Multi-agent feature development pipeline: PM → Architect → Dev → Review → QA
A structured, multi-agent pipeline for AI-assisted feature development. Model-agnostic, stack-agnostic.
PM → Architect → Dev → Review → QA — each role produces artifacts, gates, and handoffs.
npx bmad-method)npx bmad-method install --custom-source https://github.com/org/ai-feature-pipeline
# Run the setup skill to configure your project
/start afp-setup
Or interactively through your AI tool: "Run the AFP Setup skill."
/start afp-pipeline new "Add dark mode toggle"
Or through your AI tool: "Run the AFP Pipeline to scope a new feature."
skills/
├── afp-setup/ # First-time project configuration
│ ├── SKILL.md
│ └── assets/
│ ├── module.yaml # Config variables
│ └── module-help.csv # Help entries
│
└── afp-pipeline/ # Main pipeline workflow
├── SKILL.md # Workflow definition
├── prompts/ # Role-specific system prompts
│ ├── pm.md
│ ├── architect.md
│ ├── dev.md
│ ├── review.md
│ └── qa.md
├── scripts/ # Automation
│ ├── agent-runner.ts # OpenRouter-based agent executor
│ ├── rebuild-context.mjs # Source code scanner
│ └── run-pipeline.sh # Full pipeline runner
├── registries/ # Registries
│ ├── scope-checklist.md
│ ├── ship-checklist.md
│ ├── analytics-events.md
│ └── paywall-touchpoints.md
└── templates/ # Artifact templates
├── feature-brief.md
├── technical-plan.md
├── repository-context.md
├── dev-log.md
├── review-report.md
├── qa-report.md
└── retrospective.md
| Stage | Role | Produces |
|---|---|---|
| 1 | PM | feature-brief.md — requirements, AC, scope |
| 2 | Architect | technical-plan.md + repository-context.md |
| 3 | Dev | Code changes + dev-log.md |
| 4 | Review | review-report.md — verdict PASS/FAIL |
| 5 | QA | qa-report.md — verdict PASS/FAIL |
Generated by afp-setup into .ai/config.json:
| Variable | Description | Default |
|---|---|---|
project.name | Project display name | My Project |
commands.packageManager | Package manager | npm |
commands.typecheck | Typecheck command | tsc --noEmit |
commands.lint | Lint command | eslint . |
stack.router | Router library | react-router |
stack.analytics.provider | Analytics provider | "" |
stack.paywall.provider | Paywall provider | "" |
e2e.framework | E2E framework | "" |
Full list in skills/afp-setup/assets/module.yaml.
This module follows semver. Changelog is maintained in GitHub Releases.
MIT
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.
npx claudepluginhub arnaudmanaranche/ai-feature-pipeline --plugin ai-feature-pipelineComprehensive 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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.