guard

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

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/soyasis/gstack-private --skill guard-soyasis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/soyasis/gstack-private/tree/main/guard
Command: npx skills add https://github.com/soyasis/gstack-private --skill guard-soyasis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety".

Core Features & Use Cases

  • Destructive command warnings before executing dangerous operations.
  • Edit boundary enforcement restricting edits to a user-specified directory.
  • Dependency note: references to sibling /careful and /freeze scripts required.

Quick Start

Activate guard mode by specifying a target directory and running the guard command to enable both 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 from running in a production environment?

Preventing destructive commands in production requires full safety mode with destructive-command warnings. This mechanism intercepts dangerous operations like rm -rf, DROP TABLE, or force-push and warns before execution.

How do I restrict file edits to a specific directory during live system debugging?

Restricting file edits to a specific directory during live system debugging requires edit boundary enforcement. You lock down edits to a chosen path, blocking any modifications outside that user-specified directory.

Do I need the /careful and /freeze scripts to enable guard mode?

Yes, enabling guard mode requires sibling /careful and /freeze scripts. Guard mode validates their presence to combine destructive-command warnings with directory-scoped edit restrictions for end-to-end protection.

What is directory-based edit restriction for safe development workflows?

Directory-based edit restriction for safe development workflows is an isolation mechanism that blocks edits outside a specified path. It enforces safe isolation by locking down modifications to a chosen directory during operations.

Can I use full safety mode for both development and operations workflows?

Yes, full safety mode applies during both development and operations workflows where safe isolation is required. It enforces destructive-command warnings and directory-based edit restrictions simultaneously across these environments.

What destructive commands trigger warnings in guard mode?

Destructive commands that trigger warnings in guard mode include rm -rf, DROP TABLE, and force-push. The safety mechanism warns before executing these dangerous operations to protect production environments.