Safety Guard

This is the kind of thing you turn on before letting Claude run in full-auto mode on a production system. It intercepts destructive commands like `rm -rf`, `git push --force`, and `DROP TABLE` before they execute, then warns you and suggests safer alternatives. You can also freeze edits to a specific directory so an autonomous agent can't touch code outside its scope. Three modes: careful (blocks dangerous commands), freeze (locks edits to one path), or guard (both). It hooks into the tool execution layer and catches things at the Bash, Write, and Edit level. Logs everything it blocks to a file so you can review what would have happened.

skills.sh installs: 5.5K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --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.