jon-jones-guardian

Review and manage outbound actions with trust and safety checks.

Updated Feb 7, 2026
One-click install
npx skills add https://github.com/BelichickGillisMusk/belichick-margo-jesus --skill jon-jones-guardian
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jon-jones-guardian
Source: https://github.com/BelichickGillisMusk/belichick-margo-jesus/tree/main/skills/jon-jones-guardian
Command: npx skills add https://github.com/BelichickGillisMusk/belichick-margo-jesus --skill jon-jones-guardian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill acts as the final defense against external actions that could potentially harm the system or violate security protocols.

Core Features & Use Cases

  • Trust Model: Differentiates between trusted internal actions and potentially harmful external actions.
  • Outbound Action Review: Manages and reviews all actions that touch the outside world, ensuring compliance and security.
  • Decision Framework: Provides a structured approach to reviewing, rewriting, blocking, or escalating actions based on risk level.
  • Auto-Approve Rules: Allows for rapid approval of low-risk actions that meet specific criteria.
  • Escalation Rules: Ensures high-risk actions always require human approval for added security.
  • Email and Slack Handling: Specifically designed for managing email and Slack communications securely.
  • File Security: Implements strict control over file access and sharing, including sensitive documents.
  • Stop Mode: Temporarily halts all outbound actions in case of emergency, allowing for system review.

Quick Start

Use the jon-jones-guardian skill to review and send an outbound email to '[email protected]'.

Frequently Asked Questions about jon-jones-guardian

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

FAQPage Schema
How do I review and manage outbound actions before they execute?

Reviewing outbound actions involves applying a trust model to differentiate between safe internal tasks and potentially harmful external actions. You can manage these actions using a structured decision framework to review, rewrite, block, or escalate them based on their specific risk level.

How does a trust model work for securing external system actions?

A trust model for external actions works by classifying tasks as either trusted internal operations or potentially harmful external communications. It coordinates with an admin and applies safety checks to ensure system integrity before allowing any external action to proceed.

How do I set up auto-approve rules for low-risk outbound actions?

You can set up auto-approve rules to rapidly clear low-risk outbound actions that meet specific predefined criteria. This allows safe external actions to proceed quickly while ensuring high-risk actions are escalated for mandatory human approval.

Can I temporarily block all outbound external actions during a security review?

Yes, you can temporarily block all outbound external actions by activating a Stop Mode. This emergency feature halts all external communications, including email and Slack handling, allowing you to safely conduct a full system review.

What is the best way to secure email and Slack communications from unauthorized access?

Securing email and Slack communications requires implementing strict outbound action management with an admin-coordinated trust model. This ensures all outbound messages undergo safety checks and risk-level reviews before they are allowed to proceed.

How do I implement strict file access control for sensitive documents?

Implementing strict file security involves managing file access and sharing through an outbound action review process. This applies structured safety checks to prevent unauthorized external sharing of sensitive documents based on a defined trust model.