gstack-guard

Warn on destructive commands and restrict edits to a specified directory.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/tayiorbeii/paperclip-factory-kit --skill gstack-guard-tayiorbeii
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gstack-guard
Source: https://github.com/tayiorbeii/paperclip-factory-kit/tree/main/skills/gstack-guard
Command: npx skills add https://github.com/tayiorbeii/paperclip-factory-kit --skill gstack-guard-tayiorbeii

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents dangerous mistakes during debugging or production-adjacent changes by warning before destructive commands and blocking edits outside a chosen directory.

Core Features & Use Cases

  • Destructive command warnings: Detects and warns on high-risk operations like rm -rf, DROP TABLE, and force-push so you can override intentionally.
  • Directory-scoped edit freeze: Restricts file edits to a user-specified path, blocking edits outside the allowed boundary.
  • Use Case: When asked to “guard mode” or maximum safety, you can safely iterate on a restricted workspace without risking broader filesystem or database damage.

Quick Start

Activate guard mode by asking the AI to run gstack-guard and then provide the directory path you want edits restricted to.

Frequently Asked Questions about gstack-guard

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

FAQPage Schema
How do I prevent accidental destructive commands during production debugging?

To prevent destructive commands during production debugging, enable a safety mode that detects high-risk operations like rm -rf, DROP TABLE, and force-push, warning you before execution. This allows you to override intentionally while protecting the live system.

Can I restrict file edits to a specific directory to avoid broad filesystem changes?

Yes, you can restrict file edits to a specific directory by enforcing directory-scoped edit freeze boundaries. This blocks any read, edit, or write operations outside your chosen path, preventing accidental broad filesystem damage during maintenance.

What is guard mode for incident prevention and how does it work?

Guard mode is a full safety configuration for incident prevention that combines destructive-command warnings with directory-scoped edit restrictions. It runs pre-tool checks for destructive commands and enforces freeze-boundary checks on file operations to ensure safe workspace iteration.

How do I activate directory freeze boundaries for safe editing?

To activate directory freeze boundaries, initiate guard mode and provide the specific directory path you want edits restricted to. The system then enforces freeze-boundary checks for any subsequent read, edit, or write operations within that workspace.

Does guard mode work for production-adjacent maintenance workflows?

Yes, guard mode is explicitly designed for production-adjacent maintenance and live-system debugging. It restricts file edits to a user-specified path and warns on high-risk operations, ensuring you can safely iterate without risking broader filesystem or database damage.

What destructive commands are caught by filesystem protection warnings?

Filesystem protection warnings catch high-risk operations such as rm -rf, DROP TABLE, and force-push. When these destructive commands are detected, the system warns you so you can override the action intentionally and prevent accidental data loss.