action-class-policy

Official

Tiered action policies for safe agent autonomy

Authorm2ai-portfolio
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Governs autonomous agent behavior by defining clear action classes and escalation rules to prevent unsafe or unauthorized actions.

Core Features & Use Cases

  • Tiered action-class design with four levels (Read-Only, Write with Review, Production Mutation, Infrastructure Change) to map blast radii to real-world permissions.
  • Generates a formal policy document that includes classifications, approvals, rollback steps, and monitoring expectations.
  • Useful for teams deploying AI agents in production who need explicit governance, audits, and compliance alignment.

Quick Start

Provide a tiered action-class policy document tailored to your systems and governance needs.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: action-class-policy
Download link: https://github.com/m2ai-portfolio/m2ai-skills-pack/archive/main.zip#action-class-policy

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.