safety-guard
Helps developers prevent accidental damage when running automated agents on live systems.
Installation
Paste this into Claude Code, Cursor, or any agent that can run commands.
What this skill does
What it does:
- Stops dangerous commands before they run, like deleting files or forcing code changes
- Locks certain folders so the AI can only read them, not change them
- Combines both protections for maximum safety when the AI works on its own
When to use it:
- When working on real systems that are being used by people
- When letting the AI make changes without you watching every step
- When you want to protect important folders from accidental changes
- Before running big operations like moving data or updating software
SKILL.mdShow the author's original SKILL.md
--- name: safety-guard description: Use this skill to prevent destructive operations when working on production systems or running agents autonomously. metadata: origin: ECC --- # 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: ### Mode 1: Careful Mode Intercepts destructive commands before execution 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. ### Mode 2: Freeze Mode Locks file edits to a specific directory tree: ``` /safety-guard freeze src/components/ ``` Any Write/Edit outside `src/components/` is blocked with an explanation. Useful when you want an agent to focus on one area without touching unrelated code. ### Mode 3: Guard Mode (Careful + Freeze combined) Both protections active. Maximum safety for autonomous agents. ``` /safety-guard guard --dir src/api/ --allow-read-all ``` Agents can read anything but only write to `src/api/`. Destructive commands are blocked everywhere. ### Unlock ``` /safety-guard off ``` ## Implementation Uses PreToolUse hooks to intercept Bash, Write, Edit, and MultiEdit tool calls. Checks the command/path against the active rules before allowing execution. ## Integration - Enable by default for `codex -a never` sessions - Pair with observability risk scoring in ECC 2.0 - Logs all blocked actions to `~/.claude/safety-guard.log`
Mirrored from the author's public source. Install counts from the open skills registry.