careful

Intercept destructive Bash and Git commands and require confirmation before execution.

Updated Dec 17, 2025
One-click install
npx skills add https://github.com/eprouveze/HealthPulse --skill careful-eprouveze
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/eprouveze/HealthPulse/tree/main/.claude/skills/careful
Command: npx skills add https://github.com/eprouveze/HealthPulse --skill careful-eprouveze

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails prevent accidental data loss by intercepting risky commands before they run.

Core Features & Use Cases

  • Detect destructive command patterns in Bash and Git workflows.
  • Warn and require explicit confirmation before executing any destructive command.
  • Safe exceptions for common harmless operations with an override option.
  • Suitable for development, testing, and production environments in shared setups.

Quick Start

Enable the guard and require explicit confirmation before executing any destructive command.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add safety guardrails to prevent destructive bash and git commands?

Safety guardrails intercept risky bash and git commands by detecting dangerous patterns and requiring explicit confirmation before execution. This prevents accidental data loss in local and shared environments.

Can I override the warning when running destructive git commands?

Yes, destructive git commands trigger a warning that returns a permission decision, but you can override it. The guardrails include safe exceptions for common harmless operations while requiring confirmation for genuinely risky patterns.

Does this safety guardrail work in shared production environments?

Yes, the safety guardrail is suitable for development, testing, and production environments in shared setups. It applies safety checks across local and shared bash and git workflows to prevent data loss.

What are the limitations of using pre-tool hooks to intercept destructive commands?

Pre-tool hooks rely on detecting known dangerous command patterns, meaning novel or obscured destructive commands might bypass the guardrail. The hook returns a permission decision rather than blocking execution entirely, allowing user override.