safety-guard

Restricts file system writes and intercepts destructive shell commands in guarded modes.

1|Updated Apr 6, 2026

Search Tags:#automation #security #safety #risk-management #guardrails

Ready to run

npx skills add https://github.com/vrcms/everything-qwen-code --skill safety-guard-vrcms

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: safety-guard
Source: https://github.com/vrcms/everything-qwen-code/tree/main/.qwen/skills/safety-guard
Command: npx skills add https://github.com/vrcms/everything-qwen-code --skill safety-guard-vrcms

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill prevents accidental destructive commands and unauthorized file modifications, ensuring system integrity during autonomous agent operations or sensitive production tasks.

Core Features & Use Cases

Careful Mode: Intercepts and warns against dangerous commands like rm -rf, git push --force, or database drops.
Freeze Mode: Restricts agent write access to specific directory trees, preventing accidental changes to unrelated code.
Guard Mode: Combines protection layers for maximum safety during autonomous execution.

Quick Start

Activate the safety guard in careful mode to monitor all terminal commands for destructive patterns.

Frequently Asked Questions about safety-guard

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

FAQPage Schema

How do I prevent destructive shell commands during autonomous agent operations?▼

To prevent destructive shell commands during autonomous agent operations, you need pre-execution interception of terminal commands. This mechanism intercepts dangerous patterns like rm -rf or git push --force to ensure operational safety before execution.

What is the best way to restrict file system write access to specific directory scopes?▼

The best way to restrict file system write access to specific directory scopes is by using a freeze mode. This feature restricts agent write access to defined directory trees, preventing accidental modifications to unrelated code during sensitive refactoring tasks.

Can I use safety guardrails for autonomous code refactoring in production environments?▼

Yes, you can use safety guardrails for autonomous code refactoring in production environments. This skill applies specifically to production environment maintenance and sensitive code refactoring tasks by combining protection layers for maximum safety during execution.

How do I monitor terminal commands for dangerous execution patterns?▼

To monitor terminal commands for dangerous execution patterns, activate careful mode. This mode monitors all terminal commands for destructive patterns and warns against dangerous operations like database drops to maintain system integrity.

Does guard mode combine protection layers for autonomous execution workflows?▼

Yes, guard mode combines protection layers for autonomous execution workflows. It intercepts destructive system operations and restricts file system write access simultaneously to provide maximum safety during autonomous agent execution.

When should I not use automated command interception for risk management?▼

You should not use automated command interception for risk management when running trusted local scripts that require unimpeded write access or rapid unmonitored execution. The interception layer is designed for sensitive production environments where operational safety outweighs execution speed.