careful

Detect destructive commands and trigger warnings before execution across workflows.

1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/tyhuffman7/gstack-hermes --skill careful-tyhuffman7
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/tyhuffman7/gstack-hermes/tree/main/gstack-careful
Command: npx skills add https://github.com/tyhuffman7/gstack-hermes --skill careful-tyhuffman7

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands, warning before actions like rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar operations. Users can override warnings to proceed in controlled environments.

Core Features & Use Cases

  • Destructive operation detection and warning before execution
  • Per-command override to selectively bypass warnings
  • Safe mode suitable for prod, staging, and development

Quick Start

Enable careful mode and enter a destructive command to see the warning and confirm before proceeding.

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 before executing destructive shell commands like rm -rf?

To add a warning before destructive shell commands, you need a guardrail mechanism that detects patterns like rm -rf and prompts for confirmation. This Skill intercepts those operations and requires explicit approval to proceed.

Does this safety guardrail work across development, staging, and production environments?

Yes, this safety guardrail works across development, staging, and production environments. It applies destructive operation detection universally while allowing users to selectively bypass warnings in controlled contexts using per-command override logic.

Can I bypass the confirmation prompt for specific commands when I know they are safe?

You can bypass the confirmation prompt for specific commands using the per-command override feature. This allows you to selectively bypass warnings to proceed in controlled environments when you are certain the operation is safe.

What types of destructive commands does the warning system detect?

The warning system detects destructive commands including rm -rf, DROP TABLE, force-push, git reset --hard, and kubectl delete. It identifies these patterns before execution and triggers a warning to prevent accidental data loss.

How do I prevent accidental data loss from force-push or git reset --hard?

To prevent accidental data loss from git force-push or git reset --hard, implement a destructive operation detection layer. This mechanism intercepts those commands and requires confirmation before allowing the git operations to execute.