guard

Warn about destructive commands and restrict edits to a designated directory.

Updated Mar 27, 2026

Search Tags:#risk-mitigation #destructive-warnings #edit-boundary #production-protection #devops-safety #guard-mode

Ready to run

npx skills add https://github.com/AlejandroFigini/artist-portfolio --skill guard-alejandrofigini

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/AlejandroFigini/artist-portfolio/tree/main/.agent/skills/guard
Command: npx skills add https://github.com/AlejandroFigini/artist-portfolio --skill guard-alejandrofigini

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The guard skill provides a dual safety layer that warns about destructive commands and confines edits to a specified directory to prevent accidental data loss or unintended changes in production or live environments.

Core Features & Use Cases

Destructive command warnings to prompt before executing dangerous operations (rm -rf, DROP etc.).
Directory-boundary edits enforcement to restrict edits to a user-specified path.
Compatibility with existing safety tooling like /careful and /freeze for end-to-end protection in devops workflows.
Use Case: when deploying to production or debugging live systems, you can enable guard mode to reduce risk.

Quick Start

Activate guard mode to enable destructive-command warnings and directory-boundary edits.

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 during production deployments?▼

To prevent data loss during production deployments, activate guard mode to enable destructive-command warnings and restrict file edits to a designated directory boundary.

Can I restrict file edits to a specific directory when debugging live systems?▼

Yes, you can restrict edits to a specific directory by setting a designated path, which enforces an edit boundary to prevent unintended changes across your live systems.

How do destructive command warnings work for operations like rm -rf or DROP?▼

Destructive command warnings use pre-hook scripts for command validation, prompting you before executing dangerous operations like rm -rf or DROP to mitigate risk.

Does guard mode work with existing DevOps safety tools like careful and freeze?▼

Yes, guard mode is compatible with existing safety tooling like careful and freeze, providing end-to-end protection and complementing your devops workflows.

When should I enable guard mode in my development to production workflow?▼

You should enable guard mode when deploying to production or debugging live systems, creating a dual safety layer that reduces the risk of accidental data loss.

What are the limitations of using directory-boundary enforcement for edit protection?▼

Directory-boundary enforcement relies on pre-hook scripts for validation and restricts edits to a single specified path, meaning it does not protect files outside that designated directory boundary.