careful

Detect destructive commands and require user confirmation before execution.

1|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/westn/gstack-pi-port --skill careful-westn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/westn/gstack-pi-port/tree/main/port/gstack/careful
Command: npx skills add https://github.com/westn/gstack-pi-port --skill careful-westn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails prevent destructive commands from causing data loss by warning and requiring user confirmation before execution. This helps teams avoid accidental harm in production, during live debugging, or in shared environments.

Core Features & Use Cases

  • Destructive command detection: Intercepts commands like rm -rf, git reset --hard, kubectl delete, and force-push attempts and prompts for confirmation.
  • Override capability: Users can explicitly approve warnings to proceed when necessary.
  • Use Case: When touching production systems or debugging live environments, enable careful mode to prevent accidental harm.

Quick Start

Enable careful mode and observe the warning prompt before proceeding with 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 commands in production?

You can enforce safety guardrails by integrating a PreToolUse Bash hook that detects destructive patterns like rm -rf or git reset --hard and prompts for confirmation before execution. This prevents accidental data loss in production or shared environments.

What types of destructive commands are intercepted by careful mode?

Careful mode intercepts destructive commands such as rm -rf, git reset --hard, kubectl delete, and force-push attempts. It detects these risky patterns and prompts for explicit confirmation before allowing execution in live environments.

Can I override the safety warning if I need to run a destructive command intentionally?

Yes, you can override the safety warning by explicitly approving the prompt. Careful mode provides an override capability that allows users to proceed with destructive commands when they confirm the action is intentional and necessary.

When should I enable safety checks for destructive commands?

You should enable safety checks when touching production systems, debugging live environments, or working in shared environments where risky commands could impact others. Enabling careful mode prevents accidental harm during these sensitive operations.

Does this safety hook work without additional dependencies?

Yes, the safety hook works without additional dependencies. It integrates directly using a PreToolUse Bash hook to run a safety script that detects destructive patterns and requires user confirmation before execution.