By ebnrdwan
Phase-based AI development plugin with 20 specialised agents and first-class Gang multi-agent committee integration. Fork of archflow v1.2.3 with /crew drive, /crew deploy, /crew gaps, /crew features, and /crew gang-import / /crew gang-escalate handoff.
Use this agent when you need to evaluate, improve, or ensure accessibility compliance in UI components, web pages, or applications. This includes reviewing existing code for accessibility issues, providing guidance on implementing WCAG AA standards, auditing component libraries, or when building new features that need to be accessible to users with disabilities. Examples: <example>Context: User has just implemented a custom dropdown component and wants to ensure it meets accessibility standards. user: 'I just created this dropdown component, can you review it for accessibility?' assistant: 'I'll use the a11y-expert agent to review your dropdown component for WCAG AA compliance and provide specific recommendations.' <commentary>Since the user is asking for accessibility review of a component, use the a11y-expert agent to evaluate WCAG compliance.</commentary></example> <example>Context: User is planning to build a form and wants proactive accessibility guidance. user: 'I'm about to build a complex multi-step form. What accessibility considerations should I keep in mind?' assistant: 'Let me use the a11y-expert agent to provide comprehensive accessibility guidance for your multi-step form implementation.' <commentary>The user needs proactive accessibility guidance, so use the a11y-expert agent to provide WCAG-compliant recommendations.</commentary></example>
Use this agent when you need to define API contracts between frontend and backend teams. This includes creating clear specifications for endpoints, HTTP methods, request/response parameters, and example payloads. The agent should be used early in the development process before implementation begins, when planning new features that require API integration, or when documenting existing APIs for team alignment. Examples: <example>Context: The user needs to define API contracts for a new user authentication feature. user: "We need to create API contracts for our new authentication system including login, logout, and password reset" assistant: "I'll use the api-contract-architect agent to create comprehensive API contracts for the authentication system" <commentary>Since the user needs API contract documentation between frontend and backend teams, use the api-contract-architect agent to create clear specifications.</commentary></example> <example>Context: The user is planning a new feature and needs API specifications. user: "Let's define the API endpoints for the shopping cart feature" assistant: "I'm going to use the Task tool to launch the api-contract-architect agent to create the API contracts for the shopping cart feature" <commentary>The user needs API contract definitions for a new feature, so the api-contract-architect agent should be used.</commentary></example>
Use this agent when you need to build backend services using Node.js (NestJS), MySQL, and REST APIs. This includes creating API routes, implementing authentication, setting up error handling, defining database schemas, creating ER diagrams, and generating OpenAPI specifications. Examples: <example>Context: User needs to build a user management system backend. user: 'I need to create a user registration and login system with JWT authentication' assistant: 'I'll use the api-engineer agent to build the complete backend system with NestJS, MySQL schema, and authentication endpoints' <commentary>Since the user needs backend API development with the specified stack, use the api-engineer agent to handle the complete implementation.</commentary></example> <example>Context: User is building an e-commerce platform and needs product management APIs. user: 'Create REST endpoints for managing products - CRUD operations with categories and inventory tracking' assistant: 'Let me use the api-engineer agent to design the database schema and implement the product management API endpoints' <commentary>This requires backend API development with database design, perfect for the api-engineer agent.</commentary></example>
Use this agent when you need to review code output from any engineering agent to ensure quality, identify issues, and suggest improvements. Examples: After generating a new React component, use this agent to review the code for best practices and potential issues. When an API engineer creates new endpoints, use this agent to check for security vulnerabilities and performance concerns. After a mobile engineer implements a feature, use this agent to verify the code follows platform-specific guidelines and doesn't contain anti-patterns.
Consolidated DevOps engineer handling complete deployment lifecycle - CI/CD pipelines, infrastructure automation, containerization, release management, app store preparation, and version planning. Manages end-to-end deployment from development to production across web and mobile platforms.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
20 specialised agents. 6 phases. First-class Gang integration.
Drives features from strategy to launch through scoped agents and file-based handoffs —
with explicit phase gates, contract-first development, and acceptance testing.
/crew onboard
# 1. Add the marketplace
claude plugin marketplace add ebnrdwan/Crew
# 2. Install the plugin
claude plugin install crew
# 3. Run on any project
/crew onboard # existing codebase — auto-detects state, sets phase
/crew init # new project — starts at Phase 1
# Update to latest version
claude plugin marketplace update crew-marketplace
graph LR
A["STRATEGY<br/>Vision · Roadmap"] --> B["DESIGN<br/>Flows · DSL"]
B --> C["CONTRACT<br/>API · Schemas"]
C --> D["BUILD<br/>UI · API · QA"]
D --> E["QUALITY<br/>Review · Perf · A11y"]
E --> F["LAUNCH<br/>Deploy · Analytics"]
style A fill:#EA580C,stroke:#C2410C,color:#fff
style B fill:#B45309,stroke:#92400E,color:#fff
style C fill:#15803D,stroke:#166534,color:#fff
style D fill:#0F766E,stroke:#115E59,color:#fff
style E fill:#1D4ED8,stroke:#1E40AF,color:#fff
style F fill:#4338CA,stroke:#3730A3,color:#fff
| Phase | Focus | Key Agents |
|---|---|---|
| 1. Strategy | Vision, personas, roadmap | product-strategist, feature-planner |
| 2. Design | Flows, design tokens, hi-fi screens | ux-designer, dsl-generator |
| 2.5. Contract | API single source of truth | api-contract-architect |
| 3. Build | Frontend + backend + QA in parallel | ui-engineer, api-engineer, qa-engineer, pm-maestro-reviewer |
| 4. Quality | Review, perf, a11y, gap audit | code-reviewer, performance-optimizer, a11y-expert, gap-finder |
| 5/6. Launch | Deploy, analytics, i18n | devops-engineer, post-launch-analyst, i18n-engineer |
Each phase has explicit completion criteria and requires user approval before advancing.
| Command | What it does |
|---|---|
/crew | Show subcommands and current project status |
/crew init | Initialise a new project at Phase 1 |
/crew onboard | Onboard an existing codebase — detect type, audit, set phase |
/crew feature [name] | Add a feature, create branches, assign agents |
/crew setup-mcp [tool] | Connect external tools (Jira, Notion, Linear, GitHub, …) |
/crew drive [name] | End-to-end product-led feature dev (pm-architect → build → QA → audit) |
/crew deploy [flags] | Pre-deployment checklist with auto-remediation |
/crew gaps [url] | UI gap audit + auto-fix pipeline |
/crew features [filters] | Roadmap dashboard with status, pages, acceptance progress |
/crew gang-import <slug> | Import a Gang GO Package as a Crew feature |
/crew gang-escalate <id> | Send a stalled Crew feature back to Gang for re-scoring |
/crew push | Sync the current feature to GitHub Projects (live status card) |
/crew resume [id] | Resume from a usage-budget checkpoint |
/crew profile [check|set|list] | Manage user knowledge profile per tech (one-time per tech, cached) |
| Phase | Agents |
|---|---|
| 1. Strategy | product-strategist, feature-planner |
| 2. Design | ux-designer, dsl-generator |
| 2.5. Contract | api-contract-architect |
| 3. Build | ui-engineer, api-engineer, qa-engineer, pm-maestro-reviewer |
| 4. Quality | code-reviewer, performance-optimizer, a11y-expert, gap-finder, ui-animation-designer |
| 5. Launch | devops-engineer, post-launch-analyst |
| 6. Enhancement | i18n-engineer |
| Cross-cutting | doc-writer, pm-architect |
| Gang ↔ Crew | gang-bridge |
The ui-engineer handles React, React Native, SwiftUI, and Jetpack Compose from a single styled DSL — cross-platform consistency without duplicate agents.
npx claudepluginhub ebnrdwan/crew --plugin crewHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Configurable, auditable, cost-aware multi-agent business committee. Orchestrates domain experts through evidence-backed structured debate with rubric-anchored scoring, budget tracking, multi-provider routing, and advisor guardrails to produce scored strategic plans and executive Go/No-Go recommendations.