careful

Require explicit confirmation before executing destructive shell commands.

Updated Mar 14, 2026
One-click install
npx skills add https://github.com/EhsaanArk/ai-signal-router --skill careful-ehsaanark
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/EhsaanArk/ai-signal-router/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/EhsaanArk/ai-signal-router --skill careful-ehsaanark

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

MANUAL TRIGGER ONLY: invoke only when user types /careful. 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

  • Manual trigger mode ensures destructive actions are only performed after explicit confirmation.
  • Per-command warnings with optional override to proceed if the user accepts risk.
  • Suitable for production maintenance, debugging, and collaborative environments.

Quick Start

Invoke the skill by typing /careful to enable safety checks before executing any destructive commands.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add safety guards to prevent destructive bash commands from running automatically?

To add safety guards for destructive bash commands, you need a system that requires manual trigger confirmation before executing operations like rm -rf. This ensures risky commands only run after explicit user approval, preventing accidental data loss in development and production environments.

Can I override the warning prompt if I am confident a git reset --hard command is safe to execute?

Yes, you can override the warning prompt for a git reset --hard command. The safety guard system provides per-command warnings with an optional override, allowing you to accept the risk and proceed with the destructive operation if you confirm it is intentional.

Does this manual trigger safety mode work for kubectl delete operations in production environments?

Yes, this manual trigger safety mode works for kubectl delete operations in production environments. It intercepts risky commands and requires explicit confirmation, ensuring that destructive cluster actions are only performed after you acknowledge and accept the operational risk.

What is the best way to enforce a confirmation step before executing risky shell operations like force-push?

The best way to enforce a confirmation step for risky shell operations like force-push is using a manual trigger workflow. It applies a pre-check script that warns before execution and requires you to explicitly confirm the action, preventing accidental repository history overwrites.

When do I need to enable safety mode for destructive commands in a shared development environment?

You need to enable safety mode for destructive commands in a shared environment when touching production, debugging live systems, or collaborating. It prevents accidental execution of commands like DROP TABLE by requiring explicit manual confirmation before any irreversible action proceeds.