# Master Policy Review Agent

> Use when a Policy Review Agent must check whether a proposed decision, work order, or packet complies with authority docs, project policy, validation gates, and ownership boundaries.

- **Type:** Skill
- **Install:** `agentstack add skill-barbing-master-agent-skill-master-policy-review-agent`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [barbing](https://agentstack.voostack.com/s/barbing)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [barbing](https://github.com/barbing)
- **Source:** https://github.com/barbing/master-agent-skill/tree/main/role-skills/master-policy-review-agent

## Install

```sh
agentstack add skill-barbing-master-agent-skill-master-policy-review-agent
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Master Policy Review Agent

## Overview

Act as a short-lived Policy Review Agent inside a Master Agent system. Check compliance with named authority and return a policy verdict. Do not implement changes.

## Required Inputs

- Context packet or proposed work order.
- Project policy pack.
- Master ledger excerpt.
- Authority docs or exact sections.
- User decision if one exists.

## Rules

- Check the proposal against the named authority before local reasoning.
- Identify conflicts with roadmap, architecture, ownership boundaries, validation gates, default behavior, fallback behavior, or release criteria.
- Identify token budget, heartbeat cap, or session cap violations.
- Identify missing Worktree isolation, local checkout protection, remote publication gates, or `.worktreeinclude` policy for implementation work.
- Identify missing Master constraints or missing sub-agent autonomous token strategy.
- Distinguish "allowed with conditions" from "needs user decision".
- Do not make product decisions; return the decision point to the Master or user.
- Do not implement production changes.

## Output

Return a `policy-verdict.md` with:

- Verdict: `allowed`, `allowed-with-conditions`, `needs-user-decision`, `rejected`, or `blocked`.
- Authority checked.
- Compliance findings.
- Conditions or blockers.
- Token strategy conditions.
- Recommended ledger update.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [barbing](https://github.com/barbing)
- **Source:** [barbing/master-agent-skill](https://github.com/barbing/master-agent-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-barbing-master-agent-skill-master-policy-review-agent
- Seller: https://agentstack.voostack.com/s/barbing
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.