careful

Prompt for confirmation before executing destructive file, database, or Git commands.

1|1|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/putrawitama/DenchClaw --skill careful-putrawitama
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/putrawitama/DenchClaw/tree/main/skills/gstack/careful
Command: npx skills add https://github.com/putrawitama/DenchClaw --skill careful-putrawitama

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails — warns before destructive commands. Activate by saying "be careful" or when working with production systems. Warns on: rm -rf, DROP TABLE, force-push, git reset --hard, DELETE without WHERE.

Core Features & Use Cases

  • Warns before potentially destructive operations across File System, Database, and Git.
  • Requires explicit user confirmation before any destructive action.
  • Provides a standardized warning format detailing the command, risks, and reversibility.

Quick Start

Enable careful mode and always confirm before proceeding with any destructive action.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add a confirmation prompt before running destructive git or database commands?

You can add a confirmation prompt by enabling careful mode, which intercepts destructive commands like DROP TABLE or git reset --hard and requires explicit user confirmation before execution to prevent accidental data loss.

What destructive operations does this safety guardrail warn me about?

The safety guardrail warns about destructive operations across file systems, databases, and version control, specifically targeting commands like rm -rf, DROP TABLE, force-push, git reset --hard, and DELETE statements without a WHERE clause.

How do I activate the destructive command warning prompt?

To activate the destructive command warning prompt, simply enable careful mode by saying "be careful" or when you are actively working with production systems to ensure all dangerous commands are intercepted.

Does this safety guardrail work across different infrastructure systems like git and databases?

Yes, the safety guardrail works across different infrastructure systems including file systems, databases, and git version control, providing standardized warnings detailing the command risks and reversibility before any destructive action proceeds.

What happens if I do not explicitly confirm a detected destructive command?

If you do not explicitly confirm a detected destructive command, the system implements a safe fallback behavior to prevent execution, ensuring no dangerous actions like force-push or rm -rf proceed without your direct approval.