C Claude Code Internals
EN | ES

Slash Commands

Claude Code registers ~100 slash commands in src/commands.ts. They span 5 categories: core user-facing, platform-restricted, hidden, feature-flag gated, and Anthropic-internal only.

~100 total commands 5 categories 3 command types
i Command types
Each command has a type: local (runs locally, no model call), local-jsx (renders an interactive React/Ink UI), or prompt (injects a prompt into the conversation and calls the model). Skills invoked via /skill-name are a fourth category handled separately by SkillTool.

Category 1: Core user commands (~45)

Always visible in /help and typeahead. Available in all environments.

Command Type Description
/clear reset, new local Wipes conversation history. Unlike /compact, no summary is preserved.
/compact local Clears history but keeps a summary. Accepts custom summarization instructions.
/model local-jsx Changes the AI model. Shows an interactive selector if no model is specified.
/config settings local-jsx Opens the interactive configuration panel.
/memory local-jsx Opens the CLAUDE.md memory file editor.
/diff local-jsx Visual diff of uncommitted changes and per-turn diffs.
/cost local Token usage and cost breakdown. Hidden for claude.ai subscribers.
/resume continue local-jsx Reopens a previous conversation by ID or search term.
/vim local Toggles Vim keybindings for the input editor.
/theme local-jsx Opens an interactive theme selector.
/doctor local-jsx Runs diagnostics on installation, config, API, hooks, and MCP servers.
/export local-jsx Exports the conversation to a file (markdown, JSON) or clipboard.
/mcp local-jsx Manages MCP servers: enable/disable individual servers or show all statuses.
/context local-jsx Visualizes context window usage as a colored grid.
/plan local-jsx Enters plan mode or views the current session plan.
/permissions allowed-tools local-jsx Interactive UI for managing tool allow/deny rules.
/help local-jsx Shows all available commands, shortcuts, and usage information.
/init prompt Analyzes the codebase and creates a CLAUDE.md file. Also creates skills and hooks with NEW_INIT flag.
/review prompt Reviews a PR using gh pr diff and gh pr view. Looks for bugs and security issues.
/pr-comments prompt Fetches and formats comments from a GitHub PR using the gh CLI.
/security-review prompt Exhaustive security review of changes on the current branch vs origin/HEAD.
/branch fork* local-jsx Creates a conversation branch at the current point for parallel exploration.
/fast local-jsx Toggles fast mode (same model, faster output, 6x more expensive).
/rename local-jsx Renames the current conversation session.
/copy local-jsx Copies Claude's last response (or Nth-latest) to clipboard.
/rewind checkpoint local Restores code and conversation state to a previous checkpoint.
/hooks local-jsx Shows all configured hooks and their trigger events.
/skills local-jsx Lists all available skills from all sources.
/status local-jsx Comprehensive status report: version, model, account, API, tool statuses.
/tasks bashes local-jsx Lists and manages background tasks and running agents.
/add-dir local-jsx Adds an additional working directory to the session scope.
/color local-jsx Sets the prompt bar color for the current session.
/effort local-jsx Controls how much thinking the model applies (low/medium/high/max/auto).
/keybindings local Opens ~/.claude/keybindings.json for editing.
/release-notes local Shows release notes for the current version.
/stats local-jsx Shows usage statistics and activity history.
/btw local-jsx Ask a quick side question without interrupting the main conversation flow.
/exit quit local-jsx Exits Claude Code.
/agents local-jsx Manages custom agent configurations.
/plugin plugins, marketplace local-jsx Manages plugins from the Claude Code marketplace.
/ide local-jsx Shows IDE integration status (VS Code, JetBrains) and manages connections.
/feedback bug local-jsx Submits feedback or bug reports.
/insights prompt Generates an analytical report of your Claude Code usage sessions.
/statusline prompt Configures the shell status line via the statusline-setup agent.
/stickers local Opens a page to order physical Claude Code stickers.

* /fork alias only active when FORK_SUBAGENT flag is inactive

Category 2: Platform-restricted (~15)

Only available on specific platforms (claude.ai or Anthropic console).

Command Platform Description
/usage claude-ai Shows current plan usage and limits.
/upgrade claude-ai Upgrade flow for Max plan (disabled for enterprise).
/desktop claude-ai Hands off the current session to Claude Desktop (macOS/Windows).
/mobile any Shows QR code to download the Claude mobile app.
/chrome claude-ai Configures Claude in Chrome browser extension.
/login any OAuth login flow for Anthropic account.
/logout any Signs out of the current Anthropic account.
/install-github-app claude-ai, console Sets up Claude as a GitHub Actions workflow for a repo.
/install-slack-app claude-ai Installs the Claude app in Slack.
/extra-usage any Configures overage usage when rate limits are hit.
/privacy-settings any Privacy settings management (consumer subscribers only).
/passes any Generates referral passes for free weeks of Claude Code.
/session remote only Shows URL and QR code for the current remote session.
/remote-env claude-ai Configures the default remote environment for teleport sessions.
/sandbox sandboxable Configures sandbox mode for command execution.

Category 3: Hidden commands (4)

These commands exist but are not shown in /help or typeahead.

/output-style hidden

Deprecated. Redirects to /config.

/heapdump hidden

Dumps the JavaScript heap to ~/Desktop. Internal debugging tool.

/rate-limit-options hidden

Automatically triggered when rate limits are hit. Shows recovery options. claude.ai only.

/thinkback-play hidden

Plays the thinkback animation. Gated by tengu_thinkback feature flag.

Category 4: Feature-flag gated (~15)

Only appear when specific feature flags are enabled at build time.

Feature flag Command Description
PROACTIVE / KAIROS /proactive Toggle proactive / autonomous mode
KAIROS / KAIROS_BRIEF /brief Toggle brief output mode
KAIROS /assistant Assistant mode command
BRIDGE_MODE /bridge IDE bridge mode
VOICE_MODE /voice Toggle voice input mode
HISTORY_SNIP /force-snip Force history snip
WORKFLOW_SCRIPTS /workflows Manage workflow scripts
CCR_REMOTE_SETUP /web-setup Setup Claude Code on the web
KAIROS_GITHUB_WEBHOOKS /subscribe-pr Subscribe to PR webhooks
ULTRAPLAN /ultraplan Ultra planning mode
FORK_SUBAGENT /fork Fork sub-agent (replaces /branch alias)
BUDDY /buddy Buddy companion
tengu_thinkback /think-back 2025 Year in Review
tengu_ultrareview /ultrareview Deep bug-finding review (~10-20 min)

Category 5: Anthropic-internal (~22)

Only enabled when process.env.USER_TYPE === 'ant'. In external builds, they are stubbed as disabled and hidden.

Command Description
/files List all files currently in context
/tag Toggle a searchable tag on the current session
/version Print the version this session is running
/commit Create git commits with proper attribution
/commit-push-pr Full flow: commit, push, and create PR
/issue Report a model-related issue
/share Upload full session transcript for product bugs
/init-verifiers Create verifier skill(s) for automated verification
/bridge-kick Inject bridge failures for recovery testing
/backfill-sessions Backfill session data
/break-cache Force cache invalidation
/bughunter Bug hunting tool
/good-claude Good Claude reward
/ctx_viz Context visualization (internal)
/mock-limits Mock rate limits for testing
/onboarding Onboarding flow
/summary Session summary
/teleport Teleport to remote environment
/reset-limits Reset rate limits
/ant-trace Anthropic tracing
/perf-issue Performance issue reporting
/env Environment inspection

Summary

Category Count
Core user commands ~45
Platform-restricted ~15
Hidden 4
Feature-flag gated ~15
Anthropic-internal ~22
Total ~100

Additionally, the system dynamically loads skill commands from /.claude/skills/, plugin commands, MCP commands, and workflow commands (if WORKFLOW_SCRIPTS is active).

Three commands most users don't know about
/btw lets you ask a side question without affecting the main conversation. /rewind restores code and conversation state to a previous checkpoint. /branch forks the conversation so you can explore two approaches from the same point without losing either.