careful

Detect destructive commands and prompt user confirmation before execution.

Updated Jun 16, 2026
One-click install
npx skills add https://github.com/miko06/MedicineSimulator --skill careful-miko06
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/miko06/MedicineSimulator/tree/main/.opencode/skills/gstack-careful
Command: npx skills add https://github.com/miko06/MedicineSimulator --skill careful-miko06

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The 'careful' Skill mitigates the risk of destructive commands in production environments, helping users avoid accidental data loss and system damage.

Core Features & Use Cases

  • Destructive Command Detection: Identifies commands like rm -rf, DROP TABLE, git reset --hard, and others with high potential for causing irreversible damage.
  • Real-Time Warnings: Immediately alerts users to such commands, giving the option to confirm execution or cancel the operation.
  • Safe Exceptions: Allows for known-safe patterns like cleaning directories without warning.
  • Production Ready: Ideal for developers working in live environments or shared setups.

Quick Start

Use 'careful' to automatically check commands and warn before running anything potentially destructive.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent accidental data loss from destructive commands in production?

To prevent accidental data loss from destructive commands in production, you need a safety guardrail that monitors inputs and prompts for confirmation before executing high-risk operations like rm -rf or DROP TABLE.

What is destructive command detection and how does it work?

Destructive command detection is a safety mechanism that identifies potentially irreversible operations like git reset --hard. It alerts users in real-time, providing the option to confirm execution or cancel the operation before system damage occurs.

How do I add safety guardrails for dangerous shell commands?

You can add safety guardrails for dangerous shell commands by implementing a monitoring script that checks inputs against known destructive patterns and immediately warns you to confirm or cancel the execution.

Can I safely run directory cleaning commands without triggering warnings?

Yes, you can safely run directory cleaning commands without triggering warnings by configuring safe exceptions for known-safe patterns, allowing routine maintenance tasks to execute without manual confirmation.

Does command safety monitoring work across all stages of production?

Command safety monitoring is suited for use across all stages of production. It is ideal for developers working in live environments or shared setups to ensure safety of system commands.

What are the limitations of using real-time command warnings?

Real-time command warnings only trigger for recognized destructive patterns like DROP TABLE or rm -rf. Unknown dangerous commands without established patterns might not prompt a warning, requiring users to configure custom exceptions.