careful

Detect destructive shell commands and require confirmation before execution.

Updated Sep 10, 2024
One-click install
npx skills add https://github.com/TioSavich/UMEDCTA --skill careful-tiosavich
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/TioSavich/UMEDCTA/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/TioSavich/UMEDCTA --skill careful-tiosavich

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".

Core Features & Use Cases

  • Warns for high-risk commands such as rm -rf, git reset --hard, and kubectl delete before execution.
  • Allows per-command override to proceed despite warnings.
  • Logs usage analytics to ~/.gstack/analytics for auditing and improvement.
  • Integrates as a PreToolUse hook to intercept and evaluate user commands in real time.

Quick Start

Enable safety mode and confirm any 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 prevent destructive shell commands like rm -rf or git reset --hard from executing automatically?

To prevent destructive shell commands, a pre-tool hook scans input commands, detects destructive patterns like rm -rf or git reset --hard, and requires confirmation before proceeding. It returns a permission decision or allows execution when safe.

Can I override safety warnings for specific destructive operations if I need to proceed?

Yes, you can override safety warnings for specific destructive operations. The Skill allows per-command override, enabling you to proceed with execution despite the detected destructive patterns after acknowledging the warning.

How do I add safety guardrails when debugging live systems or working in shared production environments?

Adding safety guardrails for shared production environments involves integrating a PreToolUse hook to intercept and evaluate user commands in real time. This warns before high-risk operations like kubectl delete or force-push, ensuring risky actions require confirmation.

What destructive command patterns does a pre-tool hook detect for development and production maintenance?

A pre-tool hook detects destructive command patterns for development and production maintenance including rm -rf, DROP TABLE, force-push, git reset --hard, and kubectl delete. It scans input commands and blocks execution until confirmation is granted.

Does this command safety hook log analytics for auditing destructive operations?

Yes, this command safety hook logs usage analytics for auditing destructive operations. It records data to the ~/.gstack/analytics directory, capturing warning events and overrides to improve safety tracking and operational auditing.