guard

Warn against destructive commands and restrict file edits to a specified directory.

1|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/giljae/gstack-antigravity --skill guard-giljae
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/giljae/gstack-antigravity/tree/main/gstack-origin/guard
Command: npx skills add https://github.com/giljae/gstack-antigravity --skill guard-giljae

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

It provides comprehensive safety measures by warning against destructive commands and limiting file edits to specified directories, protecting critical systems from accidental or malicious changes.

Core Features & Use Cases

  • Warning for Destructive Commands: Detects and alerts before executing commands like 'rm -rf', 'DROP TABLE', or force pushes.
  • Edit Boundary Enforcement: Restricts file modifications to a user-defined directory, preventing outside edits.
  • Use Case: Safeguard production environments by activating full safety mode before performing risky operations or debugging live systems.

Quick Start

Ask the user which directory to lock edits within, then set the boundary to restrict modifications outside that path, and activate warnings for destructive commands.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I prevent destructive commands like rm -rf or DROP TABLE from running in a production environment?

To prevent destructive commands in a production environment, you can use hook scripts to monitor commands and issue danger warnings before execution. This safeguards critical systems by alerting you before risky operations run.

How do I restrict file edits to a specific directory boundary during development?

You can restrict file edits to a specific directory by setting a user-defined boundary path. This enforces edit limits, preventing any file modifications outside the specified directory to protect sensitive files.

What is the best way to enforce operational boundaries and mitigate risk on live systems?

Enforcing operational boundaries on live systems is best achieved by combining directory-based edit restrictions with destructive command warnings. This creates strict safety boundaries for debugging and risky operations.

Can I use Bash hook scripts to monitor commands and enforce edit limits on critical systems?

Yes, you can use Bash hook scripts to monitor commands and enforce edit limits on critical systems. The scripts actively track operations and restrict modifications to ensure secure handling of sensitive environments.

Does this system protection tool require any external dependencies to activate full safety mode?

No, this system protection tool requires no external dependencies to activate full safety mode. It operates independently using Bash hook scripts to provide edit restrictions and destructive command warnings.

When should I activate warnings for destructive commands and edit restrictions?

You should activate warnings for destructive commands and edit restrictions when safeguarding production environments before performing risky operations. This mitigates risk during live system debugging and critical system handling.