guard

Block destructive commands and edits outside a defined directory during deployments.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/mrkhachaturov/rkstack --skill guard-mrkhachaturov
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/mrkhachaturov/rkstack/tree/main/skills/guard
Command: npx skills add https://github.com/mrkhachaturov/rkstack --skill guard-mrkhachaturov

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Full safety mode combines destructive command warnings with directory-scoped edit restrictions to protect prod and debugging efforts.

Core Features & Use Cases

  • Destructive command warnings: detects dangerous commands such as rm -rf, DROP TABLE, force-push, and warns before executing.
  • Edit boundary enforcement: restricts edits to a user-defined directory, blocking changes outside the boundary.
  • Safe collaboration and workflow integration: enforces protections during sensitive operations across sessions.

Quick Start

Ask which directory to protect and then activate guard mode to enforce protections.

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 like rm -rf or DROP TABLE during live deployments?

To prevent destructive commands during live deployments, you need a safety mode that detects dangerous commands like rm -rf or DROP TABLE and warns before executing. This guard Skill enforces those destructive command warnings to protect production environments.

How can I restrict file edits to a specific directory during critical debugging operations?

You can restrict file edits to a specific directory by applying edit boundary enforcement. This guard Skill blocks any unauthorized edits outside your user-defined directory, ensuring debugging efforts remain scoped and safe.

What is directory-scoped edit restriction and when do I need it?

Directory-scoped edit restriction is a safety mechanism that blocks file changes outside a defined boundary. You need it during sensitive operations like live deployments to prevent accidental modifications to critical system files outside the guard boundary.

Do I need additional components to enforce edit boundaries and command warnings?

Yes, enforcing edit boundaries and command warnings requires integration with the careful and freeze components. These components work together with the guard Skill within the rkstack-plugin ecosystem to apply full safety boundaries during critical operations.

How do I activate safety mode to protect a specific production directory?

To activate safety mode, specify which directory to protect and then enable guard mode. This initiates both destructive command warnings and edit boundary enforcement to secure your production files safely.