A bootstrapping template for software projects built with Claude Code. Use it as a GitHub template, run /start, and Claude walks you through setting up all the documentation before a single line of code is written.

This repository is an opinionated project scaffold that gives Claude everything it needs to act as a coherent development team from day one:

• Specialized agents for each discipline (architecture, frontend, backend, design, database, QA, CI/CD, Docker, docs, copywriting & SEO)
• Living documentation that agents keep up to date as the project evolves
• Git conventions enforced through commit format, branch naming, and PR templates
• A product requirements document that serves as the authoritative source of truth — protected from accidental edits
• A backlog agents can reference when you ask "what should we work on next?"

Click "Use this template" → "Create a new repository" on GitHub.

Or with the GitHub CLI:

gh repo create my-project --template https://github.com/josipjelic/orchestrated-project-template --private --clone && cd my-project

Claude will read START_HERE.md and begin the onboarding sequence — asking questions about your project and filling in all the documentation placeholders automatically.

Once onboarding is complete, START_HERE.md is deleted and the project is ready. Use TODO.md to see what to work on first.

Run once after creating a new project. Claude reads START_HERE.md and walks you through the full onboarding sequence — gathering project details, copying documentation templates into place, filling in every placeholder, and building the initial backlog from your requirements.

Hand off a multi-agent task and let Claude coordinate the execution. The orchestrator analyzes your task, identifies which specialists are needed, determines the correct execution order (parallel where safe, sequential where dependencies require it), registers the work in the backlog, creates a feature branch, and runs the agents wave by wave.

/orchestrate add user authentication with email and password

Presents a wave plan for your approval before anything runs. Stops and asks if a wave fails — never silently continues.

Pull the latest .claude/ directory from the upstream template repository into your project. Useful when agents are improved, new commands are added, or documentation templates are updated.

Shows a diff and asks for confirmation before changing anything. Local-only files are never deleted.

├── CLAUDE.md                     # Master Claude instructions (auto-loaded every session)
├── PRD.md                        # Product Requirements Document — agents read, never modify
├── TODO.md                       # Prioritized backlog — humans curate, agents consult
├── README.template.md            # README template filled in during onboarding
├── START_HERE.md                 # Onboarding protocol — deleted after setup
├── .gitignore
│
├── .claude/
│   ├── agents/                   # Specialist sub-agents
│   │   ├── project-manager.md    # Backlog governance & agent coordination
│   │   ├── systems-architect.md  # Architecture decisions & ADRs (Claude Opus)
│   │   ├── frontend-developer.md # UI components & pages
│   │   ├── backend-developer.md  # API endpoints & business logic
│   │   ├── ui-ux-designer.md     # UX flows & design system specs
│   │   ├── database-expert.md    # Schema design & migrations
│   │   ├── qa-engineer.md        # Playwright E2E tests
│   │   ├── documentation-writer.md # User guide & project docs
│   │   ├── cicd-engineer.md      # GitHub Actions workflows & deployment pipelines
│   │   ├── docker-expert.md      # Dockerfiles, Compose, image optimization
│   │   └── copywriter-seo.md     # Conversion copy, brand voice, keyword strategy, technical SEO
│   ├── commands/
│   │   ├── start.md              # /start — runs the onboarding protocol
│   │   └── sync-template.md      # /sync-template — pulls latest .claude/ from upstream
│   └── templates/                # Blank doc templates — synced from upstream via /sync-template
│       ├── CLAUDE.md             # Master Claude instructions template
│       ├── PRD.md                # Product requirements template
│       ├── README.md             # Project README template
│       ├── docs/
│       │   ├── technical/        # ARCHITECTURE.md, DECISIONS.md, API.md, DATABASE.md
│       │   ├── user/             # USER_GUIDE.md
│       │   └── content/          # CONTENT_STRATEGY.md
│       └── .tasks/
│           └── TASK_TEMPLATE.md  # Task file template
│
├── .github/
│   └── PULL_REQUEST_TEMPLATE.md  # Enforces consistent PR descriptions
│
├── .tasks/                       # Detailed task files — one per TODO item
│   └── TASK_TEMPLATE.md          # Copy this when creating new tasks
│
└── docs/                         # Created during onboarding from .claude/templates/
    ├── user/USER_GUIDE.md        # How the system is used (user perspective)
    ├── technical/
    │   ├── ARCHITECTURE.md       # System design & component overview
    │   ├── API.md                # API reference (updated after every endpoint)
    │   ├── DATABASE.md           # Schema, migrations, query patterns
    │   └── DECISIONS.md          # Architecture Decision Records (ADR log)
    └── content/
        └── CONTENT_STRATEGY.md   # Brand voice, keyword targets, copy library, technical SEO specs

Each agent is a specialist Claude sub-agent with a defined role, document ownership, and working protocol.

Claude selects agents automatically based on context, or you can invoke them directly.

Commits — Conventional Commits:

feat(auth): add OAuth2 login with Google
fix(api): handle null response from payment provider

Branches:

feature/<ticket-id>-short-description
fix/<ticket-id>-short-description

PRD is read-only — PRD.md is protected by a three-layer mechanism (warning block, CLAUDE.md rule, and agent system prompts). Agents will refuse to modify it without explicit human instruction.

Documentation stays current — Agents are required to update the relevant docs/ file before marking any implementation task complete.

• Design before code — the Systems Architect agent produces specs and ADRs; specialists implement
• Copy before implementation — the Copywriter & SEO agent defines page copy, CTAs, and keyword targets before @frontend-developer builds marketing pages
• Document ownership — every docs/ file has a declared owner agent; others don't overwrite
• Append-only ADRs — architectural decisions are never silently revised; a new ADR supersedes an old one
• Tests map to requirements — QA writes tests against FR-XXX items in the PRD, not implementation details
• TODO.md is human territory — agents read the backlog to suggest work; they never auto-modify it

MIT