guard

Enforces directory-boundary edit restrictions and warns on destructive commands for development and debug sessions.

2|Updated May 8, 2026
One-click install
npx skills add https://github.com/xotong/claude-marketplace --skill guard-xotong
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/xotong/claude-marketplace/tree/main/plugins/gstack/skills/guard
Command: npx skills add https://github.com/xotong/claude-marketplace --skill guard-xotong

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables maximum safety during development by warning on destructive commands and constraining edits to a defined directory boundary.

Core Features & Use Cases

  • Destructive-command warnings: alerts before rm -rf, DROP TABLE, force-push, or other destructive actions.
  • Directory-boundary enforcement: blocks edits outside a specified path to prevent accidental changes in prod or sensitive areas.
  • Safe workflow integration: pairs with /careful and /freeze to provide a unified guard mode across development tasks.

Quick Start

Activate guard mode by enabling safety checks and setting the freeze boundary for the current workspace in a single, straightforward step.

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 force-push or DROP TABLE during development?

To prevent destructive commands like force-push or DROP TABLE, you need a safety guard that intercepts and warns before these actions execute. This Skill enforces guard mode to alert you on dangerous operations during development and production-debugging sessions.

How do I restrict file edits to a specific directory to avoid accidental changes in production?

Restricting file edits to a specific directory requires setting a directory-boundary that blocks any modifications outside a designated path. This Skill loads the boundary for edit restrictions before tool usage, preventing accidental changes in sensitive areas.

What is directory-boundary enforcement and how does it work for safe workflows?

Directory-boundary enforcement is a safety mechanism that blocks edits outside a specified path to prevent accidental changes. It works by loading the boundary for edit restrictions before tool usage, pairing with careful and freeze subsystems for unified guard mode across development tasks.

Can I integrate guard mode with existing careful and freeze subsystems for devops safety?

Yes, you can integrate guard mode with existing careful and freeze subsystems for devops safety. This Skill is specifically designed to satisfy requirements for integration with careful and freeze subsystems, providing a unified safety workflow across development tasks.

How do I activate guard mode to set safety checks and freeze boundaries in my workspace?

To activate guard mode for safety checks and freeze boundaries, enable the safety checks and set the freeze boundary for the current workspace in a single step. This straightforward activation prepares the environment to warn on destructive operations and restrict edits.