review-codebase

Codebase Review

You are the orchestrator for a full codebase review. Your job is to divide the codebase into reviewable chunks (using the documentation registry's feature boundaries), delegate each chunk to a code-reviewer agent, and compile the results into a unified report.

How It Works

Step 1: Read the registry

Read docs/.registry.json to get the feature map. Each registry entry defines a feature with its source files — these are your review units.

If no registry exists, tell the user to run codument scan first.

Step 2: Determine review scope

By default, review all features. The user may narrow scope:

• Specific features: "review auth and payments"
• By status: "review stale features only"
• By directory: "review everything under src/api/"
• By severity filter: "only critical and high issues"

If the user doesn't specify, review everything.

Step 3: Spawn code-reviewer agents

For each feature in scope, spawn a code-reviewer agent with specific instructions:

Review the "{feature-name}" feature.
Doc: {doc path from registry}
Source files to review:
{list each file from the registry entry's sources array}

Focus areas: correctness, security, performance, error handling, type safety.
Report findings by severity: Critical, High, Medium, Low.
Include a Positives section for what's done well.
{any user-specified focus or constraints}

Batching:

• Small projects (< 6 features): spawn all agents in parallel
• Larger projects: batch 3-5 agents at a time to avoid overwhelming the system

Important: Be specific in agent instructions. Include the exact file paths. Vague instructions produce vague reviews.

Step 4: Compile the report

After all agents complete, compile findings into a unified report:

# Codebase Review Report

**Date**: YYYY-MM-DD
**Features reviewed**: N
**Total findings**: N (X critical, Y high, Z medium, W low)

## Critical Issues
[all critical findings across features, grouped by feature]

## High Priority
[all high findings across features, grouped by feature]

## Medium Priority
[all medium findings, grouped by feature]

## Low Priority
[summary count only — detail available per-feature]

## Highlights
[notable positives across the codebase]

## Recommended Priorities
[ordered list: what to fix first based on severity and blast radius]