guard

Warn on dangerous commands and enforce directory-scoped edit boundaries.

5|1|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/drt0927/tw-overlay --skill guard-drt0927
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/drt0927/tw-overlay/tree/main/.gemini/skills/gstack-guard
Command: npx skills add https://github.com/drt0927/tw-overlay --skill guard-drt0927

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Full safety mode combining destructive-command warnings with a directory-scoped edit boundary, preventing risky actions and unintended edits in production or live-debug workflows.

Core Features & Use Cases

  • Combines destructive-command warnings with a directory-boundary enforcement to protect critical systems.
  • Hooks and safety advisories coordinate with related safeguards to prevent unsafe operations.
  • Uses pre-use checks and boundary controls to ensure edits stay within the defined scope during maintenance.

Quick Start

Activate guard mode and specify the directory whose edits should be restricted.

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 from running in a production environment?

You can prevent destructive commands by activating guard mode, which warns on dangerous operations and enforces a directory-based edit boundary. It applies pre-use hooks and safety checks to block risky actions within defined project folders.

Can I restrict file edits to a specific directory during live system debugging?

Yes, you can restrict file edits to a specific directory by enforcing a directory-based edit boundary. Guard mode locks edits to your defined project folder, ensuring maintenance operations stay within scope and preventing unintended changes outside that boundary.

What is a directory-based edit boundary and how does it protect workflows?

A directory-based edit boundary is a safety control restricting modifications to a predefined folder scope. It protects workflows by ensuring operations stay contained within defined project boundaries, preventing unintended changes to critical files outside that directory.

Does guard mode work without additional dependencies or components?

Yes, guard mode works without additional dependencies or external components. It operates standalone using internal pre-use hooks and boundary controls to coordinate safeguards and prevent unsafe operations within your specified project folders.

When should I use destructive-command warnings and workflow protection?

Use destructive-command warnings and workflow protection when maintaining production environments or debugging live systems. These safeguards are essential whenever you need to ensure controlled edits and prevent risky actions within defined project folders and operational workflows.