skills.rest
LGJ-Jonathan
LGJ-JonathanOFFICIAL
Explore all skills by this author →
GitHub

careful

Intercepts destructive bash commands and prompts for confirmation before execution.

Updated Mar 26, 2026
Search Tags:#git#production#bash#safety#guardrails#hook#destructive commands
One-click install
npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill careful-lgj-jonathan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills/tree/main/gstack/careful
Command: npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill careful-lgj-jonathan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Destructive shell commands like rm -rf, DROP TABLE, or git push --force can cause irreversible data loss when run accidentally, especially 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: Hooks into every Bash tool call and checks for rm -rf, DROP TABLE, TRUNCATE, git force-push, git reset --hard, kubectl delete, and docker prune patterns. - 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 with a clear warning message, letting you proceed or cancel on a case-by-case basis. - Use Case: While debugging a live production issue, you ask the AI to clean up old files. The hook catches an accidental rm -rf /var/data and warns you before any damage occurs. ## Quick Start Ask the AI to enable careful mode or safety mode before running shell commands against a 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 in Claude Code?▼

Enable the careful skill, which registers a PreToolUse hook that scans every Bash command for recursive delete patterns. When a match is found, it returns an ask decision with a warning so you can confirm or cancel before execution.

What destructive commands does the careful hook detect?▼

The hook detects rm -rf and rm --recursive, SQL DROP TABLE, DROP DATABASE, and TRUNCATE, git push --force, git reset --hard, git checkout ., kubectl delete, and docker rm -f or docker system prune.

Can I delete node_modules without triggering the warning?▼

Yes. The hook whitelists recursive deletes targeting only build artifacts such as node_modules, dist, .next, build, .turbo, coverage, .cache, and __pycache__. Commands limited to these targets pass without a warning.

Does the careful hook block commands permanently?▼

No. The hook returns a permissionDecision of ask, which displays a warning message and lets you choose to proceed or cancel. It never hard-blocks a command, and the protection ends when the session ends.

Why did the careful hook not catch my command?▼

The hook only inspects Bash tool commands matching its defined pattern list. Commands with unusual quoting may fall back to a Python JSON parser, and patterns outside the documented list, such as non-recursive rm, are not checked.

Related Skills

Explore More Software Engineering Skills→
supercent-iosupercent-io

ralphmode

Configure permission profiles for Claude Code, Codex CLI, and Gemini CLI.

Official
Advanced
full-stack-bizfull-stack-biz
26

hook-creator

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

Official
Advanced
freitasp1freitasp1

safe-git-guard

Block destructive Git commands and require backups before history-modifying operations.

Community
Advanced
cloudofgeorgecloudofgeorge

guard

Warn before destructive commands and restrict file edits to a specified directory.

Community
Advanced