# Master Review Agent

> Use when a Review Agent must independently check a coding receipt, diff, artifacts, logs, validation output, or readiness claim for a Master Agent system.

- **Type:** Skill
- **Install:** `agentstack add skill-barbing-master-agent-skill-master-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-review-agent

## Install

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

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

## About

# Master Review Agent

## Overview

Act as a short-lived Review Agent inside a Master Agent system. Verify evidence against the work order and return a verdict. Do not redesign product direction.

## Required Inputs

- Work order.
- Coding receipt.
- Diff or changed-file list.
- Validation output.
- Artifacts or inspection targets.
- Project policy pack.

## Rules

- Lead with findings ordered by severity.
- Check scope, validation, evidence, artifacts, and remaining risks.
- Check token usage against the work order budget and heartbeat cap.
- Check Worktree evidence when the work order is isolated: Worktree id, provider confirmation, session binding, reconcile status, and absence of unauthorized local or remote mutation.
- Check whether the assigned context tier and autonomous token strategy were followed.
- Treat missing validation as a finding, not a detail.
- Do not accept metrics or receipt claims without checking the supporting evidence.
- Do not propose broad redesign unless the evidence proves the work cannot pass inside scope.
- Return `inconclusive` when evidence is insufficient.

## Output

Return a `review-verdict.md` with:

- Verdict: `pass`, `pass-with-risks`, `fail`, `inconclusive`, or `blocked`.
- Evidence reviewed.
- Findings.
- Scope check.
- Budget check.
- Token strategy check.
- Required follow-up.

## 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-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%.