Claude Code ships with over 100 slash commands organized across categories. Commands are invoked by typing / followed by the command name. Some commands accept arguments (shown in the argumentHint field).
Not all commands are available in every environment. Commands may be gated by auth type (claude.ai subscriber, Console API user), feature flags, platform, or internal-only restrictions. Use /help to see commands available in your current session.
Core
| Command | Description |
|---|---|
/help | Show help and available commands |
/clear | Clear conversation history |
/exit | Exit Claude Code |
/config | View and edit configuration |
/status | Show current session status |
/model | Set the AI model for Claude Code |
/theme | Change the terminal color theme |
/color | Set agent color |
/vim | Toggle vim keybinding mode |
/version | Show current version |
Session Management
| Command | Description |
|---|---|
/resume | Resume a previous conversation |
/session | Manage sessions |
/teleport | Teleport to a remote session |
/rewind | Rewind conversation to a previous state |
/share | Share the current conversation |
/compact | Compact conversation history to save tokens |
/rename | Rename the current session |
/context | View context window usage |
/summary | Generate a conversation summary |
Code & Git
| Command | Description |
|---|---|
/diff | Show file diffs |
/review | Request a code review |
/copy | Copy content to clipboard |
/export | Export conversation or code |
/branch | Create or switch git branches |
/tag | Tag a point in the conversation |
/commit | Create a git commit (internal) |
/commit-push-pr | Commit, push, and create a PR (internal) |
/pr_comments | View and respond to PR comments |
/release-notes | Generate release notes |
/security-review | Perform a security review |
AI & Planning
| Command | Description |
|---|---|
/plan | Enter plan mode for structured task planning |
/tasks | View and manage background tasks |
/effort | Set reasoning effort level |
/fast | Toggle fast mode |
/thinkback | Replay model thinking process |
/thinkback-play | Play back thinking in real time |
/passes | Configure multi-pass processing |
/advisor | Use advisor model for guidance |
/ultraplan | Launch ultra planning mode (internal) |
Tools & Extensions
| Command | Description |
|---|---|
/mcp | Manage MCP server connections |
/skills | Browse and manage skills |
/plugin | Manage plugins |
/hooks | Configure event hooks |
/files | Browse and manage tracked files |
/agents | View and manage agent definitions |
/reload-plugins | Reload plugin configurations |
/add-dir | Add a directory for CLAUDE.md loading |
/memory | View and edit memory/CLAUDE.md files |
/chrome | Toggle browser automation |
Settings & Permissions
| Command | Description |
|---|---|
/permissions | View and manage tool permissions |
/privacy-settings | Configure privacy and data sharing |
/keybindings | Customize keyboard shortcuts |
/output-style | Set output formatting style |
/sandbox-toggle | Toggle sandbox mode |
/rate-limit-options | Configure rate limit behavior |
/statusline | Customize status line display |
Communication & Connectivity
| Command | Description |
|---|---|
/voice | Toggle voice input mode (feature-gated) |
/bridge | Manage bridge connections (feature-gated) |
/ide | Connect to IDE extensions |
/desktop | Open in desktop app |
/mobile | Connect to mobile app |
/btw | Send a brief aside message |
/feedback | Send feedback to the team |
Diagnostics & Cost
| Command | Description |
|---|---|
/doctor | Run system health diagnostics |
/cost | Show session cost breakdown |
/usage | View API usage statistics |
/stats | Show session statistics |
/env | Display environment information (internal) |
/insights | Generate a report analyzing your sessions |
/ctx_viz | Visualize context window usage (internal) |
/extra-usage | View extended usage details |
Authentication
| Command | Description |
|---|---|
/login | Authenticate with the API |
/logout | Clear authentication credentials |
/oauth-refresh | Refresh OAuth tokens |
/install-github-app | Install the GitHub App integration |
/install-slack-app | Install the Slack App integration |
Setup & Onboarding
| Command | Description |
|---|---|
/init | Initialize Claude Code in a project |
/init-verifiers | Initialize verification tools (internal) |
/onboarding | Run the onboarding flow (internal) |
/terminal-setup | Configure terminal settings |
/upgrade | Upgrade Claude Code to the latest version |
/stickers | Manage sticker packs |
Feature-Gated Commands
These commands are conditionally available based on build-time feature flags or runtime gates:
| Command | Feature Gate | Description |
|---|---|---|
/voice | VOICE_MODE | Voice input and transcription |
/bridge | BRIDGE_MODE | Always-on bridge for remote control |
/remote-control | DAEMON + BRIDGE_MODE | Remote control server |
/brief | KAIROS or KAIROS_BRIEF | Toggle brief output mode |
/assistant | KAIROS | Assistant mode commands |
/proactive | PROACTIVE or KAIROS | Proactive suggestion mode |
/force-snip | HISTORY_SNIP | Force a history snip boundary |
/workflows | WORKFLOW_SCRIPTS | Manage workflow scripts |
/web | CCR_REMOTE_SETUP | Remote setup configuration |
/peers | UDS_INBOX | View peer agent connections |
/fork | FORK_SUBAGENT | Fork a sub-agent session |
/buddy | BUDDY | Companion/buddy features |
/torch | TORCH | Torch debugging tool |
/subscribe-pr | KAIROS_GITHUB_WEBHOOKS | Subscribe to PR webhooks |
Internal-Only Commands
These commands are restricted to Anthropic employees (USER_TYPE === 'ant'):
| Command | Description |
|---|---|
/backfill-sessions | Backfill session data |
/break-cache | Set a cache-breaking injection |
/bughunter | Run the bug hunter |
/good-claude | Send positive feedback |
/issue | File an internal issue |
/mock-limits | Simulate rate limits |
/bridge-kick | Force-disconnect bridge session |
/ant-trace | View OpenTelemetry trace |
/perf-issue | Report a performance issue |
/debug-tool-call | Debug a specific tool call |
/heapdump | Capture a heap dump |
/autofix-pr | Auto-fix a PR |
/agents-platform | Agents platform management |
Skill Commands
In addition to built-in commands, skills provide dynamic slash commands. Skills are loaded from:
.claude/skills/directory in the project or home directory- Plugins that register skill commands
- Bundled skills shipped with Claude Code
- Dynamic skills discovered during file operations (matched by
pathsglobs)
Skill commands use the prompt type and generate content that is sent to the model. They can specify execution context (inline or fork), register hooks, and declare file-path triggers.