skills.rest
Simon-YHKim
Simon-YHKimCOMMUNITY
Explore all skills by this author →
GitHub

careful

Intercepts destructive bash commands and prompts for confirmation before execution.

Updated Apr 5, 2026
Search Tags:#devops#production#safety#guardrails#destructive commands#bash hook#confirmation prompt
One-click install
npx skills add https://github.com/Simon-YHKim/eject-button --skill careful-simon-yhkim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/Simon-YHKim/eject-button/tree/main/.claude/skills/careful
Command: npx skills add https://github.com/Simon-YHKim/eject-button --skill careful-simon-yhkim

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Running destructive commands like rm -rf, DROP TABLE, or git push --force in production or shared environments can cause irreversible data loss. This Skill adds a safety checkpoint that warns you before such commands execute, giving you a chance to cancel or confirm. ## Core Features & Use Cases - Destructive Command Detection: Hooks into every Bash tool call and pattern-matches against risky operations including rm -rf, DROP TABLE, TRUNCATE, git push --force, git reset --hard, kubectl delete, and docker system prune. - Safe Exceptions: Common cleanup targets like node_modules, dist, build, .next, pycache, and coverage are allowed without warnings to avoid alert fatigue. - Override-Friendly Warnings: Each match returns an "ask" permission decision with a warning message, so you stay in control and can proceed when the action is intentional. - Use Case: While debugging a live production issue, you ask the AI to clean up old database records. Before any DROP or TRUNCATE runs, the skill intercepts it and asks you to confirm, preventing an accidental wipe of the wrong table. ## Quick Start Activate careful mode before working in the production environment so every destructive command gets a confirmation prompt.

Frequently Asked Questions about careful

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent accidental rm -rf or destructive commands in Claude Code?▼

Activate the careful skill, which registers a PreToolUse hook on every Bash call. It pattern-matches commands like rm -rf, DROP TABLE, and git push --force, then returns an ask decision so you must confirm before execution.

What destructive commands does the careful skill block?▼

It warns on rm -rf and recursive deletes, DROP TABLE, DROP DATABASE, TRUNCATE, git push --force, git reset --hard, git checkout ., kubectl delete, docker rm -f, and docker system prune. Each match triggers a confirmation prompt rather than a hard block.

Does the careful skill warn on every rm command?▼

No. Safe cleanup targets such as node_modules, .next, dist, __pycache__, .cache, build, .turbo, and coverage are explicitly whitelisted and run without warnings to reduce alert fatigue during normal development.

Can I override a destructive command warning?▼

Yes. The hook returns a permissionDecision of ask with a warning message, not a denial. You can review the flagged command and choose to proceed, so intentional operations like a planned force-push still work.

How do I turn off careful mode after activating it?▼

End the current conversation or start a new session. The PreToolUse hooks are session-scoped, so the guardrails deactivate automatically when the session ends.

Related Skills

Explore More Software Engineering Skills→
sajalsuhanesajalsuhane

careful

Analyze shell commands and warn before destructive operations execute.

Community
Advanced
OrionArchitektonOrionArchitekton

coo-alerts

Monitor system health by checking ingest failures, agent issues, and database connectivity.

Community
Basic
ChrisWilesChrisWiles

wiki-rebuild

Rebuild, archive, or restore Obsidian Wiki knowledge bases.

Community
Intermediate
MatiasComercioMatiasComercio
31

git-rewrite-history

Plan and approve git history rewrites with mandatory dry-run steps.

Community
Intermediate