Subcommands32 subcommands
claude agents
Manage background agents
claude auth
Manage authentication
claude auto-mode
Inspect auto mode classifier configuration
claude doctor
Check the health of your Claude Code auto-updater
claude install
Install Claude Code native build
claude mcp
Configure and manage MCP servers
claude mcp add
Add an MCP server to Claude Code
claude mcp add-from-claude-desktop
Import MCP servers from Claude Desktop (Mac/WSL)
claude mcp add-json
Add an MCP server with a JSON string
claude mcp get
Get details about an MCP server
claude mcp list
List configured MCP servers
claude mcp remove
Remove an MCP server
claude mcp reset-project-choices
Reset all approved/rejected project-scoped servers
claude mcp serve
Start the Claude Code MCP server
claude mcp help
Display help for command
claude plugin
Manage Claude Code plugins
claude plugin details
Show a plugin's component inventory and token cost
claude plugin disable
Disable an enabled plugin
claude plugin enable
Enable a disabled plugin
claude plugin install
Install a plugin from available marketplaces
claude plugin list
List installed plugins
claude plugin marketplace
Manage Claude Code marketplaces
claude plugin prune
Remove auto-installed dependencies no longer needed
claude plugin tag
Create a {name}--v{version} git tag for a plugin release
claude plugin uninstall
Uninstall an installed plugin
claude plugin update
Update a plugin to the latest version
claude plugin validate
Validate a plugin or marketplace manifest
claude plugin help
Display help for command
claude project
Manage Claude Code project state
claude setup-token
Set up a long-lived authentication token (requires Claude subscription)
claude ultrareview
Run a cloud-hosted multi-agent code review of the current branch (or PR / base branch)
claude update
Check for updates and install if available
OptionsOn claude itself
--add-dir
Additional directories to allow tool access to <directories>
--agent
Agent for the current session (overrides 'agent' setting) <agent>
--agents
JSON object defining custom agents <json>
--allow-dangerously-skip-permissions
Make bypass-permissions mode available (without defaulting to it)
--allowedTools--allowed-tools
Comma/space-separated list of tool names to allow (e.g. "Bash(git *) Edit") <tools>
--append-system-prompt
Append a system prompt to the default system prompt <prompt>
--bare
Minimal mode: skip hooks, LSP, plugins, attribution, auto-memory, etc.
--betas
Beta headers to include in API requests (API key users only) <betas>
--brief
Enable SendUserMessage tool for agent-to-user communication
--chrome
Enable Claude in Chrome integration
-c--continue
Continue the most recent conversation in the current directory
--dangerously-skip-permissions
Bypass all permission checks
-d--debug
Enable debug mode with optional category filtering (e.g. "api,hooks") <filter>
--debug-file
Write debug logs to a specific file path (implicitly enables debug mode) <path>
--disable-slash-commands
Disable all skills
--disallowedTools--disallowed-tools
Comma/space-separated list of tool names to deny (e.g. "Bash(git *) Edit") <tools>
--effort
Effort level for the current session <level>
--exclude-dynamic-system-prompt-sections
Move per-machine sections out of the system prompt for cache reuse
--fallback-model
Enable automatic fallback to specified model when default is overloaded <model>
--file
File resources to download at startup (format: file_id:relative_path) <specs>
--fork-session
When resuming, create a new session ID instead of reusing the original
--from-pr
Resume a session linked to a PR by PR number/URL (or interactive picker) <value>
-h--help
Display help for command
--ide
Automatically connect to IDE on startup if exactly one is available
--include-hook-events
Include all hook lifecycle events in the output stream
--include-partial-messages
Include partial message chunks as they arrive
--input-format
Input format (only with --print) <format>
--json-schema
JSON Schema for structured output validation <schema>
--max-budget-usd
Maximum dollar amount to spend on API calls (only with --print) <amount>
--mcp-config
Load MCP servers from JSON files or strings (space-separated) <configs>
--model
Model for the current session (alias like 'sonnet'/'opus' or full name) <model>
-n--name
Set a display name for this session <name>
--no-chrome
Disable Claude in Chrome integration
--no-session-persistence
Disable session persistence (only with --print)
--output-format
Output format (only with --print) <format>
--permission-mode
Permission mode for the session <mode>
--plugin-dir
Load a plugin from a directory or .zip for this session only <path>
--plugin-url
Fetch a plugin .zip from a URL for this session only <url>
-p--print
Print response and exit (useful for pipes)
--remote-control
Start an interactive session with Remote Control enabled <name>
--remote-control-session-name-prefix
Prefix for auto-generated Remote Control session names <prefix>
--replay-user-messages
Re-emit user messages from stdin back on stdout for acknowledgment
-r--resume
Resume a conversation by session ID, or open interactive picker <value>
--session-id
Use a specific session ID (must be a valid UUID) <uuid>
--setting-sources
Comma-separated list of setting sources (user, project, local) <sources>
--settings
Path to a settings JSON file, or a JSON string <file-or-json>
--strict-mcp-config
Only use MCP servers from --mcp-config
--system-prompt
System prompt to use for the session <prompt>
--tmux
Create a tmux session for the worktree (requires --worktree)
--tools
Specify the built-in tools to enable (e.g. "Bash,Edit,Read", "default", or "") <tools>
--verbose
Override verbose mode setting from config
-v--version
Output the version number
-w--worktree
Create a new git worktree for this session <name>
