guard

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

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/jm199seo/lostark-accessory-viewer --skill guard-jm199seo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/jm199seo/lostark-accessory-viewer/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/jm199seo/lostark-accessory-viewer --skill guard-jm199seo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents destructive commands from running unchecked and restricts edits to a defined directory, reducing risk in production and live debugging.

Core Features & Use Cases

  • Destructive command warnings for dangerous operations (rm -rf, DROP TABLE, force-push, etc.)
  • Directory-bound edit restrictions enforced via a runtime boundary
  • Simple setup that prompts for a directory and activates safety rails across workflows

Quick Start

Ask the user to specify a directory to restrict edits to, then Guard mode activates both destructive-command warnings and the edit boundary.

Frequently Asked Questions about guard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I block destructive commands like rm -rf during live debugging?

To block destructive commands during live debugging, you need a safety mode that warns on risky operations like force-push or DROP TABLE. This skill enforces those safety rails by intercepting dangerous commands before they execute.

Can I restrict file edits to a specific directory in production?

Yes, you can restrict file edits to a specific directory in production by defining a runtime boundary. This skill prompts for a target directory and actively blocks any unintended edits outside that defined scope.

What is directory-bound edit protection and how does it work?

Directory-bound edit protection is a safety mechanism that restricts file modifications to a predefined path. It works by establishing a runtime boundary that checks edits against your specified directory and blocks any changes outside it.

How do I set up guard mode for development workflows?

To set up guard mode for development workflows, specify the directory you want to restrict edits to. Once the directory is defined, the safety rails activate automatically to warn on destructive commands and enforce the boundary.

Does this safety mode work with database operations like DROP TABLE?

Yes, this safety mode works with database operations by warning on destructive commands like DROP TABLE. It applies to development, production, and debugging workflows to prevent risky operations from running unchecked.