#claude-md

cc-safe-setup is a security utility for Claude Code that installs 8 safety hooks to ensure safe autonomous operation. It acts as a checkpoint, intercepting dangerous commands like 'rm -rf /', preventing unauthorized pushes to main branches, and catching secret leaks before execution. Specifically designed to address AI agent regressions and the Opus 4.7 safety crisis, it provides defense-in-depth through process-level hooks, including syntax validation and context window monitoring, making it an essential guardrail for AI-driven development.