guard

Enforce guard mode to block destructive commands and restrict edits to a chosen directory.

15|1|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/howdeploy/NekoFree --skill guard-howdeploy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/howdeploy/NekoFree/tree/main/skills/guard
Command: npx skills add https://github.com/howdeploy/NekoFree --skill guard-howdeploy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Guard mode prevents accidental data loss and disruptive edits by combining destructive-command warnings with directory-scoped edit restrictions, ensuring safe operations in critical environments.

Core Features & Use Cases

  • Destructive command warnings protect against rm -rf, DROP TABLE, and force-push in sensitive contexts.
  • Directory-bound edits restrict changes to a user-selected path, preventing edits outside the boundary.
  • Pre-tool checks automatically enforce safety by delegating to sibling careful and freeze scripts when preparing actions.

Quick Start

Ask to enable guard mode and specify the directory to protect, then let it enforce the boundary and warnings automatically.

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 commands like rm -rf during shell operations?

To prevent accidental destructive commands like rm -rf during shell operations, you can enable guard mode to enforce safety warnings and block risky actions. It intercepts commands during shell operations and debugging sessions to protect against data loss.

Can I restrict file edits to a specific directory boundary in production environments?

Yes, you can restrict file edits to a specific directory boundary in production environments by applying a persistent freeze boundary. This confines changes to your selected path and prevents unwanted modifications outside that directory.

What is the best way to add pre-tool checks for production security without modifying core scripts?

The best way to add pre-tool checks for production security without modifying core scripts is to leverage Bash hooks. Guard mode delegates safety checks to sibling careful and freeze scripts, intercepting actions before execution.

How do I set up a persistent freeze boundary using state files for safe debugging sessions?

To set up a persistent freeze boundary using state files for safe debugging sessions, enable guard mode and specify your target directory. The system maintains the restriction in state files while delegating enforcement to freeze scripts.

Does guard mode work with force-push and DROP TABLE commands in sensitive contexts?

Yes, guard mode works with force-push and DROP TABLE commands in sensitive contexts by applying destructive command warnings. It automatically detects and warns before these risky operations execute, ensuring production security.