careful

Prompt before executing destructive shell commands like rm -rf and DROP TABLE.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/ClyptAI/Clypt-Backend --skill careful-clyptai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/ClyptAI/Clypt-Backend/tree/main/.agents/skills/gstack/careful
Command: npx skills add https://github.com/ClyptAI/Clypt-Backend --skill careful-clyptai

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

  • Automatic command inspection via a PreToolUse hook to detect destructive patterns before execution.
  • Safe exceptions: allow common benign paths (e.g., cleanup of temporary artifacts) and provide an explicit override path with audit logging.
  • Analytics and override workflows to maintain guardrails while enabling controlled changes in shared environments.

Quick Start

Attempt a command that would delete data to see how the safety guardrails prompt for confirmation.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add safety prompts to prevent destructive bash commands like rm -rf from executing?

To add safety prompts for destructive bash commands, this Skill uses a PreToolUse hook to inspect patterns like rm -rf before execution. It automatically intercepts the command and prompts you for confirmation, allowing you to override the warning if the action is intentional.

Can I block git reset --hard and kubectl delete operations in a shared production environment?

Yes, you can block git reset --hard and kubectl delete operations in shared production environments. The Skill detects these specific destructive commands via pattern matching and issues a warning prompt with an override option.

What is the best way to guard against accidental DROP TABLE statements in shell scripts?

The best way to guard against accidental DROP TABLE statements in shell scripts is using a PreToolUse safety hook. It automatically detects dangerous database reset patterns and prompts you for explicit confirmation before allowing the script to proceed.

How do safe exceptions work for destructive command guardrails?

Safe exceptions for destructive command guardrails work by allowing common benign paths, such as temporary artifact cleanup, to execute without prompts. You can explicitly override warnings for blocked commands while the system maintains audit logging for controlled changes.

When should I use a safety guardrail for destructive shell commands?

You should use a safety guardrail for destructive shell commands when touching production, debugging live systems, or working in a shared environment. It is specifically designed for scenarios requiring careful execution to prevent irreversible data loss.

Are there limitations to using pattern matching for command safety prompts?

Pattern matching for command safety prompts relies on detecting specific destructive patterns like force-push or deletions. While it provides an override path with audit logging, highly obfuscated commands or unrecognized destructive aliases might bypass the predefined pattern rules.