multi-mode-review

Coordinate three-mode reviews to detect logic, integration, and architecture bugs.

2|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/vnnkl/agentflywheel --skill multi-mode-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multi-mode-review
Source: https://github.com/vnnkl/agentflywheel/tree/main/skills/multi-mode-review
Command: npx skills add https://github.com/vnnkl/agentflywheel --skill multi-mode-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Three-mode code review system that activates distinct review perspectives to uncover different categories of bugs. It ensures comprehensive quality checks by combining multiple viewpoints in a single workflow.

Core Features & Use Cases

  • Fresh Eyes: Detect local logic errors, off-by-one issues, and edge-case problems after code is written.
  • Cross-Agent: Catch integration and boundary issues at module interfaces.
  • Random Exploration: Identify architectural drift and systemic patterns across the codebase.
  • Use cases: Before merge, post-implementation sanity checks, or audit requests when uncertainty arises.

Quick Start

Run all three modes on the latest changes to produce a comprehensive review.

Frequently Asked Questions about multi-mode-review

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

FAQPage Schema
How do I run a comprehensive code review to catch logic, integration, and architecture bugs?

Run a three-mode code review to catch bugs across logic, integration, and architecture. This coordinates distinct perspectives—Fresh Eyes, Cross-Agent, and Random Exploration—to uncover different categories of bugs in a single workflow.

What is the best way to detect architectural drift and systemic patterns in my codebase?

Use the Random Exploration mode of a three-mode code review to identify architectural drift and systemic patterns across the codebase. It explores code changes from a high-level perspective to catch structural inconsistencies.

How do I catch integration and boundary issues at module interfaces before a merge?

Apply the Cross-Agent mode of code review to catch integration and boundary issues at module interfaces. It specifically targets interaction problems between modules before merging code changes.

When do I need a multi-perspective code review for post-implementation sanity checks?

You need a multi-perspective code review for post-implementation sanity checks, before merges, or during audit requests when uncertainty arises. It ensures comprehensive correctness by combining multiple viewpoints.

Can I use a structured review process to find local logic errors and off-by-one issues?

Yes, you can use the Fresh Eyes mode of a structured review process to detect local logic errors, off-by-one issues, and edge-case problems after code is written. It enforces explicit output formats for structured findings.