guard

Warn and block destructive commands and edits outside a safe directory boundary.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/SakshamKandel/Salt-Route-Consulting- --skill guard-sakshamkandel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/SakshamKandel/Salt-Route-Consulting-/tree/main/.agents/skills/guard
Command: npx skills add https://github.com/SakshamKandel/Salt-Route-Consulting- --skill guard-sakshamkandel

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides dual protection by issuing destructive-command warnings and enforcing a directory edit boundary to prevent accidental damage in critical environments.

Core Features & Use Cases

  • Destructive command warnings warn before executing dangerous commands like rm -rf, DROP TABLE, or force-push, helping prevent accidental data loss.
  • Edit boundary enforcement restricts file edits to a user-specified directory, adding a strong safeguard during live deployments, debugging, and production work.
  • Use Case: When performing risky operations on prod or during debugging live systems, enable /guard to ensure operations stay within safe limits.

Quick Start

Guard mode by enabling destructive-command warnings and a directory edit boundary.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I prevent accidental data loss from destructive commands like rm -rf during production deployments?

Pre-tool hook safety checks prevent accidental data loss by warning and blocking destructive commands like rm -rf or force-push before execution. This mechanism intercepts risky operations during critical development and production tasks to safeguard your 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 to enforce safe limits during live debugging. By defining a user-specified directory, the safeguard blocks any unauthorized file modifications outside that boundary.

How do pre-tool hooks work for blocking unsafe operations?

Pre-tool hooks work by running safety checks before tool execution to intercept and block unsafe operations. They coordinate with sibling safety skills to enforce directory boundaries and prevent destructive commands from modifying critical systems.

What is the best way to enforce safety boundaries when touching critical systems?

The best way to enforce safety boundaries is by applying dual protection: issuing warnings for destructive commands and restricting edits to a user-specified directory. This prevents accidental damage in critical production environments and live deployments.

Does the edit boundary safeguard work for both development and production tasks?

Yes, the edit boundary safeguard works for both development and production tasks that touch critical systems. It restricts file modifications to a safe directory, preventing accidental damage during live deployments and local debugging.