guard

Enforce edit boundaries and warn before destructive commands.

Updated Jun 18, 2026

Search Tags:#safety #guard #gstack #destructive-warnings #edit-boundary #live-system

Ready to run

npx skills add https://github.com/abhishekmmgn/didactic-invention --skill guard-abhishekmmgn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/abhishekmmgn/didactic-invention/tree/main/.agents/skills/gstack/guard
Command: npx skills add https://github.com/abhishekmmgn/didactic-invention --skill guard-abhishekmmgn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides maximum safety during live-system maintenance by combining destructive-command warnings with a strict edit boundary, preventing accidental damage and unauthorized edits.

Core Features & Use Cases

Destructive command warnings: warns before executing dangerous commands that could delete data or destabilize systems.
Edit boundary enforcement: restricts file edits to a user-specified directory to prevent accidental changes outside the approved scope.
Safe maintenance workflows: ideal for production debugging, hotfixes, or any operation requiring guarded change management.

Quick Start

Ask the user which directory should be protected and enable Guard mode to activate both destructive-command warnings and the edit boundary.

Frequently Asked Questions about guard

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

FAQPage Schema

How do I prevent accidental destructive commands during live-system maintenance?▼

To prevent accidental destructive commands during live-system maintenance, this Skill enforces warnings before executing dangerous operations. It activates safety warnings that intercept potentially destabilizing actions before they run.

Can I restrict file edits to a specific directory boundary during production debugging?▼

Yes, you can restrict file edits to a specific directory boundary during production debugging. The Skill uses a user-provided path to set a strict freeze boundary, preventing any unauthorized file modifications outside that approved scope.

What is the best way to guard production hotfixes from untrusted edits?▼

The best way to guard production hotfixes from untrusted edits is combining destructive-command warnings with strict edit boundaries. This dual approach prevents accidental data deletion while restricting file modifications to an approved directory.

Do I need any other tools installed to enforce edit boundaries on live systems?▼

Yes, you need the sibling careful and freeze skills installed to enforce edit boundaries on live systems. The Guard Skill requires these dependencies to properly set and maintain the freeze boundary using your user-provided path.

How do I set up an edit boundary for safe maintenance workflows?▼

To set up an edit boundary for safe maintenance workflows, specify which directory should be protected and enable Guard mode. This activates both destructive-command warnings and the strict edit boundary simultaneously.

When should I not use an edit boundary approach for production changes?▼

You should not use an edit boundary approach when your production changes require modifying files outside a single defined directory. The strict boundary prevents modifications beyond the user-specified path, limiting workflows that span multiple directories.