This repo ships executable examples — Python hook scripts in .claude/hooks/ and skills in .claude/commands/ that run with your shell permissions when you copy them into a project. Review them like any shell script before use (the guide itself preaches the same).

If you find a security issue in any script or instruction in this repo — e.g. a hook that could be abused, an unsafe command in a walkthrough, or a link pointing somewhere malicious — please report it privately via GitHub security advisories rather than a public issue.

Issues in Claude Code itself should go to anthropics/claude-code or Anthropic's responsible disclosure program.