careful

Warn before destructive CLI commands and prompt for confirmation.

4|1|Updated Sep 13, 2023
One-click install
npx skills add https://github.com/louisfghbvc/mcp-leetcode-crawler --skill careful-louisfghbvc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/louisfghbvc/mcp-leetcode-crawler/tree/main/.agent/skills/careful
Command: npx skills add https://github.com/louisfghbvc/mcp-leetcode-crawler --skill careful-louisfghbvc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

Core Features & Use Cases

  • Warns before destructive commands and prompts for confirmation
  • Provides override options to proceed when safety checks are intentional
  • Useful in production or shared environments to prevent accidental data loss

Quick Start

Enable careful mode and confirm each destructive command before execution.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add confirmation prompts for destructive bash commands like rm -rf or git reset?

You can add confirmation prompts for destructive bash commands by implementing safety guardrails that detect command patterns like rm -rf or git reset --hard and warn before execution. This allows you to verify and intercept potentially dangerous operations before they run.

What is the best way to prevent accidental data loss when running kubectl delete in production?

Preventing accidental data loss from kubectl delete in production requires applying safety guardrails that intercept destructive commands and require explicit user confirmation. This ensures deliberate execution while logging local usage to track override actions.

Can I override the warning when I intentionally need to force-push or drop a table?

Yes, you can override the warning when you intentionally need to force-push or drop a table. The safety guardrails provide override capability for each specific warning, allowing deliberate execution of destructive operations after confirmation.

Does this safety mode work across development, staging, and production environments?

Yes, this safety mode works across development, staging, and production environments. It applies safety guardrails to CLI workflows and scripts universally, ensuring consistent protection against accidental destructive commands regardless of the environment.

How do I enable careful mode for debugging live systems or working in shared environments?

You enable careful mode for debugging live systems or shared environments by activating the safety guardrails. This prompts you to confirm each destructive command before execution, preventing accidental data loss when touching critical infrastructure.

What types of destructive operations are intercepted by command-pattern detection?

Command-pattern detection intercepts destructive operations such as rm -rf, DROP TABLE, force-push, git reset --hard, and kubectl delete. It identifies these patterns in CLI workflows and scripts to provide configurable warnings before execution.