Msapps Sosa Governor
Plugin Verified ActiveSOSA governance engine โ enforce supervision policies, trust gradients, and capability boundaries on AI agent actions in real time
To provide real-time enforcement of governance policies, ensuring AI agent actions adhere to defined trust gradients and capability boundaries.
Features
- Enforce supervision policies
- Manage trust gradients
- Define capability boundaries
- Real-time action enforcement
Use Cases
- Preventing AI agents from exceeding their authorized capabilities
- Ensuring AI agent interactions remain within defined ethical and safety guidelines
- Monitoring and logging AI agent actions against predefined governance rules
- Establishing trust levels for AI agent interactions in complex workflows
Non-Goals
- Providing AI agent tools or functionalities directly
- Acting as a primary AI agent or conversational interface
- Replacing core AI agent decision-making logic
Installation
/plugin install msapps-sosa-governor@davepoon-buildwithclaudeQuality Score
VerifiedSimilar Extensions
Review Agent Governance
99Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.
Protect Mcp
98Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin โ receipts independently verifiable offline.
Dotforge
100Node.js 20+ with Express/Fastify, TypeScript, and ESM module rules for Claude Code.
Oh My Claudecode
99Multi-agent orchestration system for Claude Code
Worktrunk
99Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths) and automatic activity tracking (๐ค/๐ฌ indicators in `wt list` showing active Claude sessions).
Cc Safe Setup
99734 safety hooks for Claude Code โ prevent file deletion, credential leaks, git disasters, and token waste during autonomous AI coding sessions