skills.rest
dhnpmp-tech
dhnpmp-techCOMMUNITY
Explore all skills by this author →
GitHub

careful

Intercepts destructive bash commands and prompts for confirmation before execution.

Updated Mar 23, 2026
Search Tags:#production#bash#safety#guardrails#hook#destructive commands#rm -rf
One-click install
npx skills add https://github.com/dhnpmp-tech/project-agent --skill careful-dhnpmp-tech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/dhnpmp-tech/project-agent/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/dhnpmp-tech/project-agent --skill careful-dhnpmp-tech

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Accidentally running destructive commands like rm -rf, DROP TABLE, or git push --force can cause irreversible data loss, especially when working in production or shared environments. This Skill adds a safety checkpoint that warns you before such commands execute. ## Core Features & Use Cases - Destructive Pattern Detection: Scans every bash command for rm -rf, DROP TABLE, TRUNCATE, git force-push, git reset --hard, kubectl delete, and docker prune operations. - Safe Exceptions: Allows recursive deletes of build artifacts like node_modules, dist, .next, pycache, and coverage without warnings. - User Override: Returns an "ask" permission decision so you can review the warning and choose to proceed or cancel. - Use Case: While debugging a live production issue, you ask the AI to clean up old files. If it proposes rm -rf /var/data, the hook intercepts the command and warns you before anything is deleted. ## Quick Start Ask the AI to enable careful mode before running shell commands against your production environment.

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 commands when using AI coding assistants?▼

Enable a PreToolUse hook that scans every bash command for recursive delete patterns before execution. When a match is found, the hook returns an ask permission decision with a warning, letting you confirm or cancel the command.

What destructive commands does the careful skill detect?▼

It detects rm -rf and recursive deletes, SQL DROP TABLE, DROP DATABASE, and TRUNCATE, git push --force, git reset --hard, git checkout or restore of the working tree, kubectl delete, and docker rm -f or system prune.

Can I still delete node_modules without getting warnings?▼

Yes. Recursive deletes targeting only safe build artifacts such as node_modules, .next, dist, __pycache__, .cache, build, .turbo, and coverage are allowed without triggering a warning.

Does the careful hook block commands permanently?▼

No. The hook returns an ask permission decision rather than a hard denial, so you can always review the warning and choose to proceed. The protection is session-scoped and ends when the conversation ends.

Why did the careful hook not trigger on my command?▼

The hook only checks commands run through the Bash tool and matches a fixed set of destructive patterns. Commands that fail JSON parsing of the tool input are allowed by default, and patterns outside the defined list are not intercepted.

Related Skills

Explore More Software Engineering Skills→
nweiinweii
7

tirith-config

Enforce Tirith policy rules on shell commands to block homograph, ANSI, and pipe-to-shell risks.

Community
Advanced
full-stack-bizfull-stack-biz
26

hook-creator

Build and validate Claude Code plugin hooks with production safety checks.

Official
Advanced
jokerman89jokerman89

safe-install

Backs up, updates, uninstalls, and restores Lintel installations with visible snapshot management.

Community
Intermediate
vnmoorthyvnmoorthy
2

careful

Intercept destructive Bash, Git, and Kubernetes commands before execution.

Community
Advanced