off]` | Toggle [voice dictation](/en/voice-dictation), or enable it in a specific mode. Requires a Claude.ai account |

| `/web-setup` | Connect your GitHub account to [Claude Code on the web](/en/web-quickstart#connect-from-your-terminal) using your local `gh` CLI credentials. `/schedule` prompts for this automatically if GitHub isn't connected |

debug-your-config +1 -1

@@ -95,7 +95,7 @@ Most configuration surprises trace back to a small set of location and syntax ru

| Skill doesn't appear in `/skills` | Skill file is at `.claude/skills/name.md` instead of in a folder | Use a folder with `SKILL.md` inside: `.claude/skills/name/SKILL.md`. |

| Skill appears in `/skills` but Claude never invokes it | Skill has `disable-model-invocation: true` in its frontmatter, or its description doesn't match how you phrase the request | Check the badge in `/skills`: a "user-only" label means Claude won't trigger it on its own. See [skill invocation](/en/skills). |

| Subdirectory `CLAUDE.md` instructions seem ignored | Subdirectory files load on demand, not at session start | They load when Claude reads a file in that directory with the Read tool, not at launch and not when writing or creating files there. See [how CLAUDE.md files load](/en/memory#how-claude-md-files-load). |

| Subagent ignores `CLAUDE.md` instructions | Subagents don't always inherit project memory | Put critical rules in the agent file body, which becomes the subagent's system prompt. See [subagent configuration](/en/sub-agents). |

| Subagent ignores `CLAUDE.md` instructions | The built-in Explore and Plan agents skip `CLAUDE.md`. Custom subagents load it the same way the main conversation does | For Explore or Plan, restate the instruction in your delegating prompt. For a custom subagent, put critical instructions in the agent file body, which becomes the agent's system prompt. See [what loads at startup](/en/sub-agents#what-loads-at-startup). |

| Cleanup logic never runs at session end | No `SessionEnd` hook configured | Add a `SessionEnd` hook in `settings.json`. See the [hook events list](/en/hooks#hook-events). |

| MCP servers in `.mcp.json` never load | File is under `.claude/` or uses Claude Desktop's config format | Project MCP config goes at the repository root as `.mcp.json`, not inside `.claude/`. See [MCP configuration](/en/mcp). |

| MCP servers added under `mcpServers` in `settings.json` never appear | `settings.json` does not read an `mcpServers` key | Define project servers in `.mcp.json` at the repository root, or run `claude mcp add --scope user` for user-scoped servers. See [MCP configuration](/en/mcp). |

desktop +1 -1

@@ -3,7 +3,7 @@ title: desktop

source: https://code.claude.com/docs/en/desktop.md

---

# Use Claude Code Desktop

# Desktop application

> Get more out of Claude Code Desktop: parallel sessions with Git isolation, drag-and-drop pane layout, integrated terminal and file editor, side chats, computer use, Dispatch sessions from your phone, visual diff review, app previews, PR monitoring, connectors, and enterprise configuration.

discover-plugins +3 -1

@@ -123,7 +123,9 @@ Run `/plugin` to open the plugin manager. This opens a tabbed interface with fou

Go to the **Discover** tab to see plugins from the marketplace you just added.

Select a plugin to view its details, then choose an installation scope:

Select a plugin to view its details. On Claude Code v2.1.143 and later, the details pane includes a **Context cost** estimate so you can see how many tokens the plugin will add to your [context window](/en/features-overview#understand-context-costs) every turn before you install it.

Choose an installation scope:

- **User scope**: install for yourself across all projects

- **Project scope**: install for all collaborators on this repository

env-vars +13 -10

タスク管理ツールの切り替えや思考プロセスの表示制御に関連する新しい環境変数の説明が追加されました。

@@ -101,9 +101,9 @@ Claude Code supports the following environment variables to control its behavior

| `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 |

| `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE` | Set to `1` to run [fast mode](/en/fast-mode) on Claude Opus 4.7 instead of Opus 4.6. With the variable set, `/fast` switches to Opus 4.7; without it, `/fast` continues to use Opus 4.6 |

| `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE` | Removed in v2.1.142. [Fast mode](/en/fast-mode) defaults to Opus 4.7. Set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1` to keep Opus 4.6 instead |

| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Set to `false` to disable prompt suggestions (the "Prompt suggestions" toggle in `/config`). These are the grayed-out predictions that appear in your prompt input after Claude responds. See [Prompt suggestions](/en/interactive-mode#prompt-suggestions) |

| `CLAUDE_CODE_ENABLE_TASKS` | Set to `1` to enable the task tracking system in non-interactive mode (the `-p` flag). Tasks are on by default in interactive mode. See [Task list](/en/interactive-mode#task-list) |

| `CLAUDE_CODE_ENABLE_TASKS` | Controls whether sessions use the structured Task tools (`TaskCreate`, `TaskUpdate`, `TaskGet`, `TaskList`) or the legacy `TodoWrite` tool. As of Claude Code v2.1.142, Task tools are the default in all modes. Set to `0` to revert to `TodoWrite`. See [Task list](/en/interactive-mode#task-list) and [Migrate to Task tools](/en/agent-sdk/todo-tracking#migrate-to-task-tools) |

| `CLAUDE_CODE_ENABLE_TELEMETRY` | Set to `1` to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters. See [Monitoring](/en/monitoring-usage) |

| `CLAUDE_CODE_EXIT_AFTER_STOP_DELAY` | Time in milliseconds to wait after the query loop becomes idle before automatically exiting. Useful for automated workflows and scripts using SDK mode |

| `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` | Set to `1` to enable [agent teams](/en/agent-teams). Agent teams are experimental and disabled by default |

@@ -131,7 +131,7 @@ Claude Code supports the following environment variables to control its behavior

| `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` | OAuth refresh token for Claude.ai authentication. When set, `claude auth login` exchanges this token directly instead of opening a browser. Requires `CLAUDE_CODE_OAUTH_SCOPES`. Useful for provisioning authentication in automated environments |

| `CLAUDE_CODE_OAUTH_SCOPES` | Space-separated OAuth scopes the refresh token was issued with, such as `"user:profile user:inference user:sessions:claude_code"`. Required when `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` is set |

| `CLAUDE_CODE_OAUTH_TOKEN` | OAuth access token for Claude.ai authentication. Alternative to `/login` for SDK and automated environments. Takes precedence over keychain-stored credentials. Generate one with [`claude setup-token`](/en/authentication#generate-a-long-lived-token) |

| `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` | Set to `1` to keep [fast mode](/en/fast-mode) on Claude Opus 4.6. Takes precedence over `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE`, so set this if you need to pin Opus 4.6 regardless of how the default changes |

| `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` | Set to `1` to pin [fast mode](/en/fast-mode) to Claude Opus 4.6 instead of the default Opus 4.7. With the variable set, `/fast` runs on Opus 4.6. Without it, `/fast` runs on Opus 4.7 |

| `CLAUDE_CODE_OTEL_FLUSH_TIMEOUT_MS` | Timeout in milliseconds for flushing pending OpenTelemetry spans (default: 5000). See [Monitoring](/en/monitoring-usage) |

| `CLAUDE_CODE_OTEL_HEADERS_HELPER_DEBOUNCE_MS` | Interval for refreshing dynamic OpenTelemetry headers in milliseconds (default: 1740000 / 29 minutes). See [Dynamic headers](/en/monitoring-usage#dynamic-headers) |

| `CLAUDE_CODE_OTEL_SHUTDOWN_TIMEOUT_MS` | Timeout in milliseconds for the OpenTelemetry exporter to finish on shutdown (default: 2000). Increase if metrics are dropped at exit. See [Monitoring](/en/monitoring-usage) |

@@ -142,6 +142,7 @@ Claude Code supports the following environment variables to control its behavior

| `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` | Set to `1` to keep the existing marketplace cache when a `git pull` fails instead of wiping and re-cloning. Useful in offline or airgapped environments where re-cloning would fail the same way. See [Marketplace updates fail in offline environments](/en/plugin-marketplaces#marketplace-updates-fail-in-offline-environments) |

| `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` | Set to `1` to clone GitHub `owner/repo` plugin sources over HTTPS instead of SSH. Useful in CI runners, containers, or any environment without a configured SSH key for `github.com` |

| `CLAUDE_CODE_PLUGIN_SEED_DIR` | Path to one or more read-only plugin seed directories, separated by `:` on Unix or `;` on Windows. Use this to bundle a pre-populated plugins directory into a container image. Claude Code registers marketplaces from these directories at startup and uses pre-cached plugins without re-cloning. See [Pre-populate plugins for containers](/en/plugin-marketplaces#pre-populate-plugins-for-containers) |

| `CLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY` | Set to `1` to stop Claude Code from passing `-ExecutionPolicy Bypass` when spawning PowerShell for tool calls, hooks, and status line commands, and respect the machine's effective execution policy instead. By default Claude Code bypasses execution policy at process scope so `.ps1` scripts and module imports work on default-Restricted Windows installs. Process-scope bypass never overrides Group Policy `MachinePolicy` or `UserPolicy` regardless of this setting |

| `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` | Set by host platforms that embed Claude Code and manage model provider routing on its behalf. When set, provider-selection, endpoint, and authentication variables such as `CLAUDE_CODE_USE_BEDROCK`, `ANTHROPIC_BASE_URL`, and `ANTHROPIC_API_KEY` in settings files are ignored so user settings cannot override the host's routing. The automatic telemetry opt-out for Bedrock, Vertex, and Foundry is also skipped, so telemetry follows the standard `DISABLE_TELEMETRY` opt-out. See [Default behaviors by API provider](/en/data-usage#default-behaviors-by-api-provider) |

| `CLAUDE_CODE_PROXY_RESOLVES_HOSTS` | Set to `1` to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolution |

| `CLAUDE_CODE_REMOTE` | Set automatically to `true` when Claude Code is running as a [cloud session](/en/claude-code-on-the-web). Read this from a hook or setup script to detect whether you are in a cloud environment |

@@ -154,7 +155,7 @@ Claude Code supports the following environment variables to control its behavior

| `CLAUDE_CODE_SESSION_ID` | Set automatically in Bash and PowerShell tool subprocesses to the current session ID. Matches the `session_id` field passed to [hooks](/en/hooks). Updated on `/clear`. Use to correlate scripts and external tools with the Claude Code session that launched them |

| `CLAUDE_CODE_SHELL` | Override automatic shell detection. Useful when your login shell differs from your preferred working shell (for example, `bash` vs `zsh`) |

| `CLAUDE_CODE_SHELL_PREFIX` | Command prefix that wraps shell commands Claude Code spawns: Bash tool calls, [hook](/en/hooks) commands, and stdio [MCP server](/en/mcp) startup commands. Useful for logging or auditing. Example: setting `/path/to/logger.sh` runs each command as `/path/to/logger.sh <command>` |

| `CLAUDE_CODE_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools. MCP tools from `--mcp-config` are still available. Disables auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md. OAuth tokens and keychain credentials are not read, so Anthropic authentication must come from `ANTHROPIC_API_KEY` or an `apiKeyHelper` in `--settings`. Equivalent to passing [`--bare`](/en/headless#start-faster-with-bare-mode) |

| `CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT` | Set to `1` to use a shorter system prompt and abbreviated tool descriptions on any model. Set to `0`, `false`, `no`, or `off` to opt out even on models where the experiment or server configuration would otherwise enable it. The full tool set, hooks, MCP servers, and CLAUDE.md discovery remain enabled |

| `CLAUDE_CODE_SKIP_ANTHROPIC_AWS_AUTH` | Skip client-side authentication for [Claude Platform on AWS](/en/claude-platform-on-aws), for gateways that sign requests themselves |

| `CLAUDE_CODE_SKIP_BEDROCK_AUTH` | Skip AWS authentication for Bedrock (for example, when using an LLM gateway) |

@@ -162,6 +163,7 @@ Claude Code supports the following environment variables to control its behavior

| `CLAUDE_CODE_SKIP_MANTLE_AUTH` | Skip AWS authentication for Bedrock Mantle (for example, when using an LLM gateway) |

| `CLAUDE_CODE_SKIP_PROMPT_HISTORY` | Set to `1` to skip writing prompt history and session transcripts to disk. Sessions started with this variable set do not appear in `--resume`, `--continue`, or up-arrow history. Useful for ephemeral scripted sessions |

| `CLAUDE_CODE_SKIP_VERTEX_AUTH` | Skip Google authentication for Vertex (for example, when using an LLM gateway) |

| `CLAUDE_CODE_STOP_HOOK_BLOCK_CAP` | Maximum number of consecutive times a [Stop](/en/hooks#stop) or [SubagentStop](/en/hooks#subagentstop) hook may block the turn from ending before Claude Code overrides it and ends the turn anyway (default: 8). Set to `0` to disable the cap. Raise this if your hook legitimately needs more iterations to resolve |

| `CLAUDE_CODE_SUBAGENT_MODEL` | See [Model configuration](/en/model-config) |

| `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` | Set to `1` to strip Anthropic and cloud provider credentials from subprocess environments (Bash tool, hooks, MCP stdio servers). The parent Claude process keeps these credentials for API calls, but child processes cannot read them, reducing exposure to prompt injection attacks that attempt to exfiltrate secrets via shell expansion. On Linux, this also runs Bash subprocesses in an isolated PID namespace so they cannot read host process environments via `/proc`; as a side effect, `ps`, `pgrep`, and `kill` cannot see or signal host processes. `claude-code-action` sets this automatically when `allowed_non_write_users` is configured |

| `CLAUDE_CODE_SYNC_PLUGIN_INSTALL` | Set to `1` in non-interactive mode (the `-p` flag) to wait for plugin installation to complete before the first query. Without this, plugins install in the background and may not be available on the first turn. Combine with `CLAUDE_CODE_SYNC_PLUGIN_INSTALL_TIMEOUT_MS` to bound the wait |

@@ -181,10 +183,11 @@ Claude Code supports the following environment variables to control its behavior

| `CLAUDE_CONFIG_DIR` | Override the configuration directory (default: `~/.claude`). All settings, credentials, session history, and plugins are stored under this path. Useful for running multiple accounts side by side: for example, `alias claude-work='CLAUDE_CONFIG_DIR=~/.claude-work claude'` |

| `CLAUDE_EFFORT` | Set automatically in Bash tool subprocesses and hook commands to the active [effort level](/en/model-config#adjust-effort-level) for the turn: `low`, `medium`, `high`, `xhigh`, or `max`. Matches the `effort.level` field passed to [hooks](/en/hooks). Only set when the current model supports the effort parameter |

| `CLAUDE_ENABLE_BYTE_WATCHDOG` | Set to `1` to force-enable the byte-level streaming idle watchdog, or set to `0` to force-disable it. When unset, the watchdog is enabled by default for Anthropic API connections. The byte watchdog aborts a connection when no bytes arrive on the wire for the duration set by `CLAUDE_STREAM_IDLE_TIMEOUT_MS`, with a minimum of 5 minutes, independent of the event-level watchdog |

| `CLAUDE_ENABLE_STREAM_WATCHDOG` | Set to `1` to enable the event-level streaming idle watchdog. Off by default. For Bedrock, Vertex, and Foundry, this is the only idle watchdog available. Configure the timeout with `CLAUDE_STREAM_IDLE_TIMEOUT_MS` |

| `CLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK` | Set to `1` to enable the byte-level streaming idle watchdog on Amazon Bedrock `vnd.amazon.eventstream` responses. Off by default. Configure the timeout with `CLAUDE_STREAM_IDLE_TIMEOUT_MS` |

| `CLAUDE_ENABLE_STREAM_WATCHDOG` | Set to `1` to enable the event-level streaming idle watchdog. Off by default. Applies to all providers, including Bedrock. For Vertex and Foundry, this is the only idle watchdog available. On Bedrock, you can also enable the independent byte-level watchdog with `CLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK`; the two run together when both are set. Configure the timeout with `CLAUDE_STREAM_IDLE_TIMEOUT_MS` |

| `CLAUDE_ENV_FILE` | Path to a shell script whose contents Claude Code runs before each Bash command in the same shell process, so exports in the file are visible to the command. Use to persist virtualenv or conda activation across commands. Also populated dynamically by [SessionStart](/en/hooks#persist-environment-variables), [Setup](/en/hooks#setup), [CwdChanged](/en/hooks#cwdchanged), and [FileChanged](/en/hooks#filechanged) hooks |

| `CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX` | Prefix for auto-generated [Remote Control](/en/remote-control) session names when no explicit name is provided. Defaults to your machine's hostname, producing names like `myhost-graceful-unicorn`. The `--remote-control-session-name-prefix` CLI flag sets the same value for a single invocation |

| `CLAUDE_STREAM_IDLE_TIMEOUT_MS` | Timeout in milliseconds before the streaming idle watchdog closes a stalled connection. Default and minimum `300000` (5 minutes) for both the byte-level and event-level watchdogs; lower values are silently clamped to absorb extended thinking pauses and proxy buffering. For third-party providers, requires `CLAUDE_ENABLE_STREAM_WATCHDOG=1` |

| `DEBUG` | Set to `1` to enable debug mode, equivalent to launching with [`--debug`](/en/cli-reference#cli-flags). Debug logs are written to `~/.claude/debug/<session-id>.txt`, or to the path set by `CLAUDE_CODE_DEBUG_LOGS_DIR`. Only the truthy values `1`, `true`, `yes`, and `on` enable debug mode, so namespace patterns like `DEBUG=express:*` set for other tools do not trigger it |

| `DISABLE_AUTOUPDATER` | Set to `1` to disable automatic background updates. Manual `claude update` still works. Use `DISABLE_UPDATES` to block both |

| `DISABLE_AUTO_COMPACT` | Set to `1` to disable automatic compaction when approaching the context limit. The manual `/compact` command remains available. Use when you want explicit control over when compaction occurs |

@@ -192,7 +195,7 @@ Claude Code supports the following environment variables to control its behavior

| `DISABLE_COST_WARNINGS` | Set to `1` to disable cost warning messages |

| `DISABLE_DOCTOR_COMMAND` | Set to `1` to hide the `/doctor` command. Useful for managed deployments where users should not run installation diagnostics |

| `DISABLE_ERROR_REPORTING` | Set to `1` to opt out of Sentry error reporting |

| `DISABLE_EXTRA_USAGE_COMMAND` | Set to `1` to hide the `/extra-usage` command that lets users purchase additional usage beyond rate limits |

| `DISABLE_EXTRA_USAGE_COMMAND` | Set to `1` to hide the `/usage-credits` command that lets users purchase additional usage beyond rate limits |

| `DISABLE_FEEDBACK_COMMAND` | Set to `1` to disable the `/feedback` command. The older name `DISABLE_BUG_COMMAND` is also accepted |

| `DISABLE_GROWTHBOOK` | Set to `1` to disable GrowthBook feature-flag fetching and use code defaults for every flag. Telemetry event logging stays on unless `DISABLE_TELEMETRY` is also set |

| `DISABLE_INSTALLATION_CHECKS` | Set to `1` to disable installation warnings. Use only when manually managing the installation location, as this can mask issues with standard installations |

@@ -211,7 +214,7 @@ Claude Code supports the following environment variables to control its behavior

| `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_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; supported on Vertex AI with Sonnet 4.5 and later or Opus 4.5 and later; requests fail on earlier Vertex AI models 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) |

| `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 |

| `FORCE_AUTOUPDATE_PLUGINS` | Set to `1` to force plugin auto-updates even when the main auto-updater is disabled via `DISABLE_AUTOUPDATER` |

| `FORCE_PROMPT_CACHING_5M` | Set to `1` to force the 5-minute prompt cache TTL even when 1-hour TTL would otherwise apply. Overrides `ENABLE_PROMPT_CACHING_1H` |

@@ -222,8 +225,8 @@ Claude Code supports the following environment variables to control its behavior

| `MAX_STRUCTURED_OUTPUT_RETRIES` | Number of times to retry when the model's response fails validation against the [`--json-schema`](/en/cli-reference#cli-flags) in non-interactive mode (the `-p` flag). Defaults to 5 |

| `MAX_THINKING_TOKENS` | Override the [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) token budget. The ceiling is the model's [max output tokens](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison) minus one. Set to `0` to disable thinking entirely. On models with [adaptive reasoning](/en/model-config#adjust-effort-level), the budget is ignored unless adaptive reasoning is disabled via `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` |

| `MCP_CLIENT_SECRET` | OAuth client secret for MCP servers that require [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials). Avoids the interactive prompt when adding a server with `--client-secret` |

| `MCP_CONNECTION_NONBLOCKING` | Set to `true` in non-interactive mode (`-p`) to skip the MCP connection wait entirely. Useful for scripted pipelines where MCP tools are not needed. Without this variable, the first query waits up to 5 seconds for `--mcp-config` server connections. Servers configured with [`alwaysLoad: true`](/en/mcp#exempt-a-server-from-deferral) always block startup regardless of this variable, since their tools must be present when the first prompt is built |

| `MCP_CONNECT_TIMEOUT_MS` | How long the first query waits, in milliseconds, for the MCP connection batch before snapshotting the tool list (default: 5000). Servers still pending at the deadline keep connecting in the background but won't appear until the next query. Distinct from `MCP_TIMEOUT`, which bounds an individual server's connect attempt. Most relevant to non-interactive sessions that issue a single query and need slow-connecting servers to be visible |

| `MCP_CONNECTION_NONBLOCKING` | Controls whether startup waits for MCP servers to connect before the first query. As of Claude Code v2.1.142, MCP startup is non-blocking by default: servers connect in the background and their tools become available as they finish. Set to `0` to restore the blocking 5-second connection wait. Servers configured with [`alwaysLoad: true`](/en/mcp#exempt-a-server-from-deferral) still block startup regardless, since their tools must be present when the first prompt is built |

| `MCP_CONNECT_TIMEOUT_MS` | How long blocking MCP startup waits, in milliseconds, for the connection batch before snapshotting the tool list (default: 5000). Applies when `MCP_CONNECTION_NONBLOCKING=0` or for servers marked [`alwaysLoad: true`](/en/mcp#exempt-a-server-from-deferral). Servers still pending at the deadline keep connecting in the background but won't appear until the next query. Distinct from `MCP_TIMEOUT`, which bounds an individual server's connect attempt |

| `MCP_OAUTH_CALLBACK_PORT` | Fixed port for the OAuth redirect callback, as an alternative to `--callback-port` when adding an MCP server with [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials) |

| `MCP_REMOTE_SERVER_CONNECTION_BATCH_SIZE` | Maximum number of remote MCP servers (HTTP/SSE) to connect in parallel during startup (default: 20) |

| `MCP_SERVER_CONNECTION_BATCH_SIZE` | Maximum number of local MCP servers (stdio) to connect in parallel during startup (default: 3) |

errors +4 -2

@@ -177,7 +177,7 @@ Claude Code blocks further requests until the reset time shown in the message.

- Wait for the reset time shown in the error

- Run `/usage` to see your plan limits and when they reset

- Run `/extra-usage` to buy additional usage on Pro and Max, or to request it from your admin on Team and Enterprise. See [Extra usage for paid plans](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) for how this is billed.

- Run `/usage-credits` to buy additional usage on Pro and Max, or to request it from your admin on Team and Enterprise. See [usage credits for paid plans](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) for how this is billed.

- To upgrade your plan for higher base limits, see [claude.com/pricing](https://claude.com/pricing)

To watch your remaining allowance before you hit the limit, add the `rate_limits` fields to a [custom status line](/en/statusline#rate-limit-usage), or in the Desktop app click the [usage ring](/en/desktop#check-usage) next to the model picker.

@@ -202,9 +202,11 @@ This is [retried automatically](#automatic-retries) before being shown.

You have hit the rate limit configured for your API key, Amazon Bedrock project, or Google Vertex AI project.

```text

API Error: Request rejected (429) · this may be a temporary capacity issue

API Error: Request rejected (429) · this may be a temporary capacity issue. If it persists, check status.claude.com.

```

The trailing sentence names where to check service health and varies by provider. Bedrock and Vertex AI configurations name that provider's service status instead of the Anthropic status page.

**What to do:**

- Run `/status` and confirm the active credential is the one you expect. A stray `ANTHROPIC_API_KEY` in your environment can route requests through a low-tier key instead of your subscription.

fast-mode +13 -43

ファストモードに関する記述が大幅に整理・簡略化されました。

@@ -11,19 +11,18 @@ Fast mode is in [research preview](#research-preview). The feature, pricing, and

Fast mode is a high-speed configuration for Claude Opus, making the model 2.5x faster at a higher cost per token. Toggle it on with `/fast` when you need speed for interactive work like rapid iteration or live debugging, and toggle it off when cost matters more than latency.

Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities, just faster responses. Fast mode is supported on Opus 4.6 and Opus 4.7. It is not available on Sonnet, Haiku, or other models.

Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities with faster responses. Fast mode is supported on Opus 4.7 and Opus 4.6. It is not available on Sonnet, Haiku, or other models.

Fast mode requires Claude Code v2.1.36 or later. Check your version with `claude --version`.

What to know:

- Use `/fast` to toggle on fast mode in Claude Code CLI. Also available via `/fast` in Claude Code VS Code Extension.

- By default, `/fast` runs on Opus 4.6. To run fast mode on Opus 4.7 instead, set the [`CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE`](#use-fast-mode-on-opus-4-7) environment variable.

- Fast mode pricing is $30/$150 MTok on both Opus 4.6 and Opus 4.7.

- Fast mode pricing is $30/$150 MTok on both Opus 4.7 and Opus 4.6.

- Available to all Claude Code users on subscription plans (Pro/Max/Team/Enterprise) and Claude Console.

- For Claude Code users on subscription plans (Pro/Max/Team/Enterprise), fast mode is available via extra usage only and not included in the subscription rate limits.

- For Claude Code users on subscription plans (Pro/Max/Team/Enterprise), fast mode is available via usage credits only and not included in the subscription rate limits.

This page covers how to [toggle fast mode](#toggle-fast-mode), [use fast mode on Opus 4.7](#use-fast-mode-on-opus-4-7), the [cost tradeoff](#understand-the-cost-tradeoff), [when to use it](#decide-when-to-use-fast-mode), [requirements](#requirements), [per-session opt-in](#require-per-session-opt-in), and [rate limit behavior](#handle-rate-limits).

This page covers how to [toggle fast mode](#toggle-fast-mode), its [cost tradeoff](#understand-the-cost-tradeoff), [when to use it](#decide-when-to-use-fast-mode), [requirements](#requirements), [per-session opt-in](#require-per-session-opt-in), and [rate limit behavior](#handle-rate-limits).

## Toggle fast mode

@@ -38,42 +37,14 @@ For the best cost efficiency, enable fast mode at the start of a session rather

When you enable fast mode:

- If you're on a different model, Claude Code automatically switches to the fast mode model: Opus 4.6 by default, or Opus 4.7 when [`CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE`](#use-fast-mode-on-opus-4-7) is set.

- If you're on a different model, Claude Code automatically switches to Opus

- You'll see a confirmation message: "Fast mode ON"

- A small `↯` icon appears next to the prompt while fast mode is active

- Run `/fast` again at any time to check whether fast mode is on or off

When you disable fast mode with `/fast` again, you remain on the same Opus version that fast mode was running on. The model does not revert to your previous model. To switch to a different model, use `/model`.

When you disable fast mode with `/fast` again, you remain on Opus. The model does not revert to your previous model. To switch to a different model, use `/model`.

## Use fast mode on Opus 4.7

Fast mode on Opus 4.7 requires Claude Code v2.1.139 or later.

Fast mode for Claude Opus 4.7 is in research preview. It runs at the same 2.5x speed and the same price as fast mode for Opus 4.6, with no other behavior changes.

On May 14, 2026, Opus 4.7 becomes the default fast mode model. Until then, opt in by setting `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE=1`.

To opt in, set `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE=1` before launching Claude Code. With the variable set, `/fast` runs on Opus 4.7. Without it, `/fast` continues to run on Opus 4.6.

You can set the variable as a shell export:

```bash

export CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE=1

```

Or in any Claude Code [settings file](/en/settings#settings-files), including user, project, and managed settings, to scope the opt-in:

```json

{

"env": {

"CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE": "1"

}

```

Fast mode for Opus 4.6 remains available alongside Opus 4.7. The two share the same fast mode rate limit pool: usage on either model draws from the same limits.

To pin fast mode to Opus 4.6 explicitly, set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1`. This variable takes precedence, so fast mode runs on Opus 4.6 regardless of whether `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE` is set.

Opus 4.7 is the fast mode default in Claude Code v2.1.142 and later. To pin fast mode to Opus 4.6 instead, set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1`.

## Understand the cost tradeoff

@@ -81,8 +52,7 @@ Fast mode has higher per-token pricing than standard Opus:

| Mode | Input (MTok) | Output (MTok) |

| - | - | - |

| Fast mode on Opus 4.6 | $30 | $150 |

| Fast mode on Opus 4.7 | $30 | $150 |

| Fast mode | $30 | $150 |

Fast mode pricing is flat across the full 1M token context window.

@@ -117,10 +87,10 @@ You can combine both: use fast mode with a lower [effort level](/en/model-config

Fast mode requires all of the following:

- **Not available on third-party cloud providers**: fast mode is not available on Amazon Bedrock, Google Vertex AI, or Microsoft Azure Foundry. Fast mode is available through the Anthropic Console API and for Claude subscription plans using extra usage.

- **Extra usage enabled**: your account must have extra usage enabled, which allows billing beyond your plan's included usage. For individual accounts, enable this in your [Console billing settings](https://platform.claude.com/settings/organization/billing). For Team and Enterprise, an admin must enable extra usage for the organization.

- **Usage credits turned on**: your account must have usage credits turned on, which allows billing beyond your plan's included usage. For individual accounts, turn this on in your [Console billing settings](https://platform.claude.com/settings/organization/billing). For Team and Enterprise, an admin must turn on usage credits for the organization.

Fast mode usage is billed directly to extra usage, even if you have remaining usage on your plan. This means fast mode tokens do not count against your plan's included usage and are charged at the fast mode rate from the first token.

Fast mode usage draws directly from usage credits, even if you have remaining usage on your plan. This means fast mode tokens do not count against your plan's included usage and are charged at the fast mode rate from the first token.

- **Admin enablement for Team and Enterprise**: fast mode is disabled by default for Team and Enterprise organizations. An admin must explicitly [enable fast mode](#enable-fast-mode-for-your-organization) before users can access it.

@@ -149,9 +119,9 @@ This is useful for controlling costs in organizations where users run multiple c

## Handle rate limits

Fast mode has separate rate limits from standard Opus. Fast mode for Opus 4.6 and Opus 4.7 share the same rate limit pool: usage on either model draws from the same limits. When you hit the fast mode rate limit or run out of extra usage:

Fast mode has separate rate limits from standard Opus. Fast mode for Opus 4.7 and Opus 4.6 share the same rate limit pool: usage on either model draws from the same limits. When you hit the fast mode rate limit or run out of usage credits:

1. Fast mode automatically falls back to standard speed on the same Opus version

1. Fast mode automatically falls back to standard speed

2. The `↯` icon turns gray to indicate cooldown

3. You continue working at standard speed and pricing

4. When the cooldown expires, fast mode automatically re-enables

features-overview +2 -2

@@ -244,9 +244,9 @@ Run `/mcp` to see token costs per server. Disconnect servers you're not actively

**What loads:** Fresh, isolated context containing:

- The system prompt (shared with parent for cache efficiency)

- The agent's own system prompt, not the full Claude Code system prompt

- Full content of skills listed in the agent's `skills:` field

- CLAUDE.md and git status (inherited from parent)

- CLAUDE.md and git status, except the built-in Explore and Plan agents [omit both](/en/sub-agents#what-loads-at-startup)

- Whatever context the lead agent passes in the prompt

**Context cost:** Isolated from main session. Subagents don't inherit your conversation history or invoked skills.

hooks-guide +5 -3

@@ -861,11 +861,11 @@ You edited a settings file but the hooks don't appear in the menu.

- Verify your JSON is valid (trailing commas and comments are not allowed)

- Confirm the settings file is in the correct location: `.claude/settings.json` for project hooks, `~/.claude/settings.json` for global hooks

### Stop hook runs forever

### Stop hook hits the block cap

Claude keeps working in an infinite loop instead of stopping.

Claude keeps working instead of stopping, then ends the turn with a warning that the Stop hook blocked too many consecutive times.

Your Stop hook script needs to check whether it already triggered a continuation. Parse the `stop_hook_active` field from the JSON input and exit early if it's `true`:

Claude Code overrides a Stop hook after it blocks 8 times in a row without progress. Your hook script needs to check whether it already triggered a continuation. Parse the `stop_hook_active` field from the JSON input and exit early if it's `true`:

```bash

#!/bin/bash

@@ -876,6 +876,8 @@ fi

# ... rest of your hook logic

```

If your hook legitimately needs more than eight iterations to converge, raise the cap with [`CLAUDE_CODE_STOP_HOOK_BLOCK_CAP`](/en/env-vars).

### JSON validation failed

Claude Code shows a JSON parsing error even though your hook script outputs valid JSON.

hooks +4 -2

@@ -1822,7 +1822,9 @@ The [`/goal`](/en/goal) command is a built-in shortcut for a session-scoped prom

#### Stop input

In addition to the [common input fields](#common-input-fields), Stop hooks receive `stop_hook_active` and `last_assistant_message`. The `stop_hook_active` field is `true` when Claude Code is already continuing as a result of a stop hook. Check this value or process the transcript to prevent Claude Code from running indefinitely. The `last_assistant_message` field contains the text content of Claude's final response, so hooks can access it without parsing the transcript file.

In addition to the [common input fields](#common-input-fields), Stop hooks receive `stop_hook_active` and `last_assistant_message`. The `stop_hook_active` field is `true` when Claude Code is already continuing as a result of a stop hook. Check this value or process the transcript to avoid blocking on a condition that will never resolve. Claude Code overrides the hook and ends the turn after 8 consecutive blocks.

The `last_assistant_message` field contains the text content of Claude's final response, so hooks can access it without parsing the transcript file.

```json

{

@@ -2705,4 +2707,4 @@ Hook execution details, including which hooks matched, their exit codes, and ful

For more granular hook matching details, set `CLAUDE_CODE_DEBUG_LOG_LEVEL=verbose` to see additional log lines such as hook matcher counts and query matching.

For troubleshooting common issues like hooks not firing, infinite Stop hook loops, or configuration errors, see [Limitations and troubleshooting](/en/hooks-guide#limitations-and-troubleshooting) in the guide. For a broader diagnostic walkthrough covering `/context`, `/doctor`, and settings precedence, see [Debug your config](/en/debug-your-config).

For troubleshooting common issues like hooks not firing, Stop hooks that keep blocking, or configuration errors, see [Limitations and troubleshooting](/en/hooks-guide#limitations-and-troubleshooting) in the guide. For a broader diagnostic walkthrough covering `/context`, `/doctor`, and settings precedence, see [Debug your config](/en/debug-your-config).

jetbrains +1 -1

@@ -24,7 +24,7 @@ The Claude Code plugin works with most JetBrains IDEs, including:

- **Quick launch**: use `Cmd+Esc` (Mac) or `Ctrl+Esc` (Windows/Linux) to open Claude Code directly from your editor, or click the Claude Code button in the UI

- **Diff viewing**: code changes can be displayed directly in the IDE diff viewer instead of the terminal

- **Selection context**: the current selection or tab in the IDE is automatically shared with Claude Code

- **Selection context**: the current selection or tab in the IDE is automatically shared with Claude Code. [`Read` deny rules](/en/permissions#read-and-edit) block this sharing for matching files

- **File reference shortcuts**: use `Cmd+Option+K` (Mac) or `Alt+Ctrl+K` (Linux/Windows) to insert file references such as `@src/auth.ts#L1-99`

- **Diagnostic sharing**: diagnostic errors from the IDE, such as lint and syntax errors, are automatically shared with Claude as you work

mcp +3 -1

@@ -132,6 +132,8 @@ claude mcp remove github

The `/mcp` panel shows the tool count next to each connected server and flags servers that advertise the tools capability but expose no tools.

If your request needs tools from a server that is still connecting in the background, Claude waits for that server before continuing. With [tool search](#scale-with-mcp-tool-search) enabled, which is the default, the wait happens inside the `ToolSearch` call. In configurations without tool search, such as Vertex AI, a custom `ANTHROPIC_BASE_URL`, or `ENABLE_TOOL_SEARCH=false`, Claude uses the `WaitForMcpServers` tool instead.

The server name `workspace` is reserved for internal use. If your configuration defines a server with that name, Claude Code skips it at load time and shows a warning asking you to rename it.

### Dynamic tool updates

@@ -902,7 +904,7 @@ The following `.mcp.json` entry exempts one HTTP server while leaving other serv

The `alwaysLoad` field is available on all server types and requires Claude Code v2.1.121 or later. An MCP server can also mark individual tools as always-loaded by including `"anthropic/alwaysLoad": true` in the tool's `_meta` object, which has the same effect for that tool only.

Setting `alwaysLoad: true` also blocks startup until the server connects, capped at the standard 5-second connect timeout. This applies even when [`MCP_CONNECTION_NONBLOCKING=1`](/en/env-vars) is set, since the tools must be present when the first prompt is built. Other servers still connect in the background when nonblocking is enabled.

Setting `alwaysLoad: true` also blocks startup until the server connects, capped at the standard 5-second connect timeout. This applies even though MCP startup is otherwise [non-blocking by default](/en/env-vars), since the tools must be present when the first prompt is built. Other servers continue to connect in the background.

## Use MCP prompts as commands

model-config +10 -6

@@ -233,17 +233,17 @@ Thinking output is collapsed by default. Press `Ctrl+O` to toggle verbose mode a

Opus 4.7, Opus 4.6, and Sonnet 4.6 support a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions with large codebases.

Availability varies by model and plan. On Max, Team, and Enterprise plans, Opus is automatically upgraded to 1M context with no additional configuration. This applies to both Team Standard and Team Premium seats. Sonnet with 1M context is not part of the automatic upgrade and requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) on every subscription plan, including Max.

Availability varies by model and plan. On Max, Team, and Enterprise plans, Opus is automatically upgraded to 1M context with no additional configuration. This applies to both Team Standard and Team Premium seats. Sonnet with 1M context is not part of the automatic upgrade and requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) on every subscription plan, including Max.

| Plan | Opus with 1M context | Sonnet with 1M context |

| - | - | - |

| Max, Team, and Enterprise | Included with subscription | Requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Pro | Requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) | Requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Max, Team, and Enterprise | Included with subscription | Requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Pro | Requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) | Requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| API and pay-as-you-go | Full access | Full access |

To disable 1M context entirely, set `CLAUDE_CODE_DISABLE_1M_CONTEXT=1`. This removes 1M model variants from the model picker. See [environment variables](/en/env-vars).

The 1M context window uses standard model pricing with no premium for tokens beyond 200K. For plans where extended context is included with your subscription, usage remains covered by your subscription. For plans that access extended context through extra usage, tokens are billed to extra usage.

If your account supports 1M context, the option appears in the model picker (`/model`) in the latest versions of Claude Code. If you don't see it, try restarting your session.

@@ -291,7 +291,7 @@ names** (or equivalent for your API provider), to control the model names that t

| `ANTHROPIC_DEFAULT_OPUS_MODEL` | The model to use for `opus`, or for `opusplan` when Plan Mode is active. |

| `ANTHROPIC_DEFAULT_SONNET_MODEL` | The model to use for `sonnet`, or for `opusplan` when Plan Mode is not active. |

| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | The model to use for `haiku`, or [background functionality](/en/costs#background-token-usage) |

| `CLAUDE_CODE_SUBAGENT_MODEL` | The model to use for [subagents](/en/sub-agents) |

| `CLAUDE_CODE_SUBAGENT_MODEL` | The model to use for all [subagents](/en/sub-agents#choose-a-model). Overrides both the per-invocation `model` parameter and the subagent definition's `model` frontmatter |

Note: `ANTHROPIC_SMALL_FAST_MODEL` is deprecated in favor of

`ANTHROPIC_DEFAULT_HAIKU_MODEL`.

@@ -320,7 +320,11 @@ To enable [extended context](#extended-context) for a pinned model, append `[1m]

export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-7[1m]'

```

The `[1m]` suffix applies the 1M context window to all usage of that alias, including `opusplan`. Claude Code strips the suffix before sending the model ID to your provider. Only append `[1m]` when the underlying model supports 1M context, such as Opus 4.7 or Sonnet 4.6.

The `[1m]` suffix applies the 1M context window to all usage of that alias, including `opusplan`.

- Claude Code strips the suffix before sending the model ID to your provider.

- Only append `[1m]` when the underlying model [supports 1M context](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window).

- The suffix is read per variable, not per model. On Bedrock, Vertex, and Foundry, a model ID without `[1m]` in one variable uses 200K context even if another variable sets the same model with the suffix.

The `settings.availableModels` allowlist still applies when using third-party providers. Filtering matches on the model alias (`opus`, `sonnet`, `haiku`), not the provider-specific model ID.

overview +1 -1

@@ -3,7 +3,7 @@ title: overview

source: https://code.claude.com/docs/en/overview.md

---

# Claude Code overview

# Overview

> Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.

permission-modes +3 -1

@@ -70,7 +70,7 @@ The mode indicator shows these labels, mapped to the mode each one applies:

| Auto mode | `auto` |

| Bypass permissions | `bypassPermissions` |

Auto mode appears in the mode indicator after you enable **Allow dangerously skip permissions** in the extension settings, but it stays unavailable until your account meets every requirement listed in the [auto mode section](#eliminate-prompts-with-auto-mode). The `claudeCode.initialPermissionMode` setting does not accept `auto`; to start in auto mode by default, set `defaultMode` in your Claude Code [`settings.json`](/en/settings#settings-files) instead.

Auto mode appears in the mode indicator after you enable **Allow dangerously skip permissions** in the extension settings, but it stays unavailable until your account meets every requirement listed in the [auto mode section](#eliminate-prompts-with-auto-mode). The `claudeCode.initialPermissionMode` setting does not accept `auto`. To start in auto mode by default, set `defaultMode` in your [user settings](/en/settings#settings-files) instead. Claude Code ignores `defaultMode: "auto"` in project and local settings.

Bypass permissions also requires the **Allow dangerously skip permissions** toggle before it appears in the mode indicator.

@@ -164,6 +164,8 @@ Auto mode is available only when your account meets all of these requirements:

If Claude Code reports auto mode as unavailable, one of these requirements is unmet; this is not a transient outage. A separate message that names a model and says auto mode "cannot determine the safety" of an action is a transient classifier outage; see the [error reference](/en/errors#auto-mode-cannot-determine-the-safety-of-an-action).

If you set `defaultMode: "auto"` in [settings](/en/settings#available-settings) and the session starts in `default` mode with no error, the setting is likely in `.claude/settings.json` or `.claude/settings.local.json`. Claude Code ignores `auto` from those files so a repository cannot grant itself auto mode. Move it to `~/.claude/settings.json`.

### What the classifier blocks by default

The classifier trusts your working directory and your repo's configured remotes. Everything else is treated as external until you [configure trusted infrastructure](/en/auto-mode-config).

permissions +1 -1

@@ -179,7 +179,7 @@ Claude Code parses the PowerShell AST and checks each command in a compound comm

### Read and Edit

`Edit` rules apply to all built-in tools that edit files. Claude makes a best-effort attempt to apply `Read` rules to all built-in tools that read files like Grep and Glob.

`Edit` rules apply to all built-in tools that edit files. Claude makes a best-effort attempt to apply `Read` rules to all built-in tools that read files like Grep and Glob, to `@file` mentions in your prompts, and to the selection and open-file context that a connected [IDE](/en/vs-code#the-built-in-ide-mcp-server) shares with Claude.

Read and Edit deny rules apply to Claude's built-in file tools and to file commands Claude Code recognizes in Bash, such as `cat`, `head`, `tail`, and `sed`. They do not apply to arbitrary subprocesses that read or write files indirectly, like a Python or Node script that opens files itself. For OS-level enforcement that blocks all processes from accessing a path, [enable the sandbox](/en/sandboxing).

plugin-dependencies +24 -0

プラグインの依存関係管理に関する新しいセクションが追加されました。

@@ -111,6 +111,30 @@ Auto-update fetches a constrained dependency at the highest git tag that satisfi

When you uninstall the last plugin that constrains a dependency, the dependency is no longer held and resumes tracking its marketplace entry on the next update.

## Enable or disable a plugin with dependencies

Enabling a plugin also enables the plugins it depends on, and disabling a plugin is blocked if another enabled plugin still needs it. Both behaviors require Claude Code v2.1.143 or later. Earlier versions enable or disable only the named plugin and surface a `dependency-unsatisfied` error on the next load.

When you enable a plugin, Claude Code also enables its dependencies at the same scope. If a dependency has its own dependencies, Claude Code enables those too. The success message lists what else was enabled along with the plugin you named. If a dependency can't be enabled, the command refuses and tells you what's blocking and how to fix it:

| Condition | Result |

| :- | :- |

| A dependency is not installed | Enable fails and prints the `claude plugin install` command for each missing dependency. |

| A dependency is blocked by your organization's plugin policy | Enable fails and names the blocked dependency. |

| A dependency is set to `false` at a scope with higher precedence than the target scope | Enable fails. Enable the dependency at that scope, or pass `--scope` to write there. |

| All dependencies are installed and allowed | Enable succeeds and writes `true` for the plugin and each dependency that was not already enabled at the target scope. |

When you disable a plugin, Claude Code refuses if another enabled plugin still depends on it. The error names the plugins that depend on it and gives you a chained command that disables them in the right order, ending with the one you asked for.

For example, if `deploy-kit` depends on `secrets-vault`, disabling `secrets-vault` alone fails with output similar to the following:

```text

secrets-vault is still required by deploy-kit. Disable that plugin first, or

disable everything together: claude plugin disable deploy-kit@acme-tools && claude plugin disable secrets-vault@acme-tools

```

Copy the chained command from the error to disable the full set in one step.

## Remove orphaned auto-installed dependencies

Auto-installed dependencies stay on disk after the plugins that installed them are uninstalled, in case you reinstall a dependent plugin or want to keep using the dependency directly. To clean them up, run `claude plugin prune` to list the auto-installed dependencies that no longer have any installed plugin requiring them and remove them after a confirmation prompt. This requires Claude Code v2.1.121 or later.

plugin-marketplaces +2 -1

@@ -143,7 +143,7 @@ Each plugin entry needs at minimum a `name` and `source` (where to fetch it from

**Reserved names**: The following marketplace names are reserved for official Anthropic use and cannot be used by third-party marketplaces: `claude-code-marketplace`, `claude-code-plugins`, `claude-plugins-official`, `anthropic-marketplace`, `anthropic-plugins`, `agent-skills`, `knowledge-work-plugins`, `life-sciences`. Names that impersonate official marketplaces (like `official-claude-plugins` or `anthropic-tools-v2`) are also blocked.

**Reserved names**: The following marketplace names are reserved for official Anthropic use and cannot be used by third-party marketplaces: `claude-code-marketplace`, `claude-code-plugins`, `claude-plugins-official`, `anthropic-marketplace`, `anthropic-plugins`, `agent-skills`, `anthropic-agent-skills`, `knowledge-work-plugins`, `life-sciences`. Names that impersonate official marketplaces, such as `official-claude-plugins` or `anthropic-tools-v2`, are also blocked.

### Owner fields

@@ -181,6 +181,7 @@ Each plugin entry in the `plugins` array describes a plugin and where to find it

| Field | Type | Description |

| :- | :- | :- |

| `displayName` | string | Human-readable name shown in UI surfaces. Falls back to `name` when omitted. May contain spaces and any casing. Not used for namespacing or lookup. Requires Claude Code v2.1.143 or later. |

| `description` | string | Brief plugin description |

| `version` | string | Plugin version. If set (here or in `plugin.json`), the plugin is pinned to this string and users only receive updates when it changes. Omit to fall back to the git commit SHA. See [Version resolution](#version-resolution-and-release-channels). |

| `author` | object | Plugin author information (`name` required, `email` optional) |

plugins-reference +9 -4

@@ -19,7 +19,7 @@ A **plugin** is a self-contained directory of components that extends Claude Cod

Plugins add skills to Claude Code, creating `/name` shortcuts that you or Claude can invoke.

**Location**: `skills/` or `commands/` directory in plugin root

**Location**: `skills/` or `commands/` directory in plugin root, or a single `SKILL.md` file at the plugin root

**File format**: Skills are directories with `SKILL.md`; commands are simple markdown files

@@ -360,6 +360,7 @@ The manifest is optional. If omitted, Claude Code auto-discovers components in [

```json

{

"name": "plugin-name",

"displayName": "Plugin Name",

"version": "1.2.0",

"description": "Brief plugin description",

"author": {

@@ -406,6 +407,7 @@ agent `agent-creator` for the plugin with name `plugin-dev` will appear as

| :- | :- | :- | :- |

| `$schema` | string | JSON Schema URL for editor autocomplete and validation. Claude Code ignores this field at load time. | `"https://json.schemastore.org/claude-code-plugin-manifest.json"` |

| `displayName` | string | Human-readable name shown in the `/plugin` picker and other UI surfaces. Falls back to `name` when omitted. Unlike `name`, may contain spaces and any casing. Not used for namespacing or lookup. Requires Claude Code v2.1.143 or later. | `"Deployment Tools"` |

| `version` | string | Optional. Semantic version. Setting this pins the plugin to that version string, so users only receive updates when you bump it. If omitted, Claude Code falls back to the git commit SHA, so every commit is treated as a new version. If also set in the marketplace entry, `plugin.json` wins. See [Version management](#version-management). | `"2.1.0"` |

| `author` | object | Author information | `{"name": "Dev Team", "email": "dev@company.com"}` |

@@ -520,6 +522,8 @@ For all path fields:

- Multiple paths can be specified as arrays

- When a skill path points to a directory that contains a `SKILL.md` directly, for example `"skills": ["./"]` pointing to the plugin root, the frontmatter `name` field in `SKILL.md` determines the skill's invocation name. This gives a stable name regardless of the install directory. If `name` is not set in the frontmatter, the directory basename is used as a fallback.

A plugin that has a `SKILL.md` at its root, no `skills/` subdirectory, and no `skills` manifest field is automatically loaded as a single-skill plugin in Claude Code v2.1.142 and later. You do not need to set `"skills": ["./"]` in `plugin.json` for this layout. The skill's invocation name follows the same rule as above: the frontmatter `name` field, or the directory basename as a fallback.

**Path examples**:

```json

@@ -805,7 +809,7 @@ The command lists orphaned dependencies and asks for confirmation before removin

### plugin enable

Enable a disabled plugin.

Enable a disabled plugin. If the plugin declares [dependencies](/en/plugin-dependencies), Claude Code enables them transitively at the same scope, and the command fails when a dependency is not installed.

```bash

claude plugin enable <plugin> [options]

@@ -824,7 +828,7 @@ claude plugin enable <plugin> [options]

### plugin disable

Disable a plugin without uninstalling it.

Disable a plugin without uninstalling it. Fails when another enabled plugin [depends on](/en/plugin-dependencies#enable-or-disable-a-plugin-with-dependencies) the target. The error message includes a chained command that disables every dependent first.

```bash

claude plugin disable <plugin> [options]

@@ -880,7 +884,7 @@ claude plugin list [options]

### plugin details

Show a plugin's component inventory and projected token cost. The output lists all components the plugin contributes, grouped as Skills (skills and commands), Agents, Hooks, and MCP servers, along with an estimate of how many tokens it adds to each session.

Show a plugin's component inventory and projected token cost. The output lists all components the plugin contributes, grouped as Skills, Agents, Hooks, MCP servers, and LSP servers, along with an estimate of how many tokens it adds to each session. The Skills group includes both `skills/` and `commands/` entries.

```bash

claude plugin details <name>

@@ -913,6 +917,7 @@ Component inventory

Agents (0)

Hooks (1) (harness-only — no model context cost)

MCP servers (0)

LSP servers (0)

Projected token cost

Always-on: ~180 tok added to every session

remote-control +1 -1

@@ -163,7 +163,7 @@ If notifications don't arrive:

- **Local process must keep running**: Remote Control runs as a local process. If you close the terminal, quit VS Code, or otherwise stop the `claude` process, the session ends.

- **Extended network outage**: if your machine is awake but unable to reach the network for more than roughly 10 minutes, the session times out and the process exits. Run `claude remote-control` again to start a new session.

- **Ultraplan disconnects Remote Control**: starting an [ultraplan](/en/ultraplan) session disconnects any active Remote Control session because both features occupy the claude.ai/code interface and only one can be connected at a time.

- **Some commands are local-only**: commands that open an interactive picker in the terminal, such as `/mcp`, `/plugin`, or `/resume`, work only from the local CLI. Commands that produce text output, including `/compact`, `/clear`, `/context`, `/usage`, `/exit`, `/extra-usage`, `/recap`, and `/reload-plugins`, work from mobile and web.

- **Some commands are local-only**: commands that open an interactive picker in the terminal, such as `/mcp`, `/plugin`, or `/resume`, work only from the local CLI. Commands that produce text output, including `/compact`, `/clear`, `/context`, `/usage`, `/exit`, `/usage-credits`, `/recap`, and `/reload-plugins`, work from mobile and web.

## Troubleshooting

routines +1 -1

@@ -295,7 +295,7 @@ See [Network access](/en/claude-code-on-the-web#network-access) for details on a

Routines draw down subscription usage the same way interactive sessions do. In addition to the standard subscription limits, routines have a daily cap on how many runs can start per account. See your current consumption and remaining daily routine runs at [claude.ai/code/routines](https://claude.ai/code/routines) or [claude.ai/settings/usage](https://claude.ai/settings/usage).

When a routine hits the daily cap or your subscription usage limit, organizations with extra usage enabled can keep running routines on metered overage. Without extra usage, additional runs are rejected until the window resets. Enable extra usage from **Settings > Billing** on claude.ai.

When a routine hits the daily cap or your subscription usage limit, organizations with usage credits turned on can keep running routines on metered overage. Without usage credits, additional runs are rejected until the window resets. Turn on usage credits from **Settings > Billing** on claude.ai.

One-off runs do not count against the daily routine cap. They draw down your regular subscription usage like any other session, but they are exempt from the per-account daily routine run allowance.

scheduled-tasks +1 -1

@@ -11,7 +11,7 @@ Scheduled tasks require Claude Code v2.1.72 or later. Check your version with `c

Scheduled tasks let Claude re-run a prompt automatically on an interval. Use them to poll a deployment, babysit a PR, check back on a long-running build, or remind yourself to do something later in the session. To react to events as they happen instead of polling, see [Channels](/en/channels): your CI can push the failure into the session directly. To keep the session working turn after turn until a condition is met rather than on an interval, see [`/goal`](/en/goal).

Tasks are session-scoped: they live in the current conversation and stop when you start a new one. Resuming with `--resume` or `--continue` brings back any task that hasn't [expired](#seven-day-expiry): a recurring task created within the last 7 days, or a one-shot whose scheduled time hasn't passed yet. For scheduling that survives independently of any session, use [Routines](/en/routines), [Desktop scheduled tasks](/en/desktop-scheduled-tasks), or [GitHub Actions](/en/github-actions).

Tasks are session-scoped: they live in the current conversation and stop when you start a new one. Resuming with `--resume` or `--continue` brings back any task that hasn't [expired](#seven-day-expiry): a recurring task created within the last 7 days, or a one-shot whose scheduled time hasn't passed yet. For scheduling that survives independently of any session, use [Routines](/en/routines) to create a routine on Anthropic-managed infrastructure, set up a [Desktop scheduled task](/en/desktop-scheduled-tasks), or use [GitHub Actions](/en/github-actions).

## Compare scheduling options

settings +3 -2

@@ -222,7 +222,7 @@ The published schema is updated periodically and may not include settings added

| `prUrlTemplate` | URL template for the PR badge shown in the footer and in tool-result summaries. Substitutes `{host}`, `{owner}`, `{repo}`, `{number}`, and `{url}` from the `gh`-reported PR URL. Use to point PR links at an internal code-review tool instead of `github.com`. Does not affect `#123` autolinks in Claude's prose | `"https://reviews.example.com/{owner}/{repo}/pull/{number}"` |

| `respectGitignore` | Control whether the `@` file picker respects `.gitignore` patterns. When `true` (default), files matching `.gitignore` patterns are excluded from suggestions | `false` |

| `showClearContextOnPlanAccept` | Show the "clear context" option on the plan accept screen. Defaults to `false`. Set to `true` to restore the option | `true` |

| `showThinkingSummaries` | Show [extended thinking](/en/model-config#extended-thinking) summaries in interactive sessions. When unset or `false` (default in interactive mode), thinking blocks are redacted by the API and shown as a collapsed stub. Redaction only changes what you see, not what the model generates: to reduce thinking spend, [lower the budget or disable thinking](/en/model-config#extended-thinking) instead. Non-interactive mode (`-p`) and SDK callers always receive summaries regardless of this setting | `true` |

| `showThinkingSummaries` | Show [extended thinking](/en/model-config#extended-thinking) summaries in interactive sessions. When unset or `false` (default in interactive mode), thinking blocks are redacted by the API and shown as a collapsed stub. Redaction only changes what you see, not what the model generates: to reduce thinking spend, [lower the budget or disable thinking](/en/model-config#extended-thinking) instead. This setting has no effect in non-interactive mode (`-p`), the Agent SDK, or IDE extensions such as VS Code | `true` |

| `showTurnDuration` | Show turn duration messages after responses, e.g. "Cooked for 1m 6s". Default: `true`. Appears in `/config` as **Show turn duration** | `false` |

| `skillListingBudgetFraction` | Fraction of the model's context window reserved for the [skill listing](/en/skills#skill-descriptions-are-cut-short) Claude sees each turn (default: `0.01` = 1%). When the listing exceeds the budget, descriptions for the least-used skills are collapsed to bare names so Claude can still invoke them but won't see why. Raise to keep more descriptions visible at the cost of more context per turn. `/doctor` shows the current truncation count and which skills are affected. Requires Claude Code v2.1.105 or later | `0.02` |

| `skillOverrides` | Per-skill visibility overrides keyed by skill name. Value is `"on"`, `"name-only"`, `"user-invocable-only"`, or `"off"`. Lets you hide or collapse a skill without editing its SKILL.md. Does not apply to plugin skills, which are managed through `/plugin`. The `/skills` menu writes these to `.claude/settings.local.json`. See [Override skill visibility from settings](/en/skills#override-skill-visibility-from-settings). Requires Claude Code v2.1.129 or later | `{"legacy-context": "name-only", "deploy": "off"}` |

@@ -265,6 +265,7 @@ Configure how `--worktree` creates and manages git worktrees.

| `worktree.baseRef` | Which ref new worktrees branch from. `"fresh"` (default) branches from `origin/<default-branch>` for a clean tree matching the remote. `"head"` branches from your current local `HEAD`, so unpushed commits and feature-branch state are present in the worktree. Applies to `--worktree`, the `EnterWorktree` tool, and subagent isolation | `"head"` |

| `worktree.symlinkDirectories` | Directories to symlink from the main repository into each worktree to avoid duplicating large directories on disk. No directories are symlinked by default | `["node_modules", ".cache"]` |

| `worktree.sparsePaths` | Directories to check out in each worktree via git sparse-checkout. Only the listed directories plus root-level files are written to disk, which is faster in large monorepos | `["packages/my-app", "shared/utils"]` |

| `worktree.bgIsolation` | Isolation mode for [background sessions](/en/agent-view#how-file-edits-are-isolated). `"worktree"` (default) blocks `Edit`/`Write` in the main checkout until `EnterWorktree` is called. `"none"` lets background jobs edit the working copy directly. Requires Claude Code v2.1.143 or later | `"none"` |

To copy gitignored files like `.env` into new worktrees, use a [`.worktreeinclude` file](/en/worktrees#copy-gitignored-files-into-worktrees) in your project root instead of a setting.

@@ -276,7 +277,7 @@ To copy gitignored files like `.env` into new worktrees, use a [`.worktreeinclud

| `ask` | Array of permission rules to ask for confirmation upon tool use. See [Permission rule syntax](#permission-rule-syntax) below | `[ "Bash(git push *)" ]` |

| `deny` | Array of permission rules to deny tool use. Use this to exclude sensitive files from Claude Code access. See [Permission rule syntax](#permission-rule-syntax) and [Bash permission limitations](/en/permissions#tool-specific-permission-rules) | `[ "WebFetch", "Bash(curl *)", "Read(./.env)", "Read(./secrets/**)" ]` |

| `additionalDirectories` | Additional [working directories](/en/permissions#working-directories) for file access. Most `.claude/` configuration is [not discovered](/en/permissions#additional-directories-grant-file-access-not-configuration) from these directories | `[ "../docs/" ]` |

| `defaultMode` | Default [permission mode](/en/permission-modes) when opening Claude Code. Valid values: `default`, `acceptEdits`, `plan`, `auto`, `dontAsk`, `bypassPermissions`. As of Claude Code v2.1.142, `auto` is ignored when set in project or local settings (`.claude/settings.json`, `.claude/settings.local.json`) so a repository cannot grant itself auto mode. Set it in `~/.claude/settings.json` instead. The `--permission-mode` CLI flag overrides this setting for a single session | `"acceptEdits"` |

| `disableBypassPermissionsMode` | Set to `"disable"` to prevent `bypassPermissions` mode from being activated. This disables the `--dangerously-skip-permissions` command-line flag. Typically placed in [managed settings](/en/permissions#managed-settings) to enforce organizational policy, but works from any scope | `"disable"` |

| `skipDangerousModePermissionPrompt` | Skip the confirmation prompt shown before entering bypass permissions mode via `--dangerously-skip-permissions` or `defaultMode: "bypassPermissions"`. Ignored when set in project settings (`.claude/settings.json`) to prevent untrusted repositories from auto-bypassing the prompt | `true` |

skills +2 -2

@@ -419,10 +419,10 @@ Skills and [subagents](/en/sub-agents) work together in two directions:

| :- | :- | :- | :- |

With `context: fork`, you write the task in your skill and pick an agent type to execute it. For the inverse (defining a custom subagent that uses skills as reference material), see [Subagents](/en/sub-agents#preload-skills-into-subagents).

With `context: fork`, you write the task in your skill and pick an agent type to execute it. The built-in Explore and Plan agents [skip CLAUDE.md and git status](/en/sub-agents#what-loads-at-startup) to keep their context small, so a forked skill using `agent: Explore` sees only the SKILL.md content and the agent's own system prompt. For the inverse, where you define a custom subagent that uses skills as reference material, see [Subagents](/en/sub-agents#preload-skills-into-subagents).

#### Example: Research skill using Explore agent

sub-agents +31 -1

サブエージェントの挙動や設定に関する説明が拡充されました。

@@ -36,6 +36,8 @@ Claude Code includes several built-in subagents like **Explore**, **Plan**, and

Claude Code includes built-in subagents that Claude automatically uses when appropriate. Each inherits the parent conversation's permissions with additional tool restrictions.

Explore and Plan skip your CLAUDE.md files and the parent session's git status to keep research fast and inexpensive. Every other built-in and [custom subagent](#configure-subagents) loads both. For the full breakdown of what reaches a subagent, see [what loads at startup](#what-loads-at-startup).

A fast, read-only agent optimized for searching and analyzing codebases.

- **Model**: Haiku (fast, low-latency)

@@ -605,7 +607,19 @@ The subagent's system prompt replaces the default Claude Code system prompt enti

This works with built-in and custom subagents, and the choice persists when you resume the session.

For a plugin-provided subagent, pass the scoped name: `claude --agent <plugin-name>:<agent-name>`. If the plugin places the agent in a subfolder of its `agents/` directory, include the subfolder in the scoped name, for example `claude --agent my-plugin:review:security`.

For a plugin-provided subagent, you can pass just the agent name and Claude Code will find it:

```bash

claude --agent security-reviewer

```

If multiple plugins provide agents with the same name, pass the scoped name to disambiguate:

```bash

claude --agent my-plugin:security-reviewer

```

If the plugin places the agent in a subfolder of its `agents/` directory, include the subfolder in the scoped name, for example `claude --agent my-plugin:review:security`.

To make it the default for every session in a project, set `agent` in `.claude/settings.json`:

@@ -690,6 +704,22 @@ Subagents cannot spawn other subagents. If your workflow requires nested delegat

### Manage subagent context

#### What loads at startup

Each subagent starts with a fresh, isolated context window. It does not see your conversation history, the skills you've already invoked, or the files Claude has already read. Claude composes a delegation message that summarizes the task, and the subagent works from there. The exception is a [fork](#fork-the-current-conversation), which inherits the parent conversation instead of starting fresh.

A non-fork subagent's initial context contains:

- **System prompt**: the agent's own prompt plus environment details that Claude Code appends, not the full Claude Code system prompt. Custom subagents define theirs in the [markdown body](#write-subagent-files) or `prompt` field. Built-in agents have predefined prompts.

- **Task message**: the delegation prompt Claude writes when it hands off the work.

- **CLAUDE.md and memory**: every level of the [memory hierarchy](/en/memory#how-claude-md-files-load) the main conversation loads, including `~/.claude/CLAUDE.md`, project rules, `CLAUDE.local.md`, and managed policy files. The built-in Explore and Plan agents skip this.

- **Git status**: a snapshot taken at the start of the parent session. Absent when the working directory isn't a Git repository or when [`includeGitInstructions`](/en/settings#available-settings) is `false`. Explore and Plan skip it regardless.

- **Preloaded skills**: full content of any skill named in the agent's [`skills` field](#preload-skills-into-subagents). Built-in agents don't preload skills.

Explore and Plan are the only subagents that omit CLAUDE.md and git status. There is no frontmatter field or per-agent setting to change which agents skip them.

The main conversation reads Explore and Plan results with full CLAUDE.md context, so most rules don't need to reach the subagent itself. If a rule must, such as "ignore the `vendor/` directory," restate it in the prompt you give Claude when delegating.

#### Resume subagents

Each subagent invocation creates a new instance with fresh context. To continue an existing subagent's work instead of starting over, ask Claude to resume it.

tools-reference +2 -1

@@ -46,8 +46,9 @@ To add custom tools, connect an [MCP server](/en/mcp). To extend Claude with reu

| `TaskUpdate` | Updates task status, dependencies, details, or deletes tasks | No |

| `TeamCreate` | Creates an [agent team](/en/agent-teams) with multiple teammates. Only available when `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set | No |

| `TeamDelete` | Disbands an agent team and cleans up teammate processes. Only available when `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set | No |

| `TodoWrite` | Manages the session task checklist. Deprecated in favor of `TaskCreate`, `TaskGet`, `TaskList`, and `TaskUpdate`. Interactive sessions already use the Task tools by default. When you run `claude -p` or use the [Agent SDK](/en/agent-sdk/overview), `TodoWrite` is still the default. Set `CLAUDE_CODE_ENABLE_TASKS=1` to switch those to the Task tools before `TodoWrite` is removed | No |

| `TodoWrite` | Manages the session task checklist. Disabled by default as of v2.1.142 in favor of `TaskCreate`, `TaskGet`, `TaskList`, and `TaskUpdate`. Set `CLAUDE_CODE_ENABLE_TASKS=0` to re-enable | No |

| `ToolSearch` | Searches for and loads deferred tools when [tool search](/en/mcp#scale-with-mcp-tool-search) is enabled | No |

| `WaitForMcpServers` | Waits for one or more [MCP servers](/en/mcp) that are still connecting in the background, so a request can use their tools without restarting the session. Claude calls it when a needed server is not connected yet. Only appears when [tool search](/en/mcp#scale-with-mcp-tool-search) is disabled, since `ToolSearch` handles the wait when it's enabled | No |

| `WebFetch` | Fetches content from a specified URL. See [WebFetch tool behavior](#webfetch-tool-behavior) | Yes |

| `WebSearch` | Performs web searches. See [WebSearch tool behavior](#websearch-tool-behavior) | Yes |

| `Write` | Creates or overwrites files. See [Write tool behavior](#write-tool-behavior) | Yes |

ultrareview +8 -8

Ultrareview機能の評価基準や説明文の微調整が行われました。

@@ -43,17 +43,17 @@ Before launching, Claude Code shows a confirmation dialog with the review scope

## Pricing and free runs

Ultrareview is a premium feature that bills against extra usage rather than your plan's included usage.

Ultrareview is a premium feature that bills against usage credits rather than your plan's included usage.

| Plan | Included free runs | After free runs |

| - | - | - |

| Pro | 3 free runs | billed as [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Max | 3 free runs | billed as [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Team and Enterprise | none | billed as [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Pro | 3 free runs | billed as [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Max | 3 free runs | billed as [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

| Team and Enterprise | none | billed as [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

Pro and Max subscribers receive three free ultrareview runs to try the feature. These three runs are a one-time allotment per account and do not refresh. After you use all three, or after the free run period ends, each review is billed to extra usage and typically costs $5 to $20 depending on the size of the change. A run counts once the remote session starts, so a review that you stop early or that fails to complete still uses a free run. For a paid review, extra usage is billed only for the portion that ran.

Pro and Max subscribers receive three free ultrareview runs to try the feature. These three runs are a one-time allotment per account and do not refresh. After you use all three, or after the free run period ends, each review is billed to usage credits and typically costs $5 to $20 depending on the size of the change. A run counts once the remote session starts, so a review that you stop early or that fails to complete still uses a free run. For a paid review, usage credits are billed only for the portion that ran.

Because ultrareview always bills as extra usage outside the free runs, your account or organization must have extra usage enabled before you can launch a paid review. If extra usage is not enabled, Claude Code blocks the launch and links you to the billing settings where you can turn it on. You can also run `/extra-usage` to check or change your current setting.

Because ultrareview always bills as usage credits outside the free runs, your account or organization must have usage credits turned on before you can launch a paid review. If usage credits are not turned on, Claude Code blocks the launch and links you to the billing settings where you can turn them on. You can also run `/usage-credits` to check or change your current setting.

## Track a running review

@@ -80,7 +80,7 @@ Progress messages and the live session URL go to stderr so stdout stays parseabl

| `--json` | Print the raw `bugs.json` payload instead of the formatted findings |

| `--timeout <minutes>` | Maximum minutes to wait for the review to finish. Defaults to 30 |

Running `claude ultrareview` requires the same authentication and extra usage configuration as `/ultrareview`. The subcommand exits with code 0 when the review completes with or without findings, code 1 when the review fails to launch, the remote session errors, or the timeout elapses, and code 130 when interrupted with Ctrl-C. The remote review keeps running if you interrupt the subcommand; follow the session URL printed to stderr to watch it in the browser.

Running `claude ultrareview` requires the same authentication and usage credit configuration as `/ultrareview`. The subcommand exits with code 0 when the review completes with or without findings, code 1 when the review fails to launch, the remote session errors, or the timeout elapses, and code 130 when interrupted with Ctrl-C. The remote review keeps running if you interrupt the subcommand; follow the session URL printed to stderr to watch it in the browser.

For automatic reviews on GitHub pull requests, [Code Review](/en/code-review) integrates with your repository directly and posts findings as inline PR comments without a CLI step.

@@ -93,7 +93,7 @@ Both commands review code, but they target different stages of your workflow.

| Runs | locally in your session | remotely in a cloud sandbox |

| Depth | single-pass review | multi-agent fleet with independent verification |

| Duration | seconds to a few minutes | roughly 5 to 10 minutes |

| Cost | counts toward normal usage | free runs, then roughly $5 to $20 per review as extra usage |

| Cost | counts toward normal usage | free runs, then roughly $5 to $20 per review as usage credits |

| Best for | quick feedback while iterating | pre-merge confidence on substantial changes |

Use `/review` for fast feedback as you work. Use `/ultrareview` before merging a substantial change when you want a deeper pass that catches issues a single review might miss.

vs-code +2 -0

@@ -390,6 +390,8 @@ When the extension is active, it runs a local MCP server that the CLI connects t

The server is named `ide` and is hidden from `/mcp` because there's nothing to configure. If your organization uses a `PreToolUse` hook to allowlist MCP tools, though, you'll need to know it exists.

**Selection and open-file context.** While connected, the CLI includes your current editor selection and the path of the active file as context on each prompt you send. The transcript shows a `⧉ Selected N lines from <file>` line when this happens. To exclude a sensitive file such as `.env`, add a [`Read` deny rule](/en/permissions#read-and-edit) for its path. A matching deny rule prevents both the selected text and the open-file notice for that file from reaching Claude.

**Transport and authentication.** The server binds to `127.0.0.1` on a random high port and is not reachable from other machines. Each extension activation generates a fresh random auth token that the CLI must present to connect. The token is written to a lock file under `~/.claude/ide/` with `0600` permissions in a `0700` directory, so only the user running VS Code can read it.

**Tools exposed to the model.** The server hosts a dozen tools, but only two are visible to the model. The rest are internal RPC the CLI uses for its own UI — opening diffs, reading selections, saving files — and are filtered out before the tool list reaches Claude.