What problem does it solve? AI coding agents can accidentally run destructive Git commands like git push --force or git reset --hard, causing irreversible loss of work or unintended changes to shared repositories. This Skill installs a safety net that intercepts and blocks those commands before they execute. ## Core Features & Use Cases - PreToolUse Hook Installation: Sets up a Claude Code hook that intercepts Bash tool calls and blocks dangerous Git commands before they run. - Flexible Scope: Install the guardrail for a single project (.claude/settings.json) or globally across all projects (~/.claude/settings.json). - Customizable Blocklist: Edit the bundled shell script to add or remove blocked patterns such as git push, git reset --hard, git clean -f, git branch -D, and git checkout .. - Use Case: A team lets Claude Code run autonomously on a repository but wants to guarantee it can never force-push to main or wipe uncommitted changes; this Skill enforces that policy at the tool level. ## Quick Start Ask Claude to set up Git guardrails that block dangerous commands like git push and git reset --hard for this project.