Skip to content

Repository files navigation

Shipwright

Multi-agent orchestration for building production apps with Claude Code

StarsLicenseTypeScriptX


You describe what you want to build. Shipwright orchestrates 15 specialized AI agents through a 12-phase pipeline, from requirements to deployed and QA-tested.

Prerequisites

  • Claude Code (Max plan recommended for higher rate limits)
  • acpx - deterministic graph execution engine
npm ci -g acpx@latest

Quick Start

gh repo create my-app --template aster2709/shipwright --clone --private
cd my-app
npm ci
npm start

That's it. The CLI walks you through everything: pick build or feature, describe what you want, and the pipeline runs.

Alternative: Claude Code Skills (flexible, human-in-the-loop)

claude --dangerously-skip-permissions
# Then: /build a SaaS invoice platform with Stripe integration

How It Works

Q&A (5 rounds) → PRD → Research → Architecture → Design → Skeleton
[interactive] [review] [review]
Implementation Plan → Backend + Frontend (parallel) → Testing
[review]
Review → Audit → Deploy → QA → Learnings

Three interactive review gates where each document is rendered in your terminal and you can approve or suggest changes. The agent revises and re-presents until you're satisfied.

Dynamic requirements gathering with 5 rounds of adaptive questions. Each question is generated by the LLM based on your previous answers, covering users, auth, data model, deployment, and design.

Parallel implementation with separate backend and frontend sessions running concurrently via fork/join.

Shipwright pairs a deterministic graph engine (acpx fork) with Claude Code as the agent runtime. The graph handles scheduling, retries, and branching. The LLM handles reasoning and coding.

Agents (15)

AgentRole
team-leadOrchestrates pipeline, enforces completion, never idles
requirements-analystClarifying questions, PRD with budget/deployment constraints
researcherBest practices, cost analysis, technology recommendations
architectSystem design, API contracts, data model, cost estimates
ui-designerDesign system, shadcn/ui + Magic UI scaffolding via 21st.dev
skeleton-builderRepo structure, configs, empty modules that compile
implementation-plannerTask breakdown with dependencies and file ownership
backend-implementerAPI routes, database, integrations, business logic
frontend-implementerPages, components, styling per DESIGN.md spec
test-engineerUnit, integration, component tests
reviewerSecurity, performance, correctness review
auditorPRD coverage verification, gap analysis
deployerPlatform deployment, env config, cost-aware
monitorPost-deploy health checks, CI/CD verification
qa-testerDeep code audit, traces flows end-to-end, finds what breaks

Execution Modes

ModeEngineCompletionBest for
npm startInteractive CLI + acpx graph engineGuaranteedRecommended for all users
/build skillLLM orchestrator (Agent Teams)Best-effortExploratory work, flexibility
/feature skillLLM orchestrator (Agent Teams)Best-effortQuick feature additions

Skills

SkillWhen
/buildNew app from scratch — full 12-phase pipeline
/featureAdd features to an existing codebase — 8 phases
/auditGap check against PRD anytime

Agent Communication

  1. Direct messaging — teammates talk to each other for questions and handoffs
  2. Shared task list — work items with dependencies and status tracking
  3. docs/ folder — formal outputs that become the project's source of truth

The team lead is the heartbeat — actively checks progress, spawns next phases immediately, never waits passively.

Documentation

Agents produce these artifacts in docs/:

FileProducerContents
PRD.mdrequirements-analystProduct requirements, user stories, constraints
RESEARCH.mdresearcherTechnology recommendations with cost analysis
ARCHITECTURE.mdarchitectSystem design, API contracts, deployment plan
DESIGN.mdui-designerVisual design system, component library choices
IMPLEMENTATION_PLAN.mdimplementation-plannerTasks with dependencies and file ownership
QA-REPORT.mdqa-testerBrowser test results with screenshots

Architecture

cmux / tmux (observe agents in split panes)
└── acpx (deterministic graph engine — schedules phases)
└── Claude Code (agent runtime — executes each node)
├── 15 agent definitions (each owns one phase)
├── docs/ (inter-agent communication via artifacts)
└── .claude/skills/learnings/ (reusable patterns from past builds)

Self-Improvement

After successful builds, reusable patterns are saved to .claude/skills/learnings/. Future builds reference these to avoid rediscovering the same solutions. The more you build, the better it gets.

Recommended

  • cmux or tmux - split-pane agent visibility
  • 21st.dev Magic components - UI design inspiration

License

MIT

About

Multi-agent orchestration for building production apps with Claude Code. 15 agents, 12-phase pipeline, from requirements to deployed.

Topics

Resources

Stars

12 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages