One-click install
npx skills add https://github.com/imonmi/INTER-EDU --skill guard-imonmi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/imonmi/INTER-EDU/tree/main/gstack-main/gstack-main/guard
Command: npx skills add https://github.com/imonmi/INTER-EDU --skill guard-imonmi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This capability reduces risk when performing critical operations by combining destructive-command warnings with a directory-scoped edit boundary, helping teams prevent accidental data loss and unintended changes in sensitive areas.

Core Features & Use Cases

  • Destructive-command warnings: alerts before executing commands like rm -rf, DROP TABLE, or force-push.
  • Edit boundary enforcement: restricts edits to a user-specified directory, blocking changes outside that boundary.
  • Safe-prototyping for prod debugging: enables controlled experimentation while preserving system integrity.

Quick Start

Configure a target directory to protect, then activate guard mode to enable warnings and edit boundaries.

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 modifying my production directory?

To prevent destructive commands in production, you can activate guard mode to warn before executing commands like rm -rf or DROP TABLE. It enforces an edit boundary by restricting modifications to a user-specified directory, blocking changes outside that boundary.

What is an edit boundary and how does it protect sensitive workspaces?

An edit boundary restricts file modifications to a user-specified directory, blocking changes outside that boundary. It protects sensitive workspaces by coordinating pre-check hooks and persistent state to prevent accidental data loss across development environments.

How do I set up a safe prototyping environment for debugging live systems?

Set up safe prototyping for live systems by configuring a target directory to protect, then activating guard mode. This enables controlled experimentation while preserving system integrity through destructive-command warnings and edit boundary enforcement.

Does guard mode work without external dependencies or components?

Yes, guard mode works without external dependencies or components. It independently coordinates pre-check hooks, user prompts to set the freeze directory, and persistent state to enforce the boundary across development environments.

Can I restrict edits to a specific directory when touching production environments?

Yes, you can restrict edits to a specific directory when touching production by configuring a target directory to protect. Guard mode applies edit boundary enforcement to block any changes outside that specified boundary.

What types of commands trigger destructive warnings in workflow security?

Destructive warnings in workflow security trigger before executing commands like rm -rf, DROP TABLE, or force-push. These warnings activate when you are touching prod or debugging live systems to reduce risk of unintended changes.