Claude Code CLI reference

Add a working directory for file access during the current session.

Enable or disable the advisor tool, which consults a second model for guidance at key moments during a task.

fable, opus, sonnet, or a full model ID

Print a reminder to ask Claude to create or manage subagents, or to edit .claude/agents/ or ~/.claude/agents/ directly.

Skill. Load the reference for the runtime capabilities a published artifact can use.

Skill. Load diagramming guidance for Claude to follow in artifacts.

List the artifacts you own or that are shared with you.

Draft autoMode.environment entries from your project and recent sessions.

Set the auto-compact window: how full the context window gets before Claude Code compacts.

Spawn a cloud session that watches the current branch's PR and pushes fixes.

Detach the current session to run as a background agent and free this terminal.

Skill. Orchestrate large-scale changes across a codebase in parallel.

Create a branch of the current conversation at this point.

Ask a side question about the current session without adding to the conversation history.

Report a bug or share your conversation.

Move this session to a new working directory, keeping the conversation.

Configure Claude in Chrome settings

Skill. Load Claude API and Managed Agents reference material for your project.

Skill. Have Claude carry out a task in your browser, such as testing a page.

Start a new conversation with empty context.

Aliases: /reset, /new

Skill. Review the current diff, or a PR number, branch, or path you name.

Set the prompt bar color for the current session.

Free up context by summarizing the conversation so far.

Open the Settings interface to adjust theme, model, output style, and other preferences.

Visualize current context usage as a colored grid.

Copy the last assistant response to clipboard.

Alias for /usage

Skill. Design guidance for charts, graphs, and dashboards.

Skill. Enable debug logging for the current session and troubleshoot issues.

Skill. Draft UI mockups, screen flows, landing pages, or posters as designs.

Authorize design-system access for /design-sync with your claude.ai account.

Skill. Convert your repo's React design system and upload it to claude.ai.

Continue the current session in the Claude Code Desktop app.

Review the changes in your working tree, including the edits Claude made.

Skill. Run a setup checkup that diagnoses installation, settings, and configuration issues.

Set the effort level: low to xhigh, max, or auto.

Exit the CLI. In an attached background session, this detaches.

Export the current conversation as plain text.

Toggle fast mode on or off.

Send product feedback about Claude Code.

Skill. Scan your transcripts for common read-only Bash and MCP tool calls and add an allowlist.

Toggle the focus view, which shows only your last prompt and a one-line summary.

Copy the current conversation into a new background session.

Set a goal: Claude keeps working across turns until the condition is met.

Write a JavaScript heap snapshot and a memory breakdown to disk.

Show help and available commands

View hook configurations

Manage IDE integrations and show status

Bring configuration from OpenAI Codex, Google Gemini CLI, or Cursor into Claude Code.

Initialize project with a CLAUDE.md guide.

Generate an HTML report analyzing your recent sessions.

Install the Claude GitHub App for a repository.

Install the Claude Slack app. Opens a browser to complete the OAuth flow.

Open your keyboard shortcuts file

List the subagents, agent team teammates, and other Claude Code sessions.

Sign in to your Anthropic account

Sign out from your Anthropic account

Skill. Run a prompt repeatedly while the session stays open.

Manage MCP server connections and OAuth authentication.

Edit CLAUDE.md files, enable or disable auto memory, and view auto memory entries.

Show QR code to download the Claude mobile app.

Aliases: /ios, /android

Switch the AI model and save it as your default for new sessions.

List output styles or switch to one.

Share a free week of Claude Code with friends.

Manage allow, ask, and deny rules for tool permissions.

Enter plan mode directly from the prompt.

Manage Claude Code plugins. Run with no argument to open the plugin manager.

Load the reference Claude works from to write a mod.

Discover Claude Code features through quick interactive lessons.

Removed in v2.1.91. Ask Claude directly to view pull request comments instead.

View and update your privacy settings.

Open Claude FM lo-fi radio in your browser.

Show ways to keep working when a claude.ai usage limit blocks a request.

Generate a one-line summary of the current session on demand.

View the changelog in an interactive version picker.

Reload all active plugins to apply pending changes without restarting.

Re-scan skill and command directories so skills added or changed on disk load.

Make this session available for Remote Control from claude.ai.

Choose the default cloud environment for cloud sessions you start.

Rename the current session and show the name on the prompt bar.

Resume a conversation by ID or name, or open the session picker.

Alias of /code-review.

Rewind the conversation and/or code to a previous point, or summarize from there.

Aliases: /checkpoint, /undo

Skill. Launch and drive your project's app to see a change working.

Skill. Teach /run and /verify how to build, launch, and drive your project.

Toggle sandbox mode. Available on supported platforms only

Create, update, list, or run routines, which execute in the cloud.

Adjust mouse wheel scroll speed interactively.

Analyze the changes on your current branch for security vulnerabilities.

Configure Amazon Bedrock authentication, region, and model pins.

Configure Google Cloud's Agent Platform authentication, project, and region.

Skill. Review the changed code for cleanup opportunities and apply fixes.

Show what each of your skills costs in context and how often it gets used.

List available skills. Type to filter the list by name or description.

Skill. Make a new presentation as a Claude Slides artifact.

Alias for /usage. Opens on the Stats tab

Open the Settings interface on the Status tab, showing version, model, account, and connectivity.

Configure Claude Code's status line.

Order Claude Code stickers

Stop the background session you're attached to.

Spawn a forked subagent: a background subagent that inherits the full conversation.

View and manage background work in the current session.

Generate a team onboarding guide from your Claude Code usage history.

Pull a cloud session into this terminal.

Install a Shift+Enter keybinding for newlines in VS Code, Cursor, and other terminals.

Change the color theme.

Set the terminal UI renderer and relaunch into it.

Removed. Use plan mode instead.

Run a deep, multi-agent code review in a cloud sandbox.

Skill. Describe a settings change, such as allowing a command, and Claude applies it.

Open the upgrade page in your browser to switch to a higher plan tier.

Show session cost, plan usage limits, and activity stats.

Configure usage credits, or request them from your admin.

Skill. Confirm a code change does what it should by building and running your project.

Removed in v2.1.92. Toggle between Vim and Normal editing modes through /config instead.

Toggle voice dictation, or enable it in a specific mode.

Connect your GitHub account for cloud sessions using your local gh credentials.

Skill. Load the reference for writing dynamic workflow scripts.

Open the workflow progress view to watch, pause, resume, or save workflows.

Add additional working directories for Claude to read and edit files.

Enable the server-side advisor tool for this session with a model alias or full model ID.

fable, opus, sonnet, or a full model ID

Specify an agent for the current session (overrides the agent setting)

Define custom subagents dynamically via JSON.

Add bypassPermissions to the Shift+Tab mode cycle without starting in it.

Tools that execute without prompting for permission, apart from reads from network paths.

Append custom text to the end of every subagent's system prompt. Only applies in non-interactive mode with -p.

Load text from a file and append it to subagent system prompts.

Append custom text to the end of the default system prompt

Load additional system prompt text from a file and append to the default prompt

Set the auto-compact window for this session without changing your saved settings.

Render screen-reader friendly output: flat text without decorative borders or animations.

Minimal mode: skip auto-discovery of hooks, skills, custom commands, subagents, plugins, MCP servers, auto memory, and CLAUDE.md so scripted calls start faster.

Beta headers to include in API requests (API key users only)

Start the session as a background agent and return immediately.

(Research preview) MCP servers whose channel notifications Claude should listen for in this session.

Space-separated plugin:<name>@<marketplace> entries

Enable Chrome browser integration for web automation and testing

With a task description, create a new cloud session. With a session ID or claude.ai/code URL, queue a message into that session instead, with -p.

Load the most recent conversation in the current directory.

Enable channels that are not on the approved allowlist, for local development.

plugin:<name>@<marketplace> and server:<name> entries

Skip permission prompts. Equivalent to --permission-mode bypassPermissions.

Enable debug mode with optional category filtering, such as --debug='mcp,startup' or --debug='!mcp'.

Write debug logs to a specific file path. Implicitly enables debug mode.

Open the Claude Desktop app on the current directory and exit without starting a session in the terminal.

Disable all skills and commands for this session

Deny rules. A bare tool name removes the matching tools from Claude's context; a scoped rule denies only matching calls.

Set the effort level for the current session. Available levels depend on the model.

low, medium, high, xhigh, max, or ultracode

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

Create a new cloud session that runs on the self-hosted environment with the given ID. Environment IDs start with ccpool_.

Move per-user context, such as the auto memory location, out of the system prompt and into the first user message.

Run a shell command as a PTY-backed background job instead of starting a Claude session. Use with --bg.

Enable automatic fallback to the specified model(s) when the primary model is overloaded or not available.

Comma-separated list tried in order

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

Emit subagent text and thinking blocks in the output stream as assistant and user messages with parent_tool_use_id set.

Open the session picker filtered to sessions linked to a specific pull request.

PR number, GitHub/GitHub Enterprise PR URL, GitLab MR URL, or Bitbucket PR URL

Automatically connect to IDE on startup if exactly one valid IDE is available

Run Setup hooks with the init matcher before the session (print mode only)

Run Setup and SessionStart hooks, then exit without starting a conversation

Include hook lifecycle events in the output stream.

Include partial streaming events in output. Requires --print and --output-format stream-json.

Specify input format for print mode.

text, stream-json

Get validated JSON output matching a JSON Schema after the agent completes its workflow (print mode only).

Run Setup hooks with the maintenance matcher before the session (print mode only)

Stop the run once estimated spend on API calls reaches this amount (print mode only).

Limit the number of agentic turns (print mode only). Exits with an error when the limit is reached.

No limit by default

Load MCP servers from JSON files or strings (space-separated).

Sets the model for the current session with a model alias such as sonnet, opus, haiku, or fable, or a model's full name.

Set a display name for the session, shown in /resume and the terminal title.

Disable Chrome browser integration for this session

Disable session persistence so sessions are not saved to disk and cannot be resumed. Print mode only.

Specify output format for print mode.

text, json, stream-json

Begin in a specified permission mode.

default, acceptEdits, plan, auto, dontAsk, bypassPermissions, or manual (alias for default)

Specify an MCP tool to handle permission prompts in non-interactive mode.

Set who answers permission prompts in print mode.

host (default) or none

Load a plugin from a directory or .zip archive, or several from a folder of plugins, for this session only.

Fetch a plugin .zip archive from a URL for this session only.

Print response without interactive mode.

Emit a prompt_suggestion message with a predicted next user prompt after each turn that generates one.

With --environment, base the new session's checkout on a named ref instead of local HEAD

Deprecated alias for --cloud, including the existing-session form

Start an interactive session with Remote Control enabled so you can also control it from claude.ai or the Claude app.

Prefix for auto-generated Remote Control session names when no explicit name is set.

Defaults to your machine's hostname

Re-emit user messages from stdin back on stdout for acknowledgment.

Start in restricted mode, for evaluation harnesses where Claude Code must not run commands or read the machine's user and project settings.

Resume a specific session by ID or name, or show an interactive picker to choose a session.

Start with all customizations disabled to troubleshoot a broken configuration.

Use a specific session ID for the conversation (must be a valid UUID)

Comma-separated list of setting sources to load.

user, project, local

Path to a settings JSON file or an inline JSON string. Values override the same keys in settings.json files for this session.

Only use MCP servers from --mcp-config, ignoring all other MCP configurations.

Replace the entire system prompt with custom text

Load system prompt from a file, replacing the default prompt

Pass off to rebuild the system prompt on every request instead of reusing the prompt recorded on the conversation's first request.

on (default) or off

Resume a cloud session in your local terminal

Set how agent team teammates display. Overrides the teammateMode setting for this session.

in-process (default), auto, tmux, or iterm2

Create a tmux session for the worktree. Requires --worktree.

--tmux=classic for traditional tmux

Restrict which built-in tools Claude can use.

"" to disable all, "default", or tool names like "Bash,Edit,Read"

Enable verbose logging, shows full turn-by-turn output.

Output the version number

Start Claude in an isolated git worktree at <repo>/.claude/worktrees/<name>.

Update to latest version

Start the self-hosted Claude apps gateway server, for administrators deploying SSO and policy in front of Claude Code. Requires --config pointing at a gateway.yaml.

Install or reinstall the native binary.

A version like 2.1.118, or stable or latest

Sign in to your Anthropic account.

--email, --sso, --console

Log out from your Anthropic account

Show authentication status as JSON. Exits with code 0 if logged in, 1 if not.

--text for human-readable output

Open agent view to monitor and dispatch parallel background sessions.

--cwd <path>, --json, --all

Attach to a background session in this terminal.

Print the built-in auto mode classifier rules as JSON.

--label <prefix>

Restore the default auto mode configuration by removing the autoMode section from your user settings file.

-y, --yes

Follow the background-session supervisor's log file, ~/.claude/daemon.log.

Run the background-session supervisor in the foreground of this terminal, printing its log.

Print the background-session supervisor's state, version, socket directory, and worker count. Exits 1 if the supervisor isn't running.

Stop the background-session supervisor and the sessions it hosts.

--keep-workers

Print read-only installation and settings diagnostics from the terminal without starting a session.

Start an interactive session that runs /import to bring configuration from other coding agents into Claude Code.

--dry-run, --yes

Print recent output from a background session.

Configure Model Context Protocol (MCP) servers

Run a configured MCP server's OAuth flow without opening the interactive /mcp panel.

--no-browser

Clear stored OAuth credentials for an MCP server

Manage Claude Code plugins. Alias: claude plugins.

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.

--dry-run, -y/--yes, -i/--interactive, --all

Start a Remote Control server to control Claude Code from Claude.ai or the Claude app. Runs in server mode.

Restart a background session, running or stopped, with its conversation intact.

--all

Remove a background session from the list.

--discard-unpushed <commit>@<worktree-id>, --force-remove-worktree <worktree-id>

Start a runner process that registers this machine or container with a self-hosted environment and hosts Claude Code cloud sessions.

setup, doctor, orchestrator

Generate a long-lived OAuth token for CI and scripts. Requires a Claude subscription.

Stop a background session. Also accepts claude kill.

Run ultrareview non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure.

--json, --timeout <minutes> (default 45), --post, --no-post

Add an MCP server. For stdio servers, -- separates Claude's own options such as --transport, --env, and --scope from the server command.

--transport http|sse|stdio, --scope local|project|user, --env KEY=value, --header

Add an MCP server directly from a JSON configuration.

Import MCP servers already configured in Claude Desktop, then select which servers to import.

List all configured MCP servers.

Get details for a specific MCP server.

Remove an MCP server. Removing a remote server also deletes the OAuth tokens and client registration stored for it.

Start Claude Code itself as a stdio MCP server that other applications can connect to.

Reset the approval choices for project-scoped servers from .mcp.json files.

Scaffold a new plugin at ~/.claude/skills/<name>/.

--description <text>, --author <name>, --author-email <email>, --with <components...>, -f/--force

Install a plugin from one of your marketplaces.

-s/--scope user|project|local (default user), --config <key=value>, -y/--yes, --accept-command, --json, --marketplace

Remove an installed plugin from one scope.

-s/--scope, --keep-data, --prune, -y/--yes, --json

Enable a disabled plugin.

-s/--scope, --json

Disable a plugin without uninstalling it.

-a/--all, -s/--scope, --json

Update a plugin to the latest version its marketplace offers.

-s/--scope user|project|local|managed, -y/--yes, --accept-command, --json

List installed plugins with their version, scope, and status.

--json, --available, --data-size [plugin]

Show a plugin's component inventory and its projected token cost.

Show an installed plugin's userConfig options and which are set, or save new values.

--values-stdin, --json

Remove auto-installed dependencies that no installed plugin needs.

-s/--scope, --dry-run

Run a plugin's eval cases and report scored results.

--runs <n>, -j/--concurrency

Create an eval suite for the plugin in the current directory.

--bare, -i/--interactive

Create an annotated git tag named <name>--v<version> for a plugin.

--push, --dry-run, -f/--force

Run the tests for a mod, a plugin whose code registers event handlers.

Validate a plugin manifest, a marketplace manifest, or the skills in a directory.

--strict, --json

Add a marketplace from a GitHub repository, a git URL, a hosted URL, or a local path.

--scope <scope>, --sparse <paths...>, --claudeai, --json

List every marketplace you've added, with its source.

--json

Remove a marketplace's declaration from your settings.

--scope <scope>, --json

Interrupt, or clear input. Interrupts a running operation; with nothing running, the first press clears input and a second press exits.

Context: General controls

Stop all running background subagents in this session.

Context: General controls

Exit Claude Code session. The first press shows a confirmation hint and a second press within 800ms exits.

Context: General controls

Open in default text editor to edit your prompt or custom response.

Context: General controls

Redraw the screen, keeping input and conversation history.

Context: General controls

Toggle transcript viewer. Shows detailed tool usage and execution.

Context: General controls

Reverse search command history.

Context: General controls

Paste image from clipboard. Inserts an [Image #N] chip at the cursor.

Context: General controls

Change the model Claude Code starts with. Scope: Any file.

Type: string, a model alias or full model ID

Isolate Bash commands from your filesystem and network. Scope: Any file.

Type: object with enabled and related sandbox keys

Pick the interface color theme, built-in or custom. Scope: Any file.

Type: string; Default: "dark"

Start every session as a named subagent with its prompt, tools, and model. Scope: Any file.

Type: string, the name of a built-in or custom subagent

Set environment variables for every session and its subprocesses. Scope: Any file.

Type: object mapping variable names to values

Set allow, ask, and deny rules and the starting permission mode. Scope: Any file.

Type: object with allow, ask, deny and related keys

Run your own commands as hooks at points in Claude Code's lifecycle. Scope: Any file.

Type: object keyed by hook event

Configure how Claude Code creates git worktrees. Scope: Any file.

Type: object with baseRef and related keys

Override the API endpoint to route requests through a proxy or gateway.

Override the configuration directory.

Default: ~/.claude

Set to any non-empty value, such as 1, to opt out of telemetry.

Name of the model setting to use (see Model Configuration)

Timeout for API requests in milliseconds.

Default: 600000 (10 minutes)

Set to any non-empty value, such as 1, to disable nonessential traffic.

Set to false to turn off prompt suggestions.

Set to 1 to enable fullscreen rendering, a research preview.

Permissions, hooks, env vars, model defaults.

Scope: Project and global; committed to git

Shared project settings file. Affects everyone working in the folder that contains it.

Use it for: team permissions, hooks, plugins, and project environment variables

Enterprise-enforced settings that your own settings files and --settings values can't override, apart from narrow exceptions.

Location: System-level, varies by OS

Instructions loaded every session.

Scope: Project and global; committed to git

Your personal overrides, gitignored when Claude Code saves a setting to it.

Scope: Project only

Project local settings file. Affects you, in this one project only.

Use it for: personal overrides for one project

User settings file. Affects you, in every project on this machine.

Use it for: personal preferences such as theme, editor mode, default model

App state, OAuth, UI toggles, personal MCP servers.

Scope: Global only