skills.rest
MissTully
MissTullyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

guard

Warn on destructive commands and block edits outside a guarded directory.

Updated Apr 24, 2026
Search Tags:#safety#ai-assisted#guard#destructive-commands#edit-boundaries#live-systems
One-click install
npx skills add https://github.com/MissTully/Gstack --skill guard-misstully
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/MissTully/Gstack/tree/main/guard
Command: npx skills add https://github.com/MissTully/Gstack --skill guard-misstully

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides dual protection by warning on destructive commands and enforcing a directory-bound edit policy, reducing the risk of accidental damage in production or debugging sessions.

Core Features & Use Cases

  • Combines destructive command warnings with an edit boundary to guard critical environments.
  • Applies during live maintenance, debugging prod systems, or AI-assisted workflows where risky commands may be issued.
  • Supports setting a user-specified directory boundary to restrict edits and block unintended changes.

Quick Start

Activate guard mode by configuring a directory boundary and enabling both protections in your session.

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 during live system administration?▼

To prevent accidental destructive commands during system administration, you can activate guard mode to issue warnings on risky commands and enforce directory-bound edit policies. This dual protection reduces the risk of accidental damage in production environments.

What is a directory-bound edit policy for AI-assisted operations?▼

A directory-bound edit policy restricts file modifications to a user-specified boundary, blocking unintentional edits outside the guarded directory. This mechanism protects critical environments during AI-assisted workflows and live debugging sessions.

Can I set a specific directory boundary to block unintended changes in production?▼

Yes, you can set a user-specified directory boundary to block unintended changes in production. Configuring this boundary restricts edits to the specified area, safeguarding the rest of the live system from accidental modification.

How do I configure edit boundaries and destructive command warnings in my session?▼

To configure edit boundaries and destructive command warnings, activate guard mode by setting a directory boundary and enabling both protections in your session. This integrates with sibling hooks to enforce the safety protections.

Does guard mode work with sibling hooks for live debugging protections?▼

Yes, guard mode works with sibling careful and freeze hooks to set directory boundaries and enforce protections during live debugging. Integrating these hooks provides comprehensive dual protection against destructive commands and out-of-bound edits.

Related Skills

Explore More Software Engineering Skills→
ResearAIResearAI
3.3k

baseline

Standardize a reference object for quest evaluation with plan and checklist requirements.

Community
Advanced
adryanmoldokkr32-pixeladryanmoldokkr32-pixel

guard

Restrict edits to a defined directory and warn before destructive commands.

Community
Intermediate
I194I194
9

guard

Block destructive commands and edits outside a specified directory.

Community
Intermediate
DicklesworthstoneDicklesworthstone
70

dcg

Block destructive Git and filesystem commands in Claude Code workflows.

Community
Advanced