guard

Prevents unsafe edits and destructive commands on sensitive systems via directory-boundary restrictions.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/Andy-HNU/AndyClaw --skill guard-andy-hnu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/Andy-HNU/AndyClaw/tree/main/skills/gstack-guard
Command: npx skills add https://github.com/Andy-HNU/AndyClaw --skill guard-andy-hnu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents unsafe edits and destructive commands from affecting sensitive systems.

Core Features & Use Cases

  • Warns before destructive commands (rm -rf, DROP TABLE, etc.).
  • Enforces an edit boundary so changes stay within a chosen directory.
  • Integrates with careful and freeze hooks to provide end-to-end protection in prod or debugging sessions.

Quick Start

Specify a directory to restrict edits to and activate guard mode.

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 from running in a production environment?▼

To prevent destructive commands in a production environment, you need a safety guardrail that intercepts and warns before executing unsafe commands like rm -rf or DROP TABLE. This Skill activates guard mode to block these operations and protect sensitive systems.

Can I restrict file edits to a specific directory boundary during live debugging?▼

Yes, you can restrict file edits to a specific directory boundary during live debugging by setting a boundary path. The guard enforces this directory-boundary restriction so all changes stay within your chosen folder.

What is the best way to add safety guardrails for shell commands and file edits?▼

The best way to add safety guardrails for shell commands and file edits is to activate a guard mode that integrates with careful and freeze hooks. This provides end-to-end protection by warning before destructive commands and enforcing edit boundaries.

Does this production safety guard work with existing careful and freeze hooks?▼

Yes, this production safety guard coordinates directly with existing careful and freeze hooks. Integrating with these hooks provides end-to-end protection during debugging sessions and production environments.

How do I set up edit control to protect sensitive systems from accidental modifications?▼

To set up edit control for sensitive systems, specify a target directory to restrict edits to and activate guard mode. This stores the boundary path and enforces directory-boundary restrictions to prevent accidental modifications outside that area.