agentleFS
Sign inStart free
cenconq25cenconq25/claude-code-app-studio/CLAUDE.md

claude-code-app-studio

CLAUDE.md40 starsChanged 7 months agoMITView on GitHub

A coordinated team of 54 Claude Code subagents that build, ship, and operate mobile apps end to end. Each agent owns a narrow slice of the lifecycle so that responsibility, expertise, and review checkpoints stay separated and observable. Note: Framework specialists exist for each of the four supported stacks with dedicated language and UI sub-specialists. Use the set that matches the framework you have chosen. Never mix specialists across stacks for the same surface area without an ADR. The repository…

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every task follows: Question -> Options -> Decision -> Draft -> Approval

    line 64
  2. Distinctive:

    No commits without user instruction

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Claude Code App Studios -- Mobile App Studio Agent Architecture

A coordinated team of 54 Claude Code subagents that build, ship, and operate mobile apps end to end. Each agent owns a narrow slice of the lifecycle so that responsibility, expertise, and review checkpoints stay separated and observable.

Technology Stack

  • Framework: [CHOOSE: React Native + TypeScript / Flutter + Dart / Native iOS (Swift) / Native Android (Kotlin)]
  • Language: [CHOOSE: TypeScript / Dart / Swift / Kotlin]
  • Target Platforms: iOS 17+ and Android 13+ unless otherwise scoped
  • Source Control: Git, trunk-based with short-lived feature branches
  • Build & Distribution: [SPECIFY after framework is chosen — Fastlane, EAS, Xcode Cloud, Play Console, App Store Connect]
  • Backend: [SPECIFY — REST/GraphQL service, Firebase, Supabase, custom]

Note: Framework specialists exist for each of the four supported stacks with dedicated language and UI sub-specialists. Use the set that matches the framework you have chosen. Never mix specialists across stacks for the same surface area without an ADR.

Domain Glossary

The repository uses mobile-product vocabulary throughout. When reading legacy notes that reference any of these terms, translate as follows:

Term in this templateMeans
frameworkThe chosen mobile stack (RN, Flutter, iOS native, Android native)
appThe product itself
userThe person using the app
screen / flow / journeyA view, a multi-step task, the longitudinal path
PRDProduct requirements document — the single source of truth per feature
user test / betaPre-release validation with real users (TestFlight, Play internal track)
monetization / pricingRevenue model (IAP, subscriptions, ads, paid app)
animations / transitionsMotion design including micro-interactions
haptics, sound, push notificationsSensory and out-of-app communication channels
backend integration / syncAPI consumption, offline cache, conflict resolution
mobile securityCert pinning, RASP, jailbreak/root detection, secure storage
flow-designer / journey-designerThe agent that owns end-to-end task design
product-directorFinal authority on product direction
visual-design-directorOwns the visual system and UI design language
motion-directorOwns motion, haptics, and sonic identity

Project Structure

@.claude/docs/directory-structure.md

Framework Version Reference

@docs/framework-reference/FRAMEWORK.md

Technical Preferences

@.claude/docs/technical-preferences.md

Coordination Rules

@.claude/docs/coordination-rules.md

Collaboration Protocol

User-driven collaboration, not autonomous execution. Every task follows: Question -> Options -> Decision -> Draft -> Approval

  • Agents MUST ask "May I write this to [filepath]?" before using Write/Edit tools
  • Agents MUST present at least two viable options for any non-trivial decision
  • Multi-file changes require explicit approval for the full changeset
  • No commits without user instruction
  • Store-facing copy, pricing, and analytics events are user-approved before code lands

See docs/COLLABORATIVE-DESIGN-PRINCIPLE.md for the full protocol with mobile-app examples.

First session? If the project has no framework configured and no product brief yet, invoke the /start skill to walk through onboarding.

Coding Standards

@.claude/docs/coding-standards.md

Context Management

@.claude/docs/context-management.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free