guard

Block destructive commands and enforce per-directory edit boundaries.

107|19|Updated Mar 23, 2026

Search Tags:#devops #safety #risk-mitigation #guard #destructive-commands #freeze-boundary #directory-restriction

Ready to run

npx skills add https://github.com/mr-daedalium/ostack --skill guard-mr-daedalium

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/mr-daedalium/ostack/tree/main/guard
Command: npx skills add https://github.com/mr-daedalium/ostack --skill guard-mr-daedalium

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Protects live environments from destructive commands and unintended edits by enforcing a directory-based edit boundary and warning before dangerous operations.

Core Features & Use Cases

Destructive command warnings: alerts and blocks for risky commands like rm -rf, DROP TABLE, force-push, etc.
Directory-boundary enforcement: restricts edits to a user-specified path to prevent accidental changes outside safe areas.
Safe-debug workflow: ideal during prod maintenance, incident response, or sensitive deployments to minimize human error.

Quick Start

Use guard mode to set a freeze boundary for a target directory and enable destructive-command warnings.

Frequently Asked Questions about guard

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

FAQPage Schema

How do I prevent destructive commands like rm -rf from running in a production environment?▼

To prevent destructive commands, this safety mode intercepts and blocks risky operations like rm -rf, DROP TABLE, and force-push before execution. It relies on hook scripts to warn you, protecting live systems during incident response, debugging, or sensitive deployments from unintended human error.

What is a directory-boundary restriction and how does it protect live systems?▼

A directory-boundary restriction enforces a user-specified edit path to prevent accidental changes outside safe areas. By setting a freeze boundary, it restricts file modifications to a designated safe directory, protecting live environments from unintended edits during sensitive deployments.

How do I set a freeze boundary to restrict edits to a specific directory?▼

Setting a freeze boundary involves activating guard mode to target a specific directory and enable destructive-command warnings. This configuration restricts all edits to the user-specified safe path, preventing accidental modifications to files outside the designated boundary during prod maintenance.

Can I use directory-boundary enforcement during incident response on live servers?▼

Yes, directory-boundary enforcement is ideal for safe-debug workflows during incident response and prod maintenance. It minimizes human error by restricting edits to a safe path and warning before dangerous operations, ensuring live server environments remain protected.

Does this destructive command blocker require any dependencies or external components?▼

No external dependencies or components are required. The destructive command blocker relies entirely on internal /careful and /freeze hook scripts to perform checks, enforce directory boundaries, and block risky operations without needing additional installed packages.

What are the limitations of using a per-directory edit boundary for risk mitigation?▼

The limitation of a per-directory edit boundary is that protection only applies within the specified freeze boundary path. Edits or destructive commands targeting areas outside the user-specified safe directory may not be intercepted by the hook scripts.