careful

Warn before executing destructive shell and CI commands.

Updated Mar 21, 2026
One-click install
npx skills add https://github.com/studyzy/dev-agent-protocol --skill careful-studyzy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/studyzy/dev-agent-protocol/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/studyzy/dev-agent-protocol --skill careful-studyzy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides safety guardrails that warn before destructive commands are executed, helping prevent data loss or system damage by requiring explicit consent for risky operations.

Core Features & Use Cases

  • Warns before executing dangerous commands like rm -rf, git reset --hard, kubectl delete, and similar operations.
  • Allows user override after a warning to proceed or cancel, enabling safe exploration in prod or shared environments.
  • Logs and surfaces warnings to help teams review destructive actions and improve safety practices.

Quick Start

Enable careful mode to trigger warnings before 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 add a warning prompt before executing destructive shell commands?

To add a warning prompt before executing destructive shell commands, enable careful mode to trigger a pre-execution hook that detects risky patterns and requires explicit confirmation before proceeding.

What is a pre-execution hook for shell safety and how does it work?

A pre-execution hook for shell safety intercepts commands before they run, detects destructive patterns like rm -rf or git reset --hard, and prompts the user for explicit consent to prevent accidental data loss.

Can I get a warning before running kubectl delete or git reset --hard in production?

Yes, you can get a warning before running kubectl delete or git reset --hard in production by enabling careful mode, which applies guardrails during live debugging and production changes.

How do I override a command warning if I want to proceed with a destructive operation?

You can override a command warning to proceed with a destructive operation by explicitly confirming the prompt, which allows safe exploration in prod or shared environments while maintaining the safety guardrail.

Does this destructive command warning system work in CI environments?

Yes, this destructive command warning system works in CI environments, applying safety guardrails to warn before risky operations are executed during automated production changes and shared environment collaboration.

Are there limitations when using careful mode for live debugging in shared environments?

A limitation of careful mode during live debugging in shared environments is that it requires manual confirmation for each detected destructive command, which may interrupt automated scripts or non-interactive CI pipelines.