One-click install
npx skills add https://github.com/fray-cloud/coin --skill careful-fray-cloud
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/fray-cloud/coin/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/fray-cloud/coin --skill careful-fray-cloud

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

  • Pre-checks for destructive commands
  • Warning messages and user override options
  • Audit logging of warnings and decisions

Quick Start

Enable careful mode in your workflow to warn before destructive commands like rm -rf, DROP TABLE, or git reset --hard.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add a warning prompt before running destructive bash commands like rm -rf?

You can intercept and block destructive shell commands by enabling safety mode, which warns before risky operations like rm -rf or git reset --hard and logs decisions locally while allowing explicit user overrides to proceed.

Can I override the safety warning when executing a git reset --hard or DROP TABLE?

Yes, you can explicitly override the safety warning to proceed with executing git reset --hard or DROP TABLE; the Skill logs each override decision locally to maintain an auditable trail of destructive operations.

What destructive commands are caught by safety mode when debugging live systems?

Safety mode catches destructive commands such as rm -rf, DROP TABLE, git reset --hard, and kubectl delete, warning you before execution to prevent data loss when debugging live systems or touching production.

Does this destructive-command guard work across both development and production workflows?

Yes, this destructive-command guard works across both development and production workflows, applying pre-checks to risky shell operations and logging warning decisions locally to enable auditable safety in shared environments.

Are locally logged override decisions auditable for shared environment operations?

Yes, locally logged override decisions are auditable; the Skill records warnings and user choices locally during destructive operations, ensuring shared environment workflows maintain a clear audit trail of safety decisions.