guard

Enforce destructive-command warnings and directory-bound edit restrictions.

1|Updated May 6, 2026
One-click install
npx skills add https://github.com/yckkkk/reo --skill guard-yckkkk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/yckkkk/reo/tree/main/.agents/skills/guard
Command: npx skills add https://github.com/yckkkk/reo --skill guard-yckkkk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides guard rails to prevent accidental destructive actions and unauthorized edits by combining destructive command warnings with a directory-bound edit restriction.

Core Features & Use Cases

  • Destructive-command warnings that prompt before executing dangerous operations.
  • Directory-bound edits enforced via a user-defined freeze boundary.
  • Integration with the /careful and /freeze workflows to secure prod and debugging environments.

Quick Start

Ask the user which directory to protect, then enable both destructive-command warnings and a directory edit boundary for that path.

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 from executing in a production environment?

Preventing accidental destructive commands is achieved by enforcing guard rails that prompt the user before executing dangerous operations. This skill secures production and debugging environments by warning operators prior to running any destructive action.

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

Restricting file edits to a specific directory boundary is supported by defining a user-protected freeze path. The skill enforces this directory-bound edit restriction to prevent unauthorized edits outside the approved folder.

How do destructive command warnings and edit boundaries work together to secure data?

Destructive command warnings and directory-bound edit boundaries work together by combining execution prompts with path restrictions. This integrated mechanism prevents operators from deleting data or editing outside approved folders during development and production debugging.

Do I need to specify a directory before enabling edit protection?

Specifying a protected directory is required before enabling edit protection. The skill prompts you to define the freeze boundary path, then applies both destructive-command warnings and directory edit restrictions to secure that specific location.

What is the best way to add safety guard rails for unauthorized file edits?

Adding safety guard rails for unauthorized file edits is best handled by combining destructive-command warnings with a directory-bound restriction. This approach secures approved folders by integrating careful and freeze workflows to validate operations.

Does this guard skill integrate with existing careful and freeze workflows?

Integrating with existing careful and freeze workflows is supported by referencing the sibling scripts directly. The skill implements checks that call these workflows to secure production and debugging environments against destructive actions.