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.

skills.sh installs: 4K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Safety Guard — Prevent Destructive Operations

When to Use

When working on production systems
When agents are running autonomously (full-auto mode)
When you want to restrict edits to a specific directory
During sensitive operations (migrations, deploys, data changes)

How It Works

Three modes of protection. They are instructions the agent follows, not enforced blocks (see Enforcement).

Mode 1: Careful Mode

Before it runs a destructive command, the agent stops and warns:

Watched patterns:
- rm -rf (especially /, ~, or project root)
- git push --force
- git reset --hard
- git checkout . (discard all changes)
- DROP TABLE / DROP DATABASE
- docker system prune
- kubectl delete
- chmod 777
- sudo rm
- npm publish (accidental publishes)
- Any command with --no-verify

When detected: shows what the command does, asks for confirmation, suggests safer alternative.