claude-code-docs

Answers questions about Anthropic's Claude Code from a local mirror of its official documentation (code.claude.com/docs). Use when someone asks how Claude Code behaves or how to set it up: CLI flags, settings, hooks, skills, plugins, MCP servers, subagents, slash commands, permissions, sandboxing, memory and CLAUDE.md, output styles, the Agent SDK, the IDE, desktop, web, and Slack surfaces, monitoring, or release notes. Read the mirror before searching the web. Not for OpenAI Codex, Cursor, the Claude API, or claude.ai chat.

License: MIT for the mirroring tooling; the mirrored documentation belongs to Anthropic.
Compatibility: Any agent that reads Agent Skills, such as Claude Code, Codex, or Cursor. Needs read access to this skill's files and no network access.

Read SKILL.md at the source

Pinned to revision 12f7babab1db, so it is the text this page describes rather than whatever the author pushed since.

Pre-approved tools experimental

Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.

Read
Grep
Glob

Files

Every link opens the file at its source, pinned to the revision this page describes.