guard

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

Updated Apr 22, 2026
One-click install
npx skills add https://github.com/diiviikk5/rezops --skill guard-diiviikk5
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/diiviikk5/rezops/tree/main/guard
Command: npx skills add https://github.com/diiviikk5/rezops --skill guard-diiviikk5

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Guard mode provides a unified safety layer that warns about destructive commands and enforces a directory-boundary to prevent accidental production edits, reducing the risk of high-impact mistakes during maintenance or debugging.

Core Features & Use Cases

  • Destructive command warnings: Intercepts and warns on dangerous commands (e.g., rm -rf, DROP TABLE, force-push) before execution.
  • Edit boundary enforcement: Restricts file edits to a user-specified directory, blocking edits outside the boundary.
  • Use Case: Use during critical production changes or debugging sessions to minimize inadvertent damage and enforce change-control discipline.

Quick Start

Ask for the directory to restrict edits to, then activate guard mode to enable 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 production maintenance?

To prevent accidental destructive commands during production maintenance, you can enforce strict change-control warnings. This safety mode intercepts dangerous commands like rm -rf or DROP TABLE and requires explicit user confirmation before execution.

Can I restrict file edits to a specific directory boundary?

Yes, you can restrict file edits to a specific directory boundary. By setting a user-specified directory path, the system blocks any file modifications attempted outside of that defined edit boundary.

What is the best way to enforce change-control discipline during debugging sessions?

The best way to enforce change-control discipline during debugging sessions is activating a unified safety layer. This approach combines destructive command warnings with directory-boundary enforcement to minimize inadvertent damage to production systems.

Does this safety mode warn before executing force-push or database drop commands?

Yes, this safety mode warns before executing force-push or database drop commands. It actively intercepts high-risk destructive actions, ensuring you receive a warning and must confirm before the command proceeds.

How do I set up an edit boundary to block production file modifications?

To set up an edit boundary that blocks out-of-scope production file modifications, you provide a target directory path upon activation. The system then enforces this boundary, restricting all edits strictly to your defined directory.

When should I use a destructive command warning system for production systems?

You should use a destructive command warning system during high-risk maintenance on production systems or critical debugging sessions. It provides a strict change-control workflow that reduces the risk of high-impact mistakes.