guard

Warn before destructive shell commands and restrict edits to a protected directory.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/hetsheth-droid/toolbox-template --skill guard-hetsheth-droid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/hetsheth-droid/toolbox-template/tree/main/incubating/gstack/guard
Command: npx skills add https://github.com/hetsheth-droid/toolbox-template --skill guard-hetsheth-droid

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enforces safety during shell interactions by combining destructive-command warnings with directory-bound edit restrictions to prevent accidental damage.

Core Features & Use Cases

  • Combines destructive-command warnings with a configurable edit boundary to block risky actions outside a protected directory.
  • Integrates with the existing careful and freeze skills to provide a unified guardrail during critical operations.
  • Use Case: When working on production or debugging live systems, enable guard to get warnings before destructive commands and enforce edits only within a safe path.

Quick Start

Activate guard mode to enable both destructive-command warnings and edit-boundary protections.

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 bash commands when modifying production systems?

To prevent accidental destructive bash commands on production systems, enable a safety mode that triggers warnings before risky shell interactions execute. This combines directory-bound edit restrictions with pre-tool hooks to block dangerous actions outside protected paths.

What are destructive-command warnings and how do they work in bash scripts?

Destructive-command warnings in bash scripts are pre-tool checks that intercept and warn against risky shell interactions before execution. They enforce safety by requiring confirmation for commands that could accidentally damage live environments or critical data.

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 applying freeze boundary protections. This enforces edits only within a configured safe path, preventing accidental modifications to files outside that protected directory.

Do I need any other skills to use directory-bound edit protection in team workflows?

Yes, directory-bound edit protection requires the sibling careful and freeze skills to function properly. These integrate with the main safety mode to provide a unified guardrail during critical operations and team workflows using gstack.

What is the best way to enforce edit boundaries and risk mitigation across team workflows?

The best way to enforce edit boundaries and risk mitigation across team workflows is to combine destructive-command warnings with directory-bound restrictions. Activating a full safety mode applies pre-tool hooks to enforce checks before any destructive actions or edits occur.