Saijayanth001

Accenture Enterprise Multi Agent Code Review Orchestrator — Testing skill for Claude Code

Testing community

A production-ready multi-agent code review system powered by the Claude Agent SDK.

How to install Accenture Enterprise Multi Agent Code Review Orchestrator

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Saijayanth001/Accenture-Enterprise-Multi-Agent-Code-Review-Orchestrator and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Accenture Enterprise Multi Agent Code Review Orchestrator does

A production-ready multi-agent code review system powered by the Claude Agent SDK. Specialized AI agents collaborate to analyze pull requests from multiple perspectives, including code quality, test coverage, and refactoring opportunities, and synthesize their findings into a comprehensive, actionable review report.

Alternatives in Testing

Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
Ext Apps — Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP serve 1.9k ★
Spy — by spylang - Enforces strict coding conventions with comprehensive testing guidelines, multiple code compilati 678 ★

README

Enterprise Multi-Agent Code Review Orchestrator

Production-ready multi-agent system that automates code review, test coverage analysis, and refactoring suggestions for GitHub pull requests using Claude Agent SDK.

Features

Multi-Agent Architecture: Coordinates 3 specialized subagents for comprehensive PR analysis
Code Quality Analysis: Security vulnerabilities, performance issues, best practices
Test Coverage Analysis: Identifies untested code paths with extended thinking
Refactoring Suggestions: Modernization opportunities and pattern improvements
MCP Integration: GitHub and Eslint servers for external data access
Claude Skills: Language-specific analysis (JavaScript, TypeScript, Python, Security)
Production-Grade: Rate limiting, retry logic, structured logging, error handling

Architecture

Orchestrator

Main coordinator that:

Fetches PR files via GitHub MCP
Spawns 3 subagents in parallel for each file
Aggregates results into unified review report
Enforces rate limits and validates structured outputs

Subagents

Agent	Purpose	Key Features
code-quality-analyzer	Security, performance, maintainability	Invokes Claude Skills, severity-leveled feedback
test-coverage-analyzer	Identifies untested code paths	Extended thinking, priority-based suggestions
refactoring-suggester	Modernization and patterns	Before/after examples, impact assessment

Prerequisites

Node.js 20+
Anthropic API key
GitHub personal access token
TypeScript 5.3+

Installation

# Clone repository
cd project/starter

# Install dependencies
npm install

# Copy environment template
cp .env.example .env

Configuration

Edit `.env` with your credentials:

ANTHROPIC_API_KEY=sk-ant-your-key-here
GITHUB_TOKEN=ghp_your-token-here

# REQUIRED: Absolute path to project root (contains .claude/skills/)
PROJECT_ROOT=/absolute/path/to/p