By AZidan
Orchestrate AI agents across the full software development lifecycle—from product strategy, feature planning, and coding (backend, frontend, mobile) through accessibility audits, performance optimization, localization, testing, deployment, documentation, and post-launch analytics—using structured phases and file-based handoffs.
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.
Turn Claude Code into a structured development team.
Website · Quick Start · How It Works · Phases · Agents · Commands
Archflow is a phase-based AI development framework for Claude Code. It orchestrates 16+ specialized agents through a structured workflow — from product strategy to production deployment.
Instead of one AI doing everything, each task goes to an agent with deep expertise in its domain. A product-strategist defines business goals. A ux-designer creates the design system. An api-contract-architect locks down API specs. Then ui-engineer and api-engineer build frontend and backend in parallel — coordinated through file-based handoffs and mandatory approval gates.
Archflow works with any project type — fullstack, frontend-only, backend-only, or mobile — and adapts its phases, agents, and artifact structure accordingly.
claude plugin marketplace add azidan/archflow https://github.com/AZidan/archflow
claude plugin install archflow --scope project
This saves the plugin reference to .claude/settings.json in your repo — any team member who clones gets prompted to install automatically.
Free and open source. No lock-in. Uninstall anytime with claude plugin uninstall archflow.
Open Claude Code in your project directory:
cd your-project
claude
/archflow onboard — agents analyze your code, import context from your tools, and generate all artifacts for approval./archflow feature # Interactive wizard
/archflow feature login # Quick-add by name
Archflow creates the feature branch, breaks it into tasks, and guides implementation through the appropriate agents. Features are filtered by scope — a backend_only repo only sees backend-scoped features from the roadmap.
Building software with AI means context gets lost, quality varies, and the same mistakes repeat. Archflow fixes this with three ideas:
Phase 1 Strategy & Planning product-strategist, feature-planner
Phase 2 Design ux-designer, dsl-generator
Phase 2.25 High-Fidelity Screens SuperDesign MCP (optional)
Phase 2.5 API Architecture api-contract-architect
Phase 3 Implementation (Parallel) ui-engineer + api-engineer, qa-engineer, pm-maestro-reviewer
Phase 4 Quality & Optimization code-reviewer, performance-optimizer, pm-maestro-reviewer
Phase 5 Launch & Operations devops-engineer, post-launch-analyst
Phase 6 Enhancement (On-Demand) i18n-engineer, post-launch-analyst, any agent as needed
Each phase has explicit completion criteria, expected output artifacts, and requires user approval before advancing.
Most AI workflows assume you're starting from scratch. Archflow meets you where you are.
Run /archflow onboard and it dispatches up to 9 agents in parallel to deeply analyze your codebase. They import context from tools you already use (Jira, Notion, Linear, GitHub, Confluence, Slack), reverse-engineer your design system and API contracts, and drop you into the right phase based on what already exists.
Structural codebase indexing for efficient navigation. Reduces token consumption by 60-80% through targeted line-range reads instead of full file scans.
npx claudepluginhub azidan/archflow --plugin archflowFull-stack agents — frontend, backend, API, DevOps architects
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Use this agent when you need to design scalable architecture and folder structures for new features or projects. Examples include: when starting a new feature module, refactoring existing code organization, planning microservice boundaries, designing component hierarchies, or establishing project structure conventions. For example: user: 'I need to add a user authentication system to my app' -> assistant: 'I'll use the code-architect agent to design the architecture and folder structure for your authentication system' -> <uses agent>. Another example: user: 'How should I organize my e-commerce product catalog feature?' -> assistant: 'Let me use the code-architect agent to design a scalable structure for your product catalog' -> <uses agent>.
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
Development toolkit for Claude Code — plan, implement, ship, review, and assess features with AI-assisted workflows. Progressive zero-config init: auto-configures with sensible defaults on first skill invocation, no upfront ceremony required. Three-tier ceremony model: swift (lightweight), standard (mid-ceremony spec-plan-execute), and thorough (full pipeline) with severity-aware scope routing. Five entry points: arn-planning (scope router, spec, plan), arn-implementing (execute plans, swift, or standard changes), arn-shipping (commit, push, PR), arn-reviewing-pr (PR feedback), arn-assessing (codebase health). Includes arn-code-sketch for UI preview, arn-code-swift for quick implementations, and arn-code-standard for mid-ceremony changes. Includes arn-code-catch-up for retroactive documentation of out-of-pipeline commits. Pipeline preference persistence for streamlined repeat sessions. Batch pipeline: arn-code-batch-planning (multi-feature planning), arn-code-batch-implement (parallel worktree execution), arn-code-batch-merge (conflict-aware merge), arn-code-batch-simplify (cross-feature quality).
The full arc from idea to shipped code. Lifecycle workflows for vision, ideation, implementation, review, testing, audit, launch, and commits.