careful

Detect destructive Bash commands and request confirmation before execution.

Updated May 7, 2026
One-click install
npx skills add https://github.com/TumeloRamaphosa/StudEx-Valley-OS --skill careful-tumeloramaphosa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/TumeloRamaphosa/StudEx-Valley-OS/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/TumeloRamaphosa/StudEx-Valley-OS --skill careful-tumeloramaphosa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces the risk of accidental data loss or production-impacting changes by warning you before running destructive Bash commands.

Core Features & Use Cases

  • Destructive command detection: Flags common high-risk operations like recursive deletes, SQL DROP/TRUNCATE statements, force-pushes, hard resets, kube resource deletion, and dangerous Docker pruning.
  • Safe exceptions with allowances: Permits recursive deletes only for typical build/artifact directories (for example, node_modules and build outputs) without warning.
  • User override behavior: When a risky command is detected, it requires confirmation instead of silently blocking or proceeding.

Quick Start

Tell your assistant to use the careful skill when you are about to run a command that could be destructive, such as rm -rf, DROP TABLE, git push --force, kubectl delete, or git reset --hard.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent destructive bash commands from running accidentally?

To prevent destructive bash commands, you need safety guardrails that intercept risky patterns before execution. This skill flags operations like recursive deletes and force-pushes, returning a warning that requires your confirmation before proceeding.

What destructive command patterns does bash safety validation detect?

Bash safety validation detects high-risk operations including recursive deletes, SQL DROP or TRUNCATE statements, git push --force, git reset --hard, kubectl delete, and dangerous Docker pruning commands.

Can I safely run recursive deletes on build directories without triggering warnings?

You can safely run recursive deletes on typical build and artifact directories like node_modules without triggering warnings. The safety validation includes allowances that permit these specific directory deletions.

How does command validation handle risky commands in production environments?

Command validation handles risky commands in production environments by requiring confirmation instead of silently blocking or proceeding. It intercepts the command via a PreToolUse Bash hook and asks for your permission.

Does this safety guardrail work with kubectl and git operations?

Yes, the safety guardrail works with kubectl and git operations by validating shell command generation workflows. It specifically detects risky kube resource deletions, git force-pushes, and hard resets before execution.