Skip to content
Back to skills

Run Multi Agent Code Review Rounds With Structured Reviewer Discourse Before Human Approval

ASecurity

Use Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review.

  • 36 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added June 2, 2026
ai-agentsgonodecode-reviewgitsecuritydocumentation

Works with

  • claude code
  • cursor
  • cli

Security analysis

A100/100

Scanned June 2, 2026

npx -y skills add agentskillexchange/skills --skill run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Run Multi Agent Code Review Rounds With Structured Reviewer Discourse Before Human Approval?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Run Multi Agent Code Review Rounds With Structured Reviewer Discourse Before Human Approval
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/agentskillexchange-run-multi-agent-code-review-rounds-with-structured/badge)](https://www.skillsdirectory.com/skills/agentskillexchange-run-multi-agent-code-review-rounds-with-structured)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "Run multi-agent code review rounds with structured reviewer discourse before human approval"
slug: "run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval"
description: "Use Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review."
github_stars: 131
verification: "security_reviewed"
source: "https://github.com/spencermarx/open-code-review"
author: "Spencer Marx"
publisher_type: "individual"
category: "Code Quality & Review"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "spencermarx/open-code-review"
  github_stars: 131
  npm_package: "@open-code-review/cli"
  npm_weekly_downloads: 1089
---

# Run multi-agent code review rounds with structured reviewer discourse before human approval

Use Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review.

## Prerequisites

Node.js 20+, Git, and a supported AI coding assistant such as Claude Code, Cursor, Windsurf, or another OCR-supported tool. GitHub CLI auth is also needed if you want to post reviews back to pull requests.

## Installation

Requirements and caveats from upstream:
- **Prerequisites**: GitHub CLI (gh) installed and authenticated, open PR on current branch.

Basic usage or getting-started notes:
- The dashboard is the recommended way to run reviews, browse results, and manage your workflow. Launch it with ocr dashboard.
- ### Run reviews and maps
- <img src="assets/ocr-tool-example-translated-human-review.png" alt="Human-voice review posted to GitHub PR" width="700" />

- Source: https://github.com/spencermarx/open-code-review
- Extracted from upstream docs: https://raw.githubusercontent.com/spencermarx/open-code-review/HEAD/README.md

## Documentation

- https://github.com/spencermarx/open-code-review#readme

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval/)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…