guard

Enforce destructive command warnings and directory-scoped edit restrictions.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/mmunro3318/3d-render-pipeline --skill guard-mmunro3318
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/mmunro3318/3d-render-pipeline/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/mmunro3318/3d-render-pipeline --skill guard-mmunro3318

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Full safety mode reduces risk when performing destructive commands or edits by enforcing both command-level warnings and directory-scoped restrictions.

Core Features & Use Cases

  • Combines destructive command warnings with directory-scoped edits to prevent accidental changes to prod or critical systems.
  • Integrates with /careful and /freeze to provide layered safety during maintenance or debugging.
  • Use case: when touching production-like environments, enabling guard mode ensures edits are restricted to a defined path.

Quick Start

Enable guard mode to activate destructive-command warnings and directory-scoped edits.

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-like environment?

Preventing destructive commands in production-like environments requires enforcing combined safety checks that warn before dangerous actions execute. Guard mode activates command-level warnings and directory-scoped restrictions to reduce risk during maintenance or debugging.

How do I restrict file edits to a specific directory during a maintenance window?

Restricting file edits to a specific directory during maintenance requires enabling directory-scoped edit restrictions. Guard mode enforces path limits so accidental changes to critical systems outside the defined scope are blocked before they occur.

What is layered safety for destructive commands and unscoped edits?

Layered safety for destructive commands and unscoped edits combines command-level warnings with directory-scoped restrictions. This approach integrates multiple pre-tool hooks to warn before destructive actions, preventing accidental changes to critical systems.

Can I use guard mode for debugging production-like environments?

Using guard mode for debugging production-like environments is a supported use case. It ensures edits are restricted to a defined path and provides destructive-command warnings, making it suitable for maintenance windows where access must be limited.

Do I need the careful and freeze hook scripts to enforce directory-scoped edits?

Yes, enforcing directory-scoped edits and destructive-command warnings depends on the sibling careful and freeze hook scripts. Guard mode defines pre-tool hooks that build upon these dependencies to provide layered safety during development.