code-council

Run parallel code reviews across multiple AI backends and synthesize verified findings.

7|1|Updated Jan 19, 2026
One-click install
npx skills add https://github.com/makoMakoGo/code-dispatcher-toolkit --skill code-council
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-council
Source: https://github.com/makoMakoGo/code-dispatcher-toolkit/tree/main/skills/code-council
Command: npx skills add https://github.com/makoMakoGo/code-dispatcher-toolkit --skill code-council

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of code review by leveraging multiple AI backends to identify potential issues, ensuring higher code quality and security.

Core Features & Use Cases

  • Parallel AI Review: Runs 2-3 AI reviewers simultaneously on the same code.
  • Finding Verification: The host agent verifies each finding from the AI reviewers.
  • Synthesized Report: Consolidates and presents verified findings in a clear, actionable report.
  • Use Case: Use this skill to get a comprehensive code review for a new feature before merging it into the main branch, catching security vulnerabilities and logic errors early.

Quick Start

Run code-council on the file src/main.py.

Frequently Asked Questions about code-council

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How can I use AI to find security vulnerabilities and logic errors before merging code?

Parallel AI code review runs 2-3 AI reviewers simultaneously on the same code to identify security vulnerabilities and logic errors. The host agent verifies each finding to ensure accuracy before merging into the main branch.

What is the best way to perform multi-backend code review for performance issues?

Multi-backend code review uses the code-dispatcher to run parallel execution across multiple AI agents. It verifies findings across different backends and synthesizes a final actionable report highlighting performance issues and code quality concerns.

Does AI code review verify findings or just list potential code quality concerns?

AI code review verifies findings by having the host agent validate each issue reported by the AI reviewers. Instead of just listing potential code quality concerns, it consolidates and presents only verified findings in a synthesized report.

How do I run a parallel code review on a specific file like src/main.py?

To run a parallel code review on a specific file like src/main.py, execute the council skill targeting that file path. The skill dispatches the file to multiple AI backends for simultaneous analysis and synthesizes the verified results.

Can I use this parallel code review approach for a new feature branch?

Yes, you can use parallel code review for a new feature branch. It is designed to provide a comprehensive code review before merging, automatically catching security vulnerabilities, logic errors, and performance issues early in development.

What are the limitations of using automated AI agents for code review?

A limitation of using AI agents for code review is the potential for unverified false positives, which is why the host agent verifies each finding. Users must still review the synthesized report to ensure the identified issues match their specific application context.