What problem does it solve? AI coding agents can execute destructive git operations like force pushes, hard resets, and branch deletions that permanently destroy work. This Skill installs a PreToolUse hook that intercepts and blocks these commands before Claude Code can run them. ## Core Features & Use Cases - Command Blocking: Intercepts git push, git reset --hard, git clean -f/-fd, git branch -D, git checkout ., and git restore . before execution. - Flexible Scope: Installs the guardrail hook either per-project (.claude/settings.json) or globally across all projects (~/.claude/settings.json). - Customizable Patterns: The blocked-pattern list in the shell script can be edited to add or remove commands based on team policy. - Use Case: A developer lets Claude Code run autonomously on a repository but wants to guarantee it can never force-push to main or wipe uncommitted changes; the hook returns exit code 2 with a BLOCKED message whenever a dangerous pattern is detected. ## Quick Start Set up git guardrails in Claude Code to block dangerous git commands like push and reset --hard for this project.