claude 命令手册

➜ claude --help Usage: claude [options] [command] [prompt]

Claude Code - starts an interactive session by default, use -p/--print for non-interactive output

Arguments: prompt Your prompt

Options: --add-dir Additional directories to allow tool access to --agent Agent for the current session. Overrides the 'agent' setting. --agents JSON object defining custom agents (e.g. '{"reviewer": {"description": "Reviews code", "prompt": "You are a code reviewer"}}') --allow-dangerously-skip-permissions Enable bypassing all permission checks as an option, without it being enabled by default. Recommended only for sandboxes with no internet access. --allowedTools, --allowed-tools Comma or space-separated list of tool names to allow (e.g. "Bash(git ) Edit") --append-system-prompt Append a system prompt to the default system prompt --autocompact Auto-compact window size (auto, or 100k–1M tokens) --ax-screen-reader Render screen-reader friendly output (flat text, no decorative borders or animations). --bg, --background Start the session as a background agent and return immediately (manage with claude agents) --bare Minimal mode: skip hooks, LSP, plugin sync, attribution, auto-memory, background prefetches, keychain reads, and CLAUDE.md auto-discovery. Sets CLAUDE_CODE_SIMPLE=1. Anthropic auth is strictly ANTHROPIC_API_KEY or apiKeyHelper via --settings (OAuth and keychain are never read). 3P providers (Bedrock/Vertex/Foundry) use their own credentials. Skills still resolve via /skill-name. Explicitly provide context via: --system-prompt[-file], --append-system-prompt[-file], --add-dir (CLAUDE.md dirs), --mcp-config, --settings, --agents, --plugin-dir. --betas Beta headers to include in API requests (API key users only) --brief Enable SendUserMessage tool for agent-to-user communication --chrome Enable Claude in Chrome integration --cloud [description|session_id|url] Create a cloud session with the given description, or attach to an existing one by session ID or claude.ai/code URL -c, --continue Continue the most recent conversation in the current directory --dangerously-skip-permissions Bypass all permission checks. Recommended only for sandboxes with no internet access. -d, --debug [filter] Enable debug mode with optional category filtering (e.g., "api,hooks" or "!1p,!file") --debug-file Write debug logs to a specific file path (implicitly enables debug mode) --disable-slash-commands Disable all skills --disallowedTools, --disallowed-tools Comma or space-separated list of tool names to deny (e.g. "Bash(git ) Edit") --effort Effort level for the current session (low, medium, high, xhigh, max) --environment Create a new cloud session that runs on the given self-hosted environment (ccpool_...). --exclude-dynamic-system-prompt-sections Move per-machine sections (cwd, env info, memory paths, git status) from the system prompt into the first user message. Improves cross-user prompt-cache reuse. Only applies with the default system prompt (ignored with --system-prompt). (default: false) --fallback-model Enable automatic fallback to specified model(s) when the default model is overloaded or not available. Accepts a comma-separated list to try each in order. Re-tries the primary at the start of each user turn. (only works with --print) --file File resources to download at startup. Format: file_id:relative_path (e.g., --file file_abc:doc.txt file_def:img.png) --fork-session When resuming, create a new session ID instead of reusing the original (use with --resume or --continue) --forward-subagent-text Forward subagent text and thinking blocks as assistant/user messages with parent_tool_use_id set (only works with --print and --output-format=stream-json) --from-pr [value] Resume a session linked to a PR by PR number/URL, or open interactive picker with optional search term -h, --help Display help for command --ide Automatically connect to IDE on startup if exactly one valid IDE is available --include-hook-events Include all hook lifecycle events in the output stream (only works with --output-format=stream-json) --include-partial-messages Include partial message chunks as they arrive (only works with --print and --output-format=stream-json) --input-format Input format (only works with --print): "text" (default), or "stream-json" (realtime streaming input) (choices: "text", "stream-json") --json-schema JSON Schema for structured output validation. Example: {"type":"object","properties":{"name":{"type":"string"}},"required":["name"]} --max-budget-usd Maximum dollar amount to spend on API calls (only works with --print) --mcp-config Load MCP servers from JSON files or strings (space-separated) --model Model for the current session. Provide an alias for the latest model (e.g. 'fable', 'opus', or 'sonnet') or a model's full name (e.g. 'claude-fable-5'). -n, --name Set a display name for this session (shown in the prompt box, /resume picker, and terminal title) --no-chrome Disable Claude in Chrome integration --no-session-persistence Disable session persistence - sessions will not be saved to disk and cannot be resumed (only works with --print) --output-format Output format (only works with --print): "text" (default), "json" (single result), or "stream-json" (realtime streaming) (choices: "text", "json", "stream-json") --permission-mode Permission mode to use for the session (choices: "acceptEdits", "auto", "bypassPermissions", "manual", "dontAsk", "plan") --plugin-dir Load a plugin from a directory or .zip for this session only (repeatable: --plugin-dir A --plugin-dir B.zip) (default: []) --plugin-url Fetch a plugin .zip from a URL for this session only (repeatable: --plugin-url A --plugin-url B) (default: []) -p, --print Print response and exit (useful for pipes). Note: The workspace trust dialog is skipped when Claude is run in non-interactive mode (via -p, or when stdout is not a TTY, e.g. piped or redirected output). Only use this in directories you trust. Settings files that fail validation are silently ignored in this mode (no error dialog is shown). --prompt-suggestions [value] Enable prompt suggestions. In print/SDK mode, emits a prompt_suggestion message after each turn with a predicted next user prompt (choices: "true", "false", "1", "0", "yes", "no", "on", "off", preset: "true") --remote-control [name] Start an interactive session with Remote Control enabled (optionally named) --remote-control-session-name-prefix Prefix for auto-generated Remote Control session names (default: hostname) --replay-user-messages Re-emit user messages from stdin back on stdout for acknowledgment (only works with --input-format=stream-json and --output-format=stream-json) -r, --resume [value] Resume a conversation by session ID, or open interactive picker with optional search term --safe-mode Start with all customizations (CLAUDE.md, skills, plugins, hooks, MCP servers, custom commands and agents, output styles, workflows, custom themes, keybindings, and more) disabled — useful for troubleshooting a broken configuration. Admin-managed (policy) settings still apply. Auth, model selection, built-in tools, and permissions work normally. Sets CLAUDE_CODE_SAFE_MODE=1. --session-id Use a specific session ID for the conversation (must be a valid UUID) --setting-sources Comma-separated list of setting sources to load (user, project, local). --settings Path to a settings JSON file or a JSON string to load additional settings from --strict-mcp-config Only use MCP servers from --mcp-config, ignoring all other MCP configurations --system-prompt System prompt to use for the session --teleport [session] Resume a teleport session, optionally specify session ID --tmux Create a tmux session for the worktree (requires --worktree). Uses iTerm2 native panes when available; use --tmux=classic for traditional tmux. --tools Specify the list of available tools from the built-in set. Use "" to disable all tools, "default" to use all tools, or specify tool names (e.g. "Bash,Edit,Read"). --verbose Override verbose mode setting from config -v, --version Output the version number -w, --worktree [name] Create a new git worktree for this session (optionally specify a name)

Commands: agents [options] Manage background agents auth Manage authentication auto-mode Inspect or reset auto mode classifier configuration doctor Check the health of your Claude Code installation. Reads settings files in the current directory without a trust prompt. For a full checkup that can also fix issues, run /doctor in a session. gateway [options] Run the enterprise auth/telemetry gateway import [options] [source] Import config from another AI coding agent into Claude Code install [options] [target] Install Claude Code native build. Use [target] to specify version (stable, latest, or specific version) mcp Configure and manage MCP servers plugin|plugins Manage Claude Code plugins project Manage Claude Code project state setup-token Set up a long-lived authentication token (requires Claude subscription) ultrareview [options] [target] Run a cloud-hosted multi-agent code review of the current branch (or a PR number / base branch) and print the findings update|upgrade Check for updates and install if available