Prevent Destructive Ops
Your AI blocks or warns before destructive commands on production systems or during autonomous runs. It restricts edits to allowed directories and intercepts risky commands like forced git pushes or data drops.
affaan-m on GitHub
Curated by PromptsEdge from a public repo · MIT license. All credit goes to the author.
What is this skill?
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
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)
What’s inside
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 neversessions - Pair with observability risk scoring in ECC 2.0
- Logs all blocked actions to
~/.claude/safety-guard.log
Install this skill
- 1
Get the skill — it’s free
Use the Get this skill panel. Unlocked skills stay in My skills. - 2
Download or clone the files
Download the zip, or clone the repo and copy theskills/safety-guardfolder. - 3
Put it where your agent looks for skills
For Claude Code, use your personal skills folder (every project) or a project’s own folder:~/.claude/skills/safety-guard/SKILL.md # all projects .claude/skills/safety-guard/SKILL.md # this project only
- 4
Just ask
No command needed. The agent reads the skill’s description and loads it on its own when your request matches.
SKILL.md frontmatter
What your agent reads to decide when to load this skill.
--- name: safety-guard description: Use this skill to prevent destructive operations when working on production systems or running agents autonomously. ---
Files
Open any Markdown file to read it here.
Related skills
View all →- Configure and Optimize ViteFreeYour AI configures Vite projects including plugins, environment variables, proxy setup, and build optimization. It handles dev server, SSR, library mode, and troubleshooting common Vite issues.
- Edit and Structure VideoFreeYour AI edits and structures existing video footage into polished content. It manages cutting, overlays, subtitles, voiceovers, and reframing using FFmpeg, Remotion, ElevenLabs, Descript, and CapCut workflows.
- Team Agent OrchestrationFreeYour AI coordinates multiple agents as a team using work items, ownership, Kanban states, and merge gates. It manages shared workflow visibility, branch isolation, and control pane handoffs for multi-agent project collaboration.
- Taste-Based Video ApplicationFreeYour AI generates videos applying a distilled style pack, planning cuts by measured rhythm and grading with LUTs. It weaves generated and existing footage into finished edits with overlays and 3D props, verifying results numerically.