careful

Detect destructive Bash commands and prompt for confirmation before execution.

43|7|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/lucas-flatwhite/gstack-ko --skill careful-lucas-flatwhite
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/lucas-flatwhite/gstack-ko/tree/main/careful
Command: npx skills add https://github.com/lucas-flatwhite/gstack-ko --skill careful-lucas-flatwhite

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails prevent execution of destructive commands by warning before actions like rm -rf, DROP TABLE, git reset --hard, kubectl delete, and similar operations. Users can override warnings to proceed when necessary.

Core Features & Use Cases

  • Detects dangerous command patterns in Bash workflows and prompts for confirmation.
  • Allows per-command override decisions, enabling careful but flexible workflows.
  • Ideal for production maintenance, debugging live systems, or collaborative environments where dangerous actions could impact others.

Quick Start

Invoke careful mode and proceed only after reviewing the warning prompts for any destructive commands.

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 executing in production?

You can prevent destructive bash commands by applying safety guardrails that detect risky patterns like deletions or force-pushes and prompt for human confirmation before execution.

Can I override the confirmation prompt for specific destructive commands?

Yes, you can override the confirmation prompt on a per-command basis, allowing you to bypass the safety guardrails and proceed with the specific destructive operation when necessary.

What types of dangerous operations does the safety guardrail warning detect?

The safety guardrail warning detects dangerous operations such as deletions, resets, and force-push actions, specifically targeting risky patterns like rm -rf, DROP TABLE, git reset --hard, and kubectl delete.

Does this safety mode work for collaborative development and live system debugging?

Yes, this safety mode is ideal for collaborative development and live system debugging where dangerous actions could impact others, enforcing detection of risky patterns and logging decisions for verification.

How do I integrate command confirmation into my existing Bash workflow?

You integrate command confirmation into your Bash workflow through a manual trigger hook that enforces detection of risky patterns, prompts for verification, and logs decisions before executing commands.