Reviewflow

Automated AI code reviews powered by Claude Code. Assign a reviewer on your merge request — Claude reviews the code, tracks progress in real time, and follows up when you push fixes.

Works with GitLab and GitHub out of the box.

How It Works

Developer pushes code
       │
       ▼
GitLab/GitHub webhook ──► Review server receives event
                                    │
                                    ▼
                          Queue deduplicates & schedules
                                    │
                                    ▼
                          Claude Code runs review skill
                                    │
                          ┌─────────┼─────────┐
                          ▼         ▼         ▼
                     Agent 1   Agent 2   Agent N
                   (Archi)    (Tests)   (Quality)
                          │         │         │
                          └─────────┼─────────┘
                                    ▼
                          MCP server reports progress
                                    │
                                    ▼
                          Dashboard shows live status
                                    │
                                    ▼
                          Review posted on MR/PR
                                    │
                                    ▼
                          Dev pushes fixes ──► Auto follow-up

Key Features

Multi-Agent Reviews

Each review runs a configurable set of specialized audit agents — Clean Architecture, SOLID, Testing, DDD, Code Quality, and more. Define your own agents per project to match your team's standards.

{
  "agents": [
    { "name": "clean-architecture", "displayName": "Clean Archi" },
    { "name": "security", "displayName": "Security" },
    { "name": "testing", "displayName": "Testing" }
  ]
}

MCP Integration

A built-in Model Context Protocol server gives Claude structured tools to report progress, manage review phases, and queue actions on discussion threads — replacing fragile text-marker parsing with typed tool calls.

Smart Queue

Powered by p-queue with:

• Concurrency control — limit parallel reviews (default: 2)
• Deduplication — prevents duplicate reviews within a configurable time window
• Graceful cancellation — abort running reviews via dashboard or API
• Memory guard — auto-kills if RSS exceeds 4 GB
• Retry on failure — failed jobs clear deduplication so they can be re-triggered immediately

Real-Time Dashboard

A WebSocket-powered dashboard shows live review progress:

• Phase and agent-level progress bars
• Running / queued / completed review counts
• Review history with duration, scores, and error details
• Team tab with developer cards, insights, and AI analysis
• Stats section with canvas charts, score trends, and animated counters
• Log stream for debugging
• Auto-reconnection with exponential backoff

Developer & Team Insights

The dashboard computes performance insights from your review history — no configuration needed.

Per-developer analysis across 4 categories:

Each developer gets a level (beginner → expert), a trend (improving / stable / declining), identified strengths and weaknesses, and a title based on their strongest category (Architect, Firefighter, Workhorse, Sentinel, or Balanced).

Team-level analysis shows top performer, most improved developer, and actionable tips.

AI-powered narrative (optional): click "Generate AI Insights" to have Claude produce a written analysis with per-developer and team recommendations.

Insights are computed from the first 5 reviews onward and persist across sessions.

Follow-Up Reviews

When a developer pushes fixes after a review, Claude automatically:

1. Re-reads the discussion threads
2. Checks if blocking issues are resolved
3. Resolves threads on GitLab/GitHub
4. Posts a follow-up summary with updated score

This creates an iterative review loop, not just a one-shot check.

Multi-Platform Support

No API tokens needed — both platforms use secure CLI-based OAuth.

Customizable Review Skills

Review behavior is defined by Claude Code skills — Markdown files in your project that tell Claude what to audit and how. Templates included for frontend, backend, and API reviews in English and French.

Quick Start

1. Install

npm install -g reviewflow

2. Initialize

reviewflow init

The interactive wizard will:

• Configure server port and usernames
• Generate webhook secrets
• Scan your filesystem for git repositories
• Set up MCP server integration with Claude Code

For non-interactive setup: reviewflow init --yes

3. Start

reviewflow start
# Dashboard at http://localhost:3847

Then configure a webhook on your GitLab/GitHub project pointing to your server.

Validate your setup

reviewflow validate

For detailed setup, see the Quick Start Guide.

CLI Reference

Documentation

API

Development

npm run dev          # Dev server with hot reload
npm test             # Tests in watch mode
npm run test:ci      # Tests (CI mode)
npm run typecheck    # TypeScript validation
npm run lint         # Biome linting
npm run verify       # All checks (typecheck + lint + test)

See CONTRIBUTING.md for guidelines.

License

MIT — Damien Gouron