Skills Directory

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wan

Tracks token spend across an agent run and stops or downgrades before it blows the budget. Use when running long autonomous tasks with a har

Marks and handles untrusted content entering an agent context. Use in any pipeline that reads web pages, emails, documents or third-party AP

Prevents an agent from acting on state it never checked. Use in any agent with file, shell or API write access.