plan-review

Coordinate three reviewers to cross-check code and write .spec/{slug}/review.md.

9|1|Updated Mar 11, 2026

Search Tags:#automation #architecture #code-review #plan-review #spec.md #agent-teams #review-report

Ready to run

npx skills add https://github.com/mark22013333/crew --skill plan-review-mark22013333

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: plan-review
Source: https://github.com/mark22013333/crew/tree/main/plugins/feature-workflow/skills/plan-review
Command: npx skills add https://github.com/mark22013333/crew --skill plan-review-mark22013333

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Plan-review coordinates three reviewers in an Agent Teams leader-delegate setup to perform parallel, cross-checked code reviews, ensuring faster, more reliable findings and a shared understanding stored in the project spec.

Core Features & Use Cases

Three independent reviewers assess logic, quality, and performance, then share findings for cross-review.
Leader compiles a final report into .spec/{slug}/review.md to preserve traceability and enable downstream QA.
Integrates with existing task workflows by identifying active tasks from Git branches and .spec/{slug}/files.md when present.

Quick Start

Start a plan-review with three reviewers to audit the current task and write the consolidated review to .spec/{slug}/review.md.

Frequently Asked Questions about plan-review

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

FAQPage Schema

How do I run a parallel code review for logic, quality, and performance?▼

Parallel code review is orchestrated by coordinating three independent reviewers in an Agent Teams leader-delegate setup to assess logic, quality, and performance simultaneously, followed by a cross-check phase to validate findings before compilation.

How does an Agent Teams leader-delegate setup work for cross-checked code reviews?▼

An Agent Teams leader-delegate setup works by assigning three delegate reviewers to evaluate code independently, then the leader collects and cross-checks their findings to compile a final consolidated review report, ensuring faster and more reliable results.

Can I use Git branches to define the scope for an automated code review?▼

Yes, you can use Git branches to define the review scope. The review process identifies active tasks from Git branches and supporting spec files to automatically determine what code changes require evaluation.

Where does the final code review report get saved for downstream QA?▼

The final code review report is saved as the authoritative artifact in `.spec/{slug}/review.md`, preserving traceability and enabling downstream QA by storing the consolidated leader report within the project spec.

What prerequisites do I need for a three-person parallel code review?▼

Prerequisites include an active project with supporting spec files like `.spec/{slug}/files.md` when available, and adherence to the guidelines and prerequisites described in the plan-review workflow before initiating the review.

When should I not use a parallel agent-based code review?▼

You should avoid parallel agent-based code review if your project lacks active Git branches for task discovery or does not support the Agent Teams leader-delegate architecture required to coordinate the three reviewers.