Safety Guard

A pre-execution safety net for when Claude is touching production systems or running autonomously. It works in three modes: Careful (intercepts destructive commands like rm -rf, git push --force, DROP TABLE and asks for confirmation), Freeze (locks edits to a specific directory), and Guard (both combined). The hook-based implementation catches dangerous operations before they execute, which is exactly what you want when an agent is running in full-auto mode and you step away from your desk. Logs blocked actions to ~/.claude/safety-guard.log so you can see what it stopped. Turn it off with /safety-guard off when you need full control back.

Install to Claude Code

npx -y skills add affaan-m/everything-claude-code --skill safety-guard --agent claude-code