careful

Detect and block destructive commands matching predefined patterns before execution.

1|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/greencm/gstuck --skill careful-greencm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/greencm/gstuck/tree/main/output/gstack/careful
Command: npx skills add https://github.com/greencm/gstuck --skill careful-greencm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill acts as a safety net for destructive commands, preventing accidental damage to systems and data.

Core Features & Use Cases

  • Destructive Command Detection: Identifies and alerts on potentially harmful commands like rm -rf, DROP TABLE, and git reset --hard.
  • User Override: Allows users to override warnings if they understand the risks.
  • Use Case: When working in a shared environment or on a production system, this Skill can prevent accidental data loss or system damage by flagging dangerous commands.

Quick Start

Activate the careful skill when performing a destructive operation to ensure safety.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent destructive commands from accidentally running in a shared environment?

You can prevent destructive commands by implementing safety guardrails that monitor and block harmful patterns. This Skill acts as a safety net by using a pre-execution hook to analyze and block commands like rm -rf or DROP TABLE in production systems.

What destructive command patterns should guardrails check for in Bash and other tools?

Destructive command guardrails should check for predefined patterns indicating potentially harmful actions, specifically targeting commands like rm -rf, DROP TABLE, and git reset --hard to prevent accidental data loss or system damage.

How do I set up a pre-execution hook to block harmful commands before they execute?

To set up a pre-execution hook for blocking harmful commands, activate the careful skill before performing destructive operations. The hook analyzes your commands against predefined patterns and alerts you to prevent accidental system damage.

Can I override safety warnings for destructive commands if I understand the risks?

Yes, you can override safety warnings for destructive commands if you understand the risks. The guardrails allow user overrides to bypass alerts, ensuring flexibility when you intentionally need to execute potentially harmful actions.

Does command checking work for both database operations and Git commands?

Yes, command checking works for database operations and Git commands by identifying predefined destructive patterns. The guardrails monitor Bash and other tools to prevent accidental data loss from commands like DROP TABLE or git reset --hard.

When should I use safety guardrails for command execution?

You should use safety guardrails for command execution when working in shared environments or production systems. Implementing these guardrails prevents accidental data loss and system damage by flagging dangerous commands before they run.