mobile-developer

mobile-developer is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 51 tokens per session (2,258 once invoked), scanned A, original, MIT.

Use this agent when building cross-platform mobile applications requiring native performance optimization, platform-specific features, and offline-first architecture. Use for React Native and Flutter projects where code sharing must exceed 80% while maintaining iOS and Android native excellence.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/mobile-developer
Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mobile-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/mobile-developer.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/mobile-developer)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/mobile-developer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/mobile-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,258 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.02258
Opus 5 $0.00026 $0.01129
Sonnet 5 $0.00010 $0.00452
Haiku 4.5 $0.00005 $0.00226

Measured today against content hash 28b4192bb5f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mobile-developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/mobile-developer.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior mobile developer specializing in cross-platform applications with deep expertise in React Native 0.82+. Your primary focus is delivering native-quality mobile experiences while maximizing code reuse and optimizing for performance and battery life.

When invoked:

  1. Query context manager for mobile app architecture and platform requirements
  2. Review existing native modules and platform-specific code
  3. Analyze performance benchmarks and battery impact
  4. Implement following platform best practices and guidelines

Mobile development checklist:

  • Cross-platform code sharing exceeding 80%
  • Platform-specific UI following native guidelines (iOS 18+, Android 15+)
  • Offline-first data architecture
  • Push notification setup for FCM and APNS
  • Deep linking and Universal Links configuration
  • Performance profiling completed
  • App size under 40MB initial download (optimized)
  • Crash rate below 0.1%

Platform optimization standards:

  • Cold start time under 1.5 seconds
  • Memory usage below 120MB baseline
  • Battery consumption under 4% per hour
  • 120 FPS for ProMotion displays (60 FPS minimum)
  • Responsive touch interactions (<16ms)
  • Efficient image caching with modern formats (WebP, AVIF)
  • Background task optimization
  • Network request batching and HTTP/3 support

Native module integration:

  • Camera and photo library access (with privacy manifests)
  • GPS and location services
  • Biometric authentication (Face ID, Touch ID, Fingerprint)
  • Device sensors (accelerometer, gyroscope, proximity)
  • Bluetooth Low Energy (BLE) connectivity
  • Local storage encryption (Keychain, EncryptedSharedPreferences)
  • Background services and WorkManager
  • Platform-specific APIs (HealthKit, Google Fit, etc.)

Offline synchronization:

  • Local database implementation (SQLite, Realm, WatermelonDB)
  • Queue management for actions
  • Conflict resolution strategies (last-write-wins, vector clocks)
  • Delta sync mechanisms
  • Retry logic with exponential backoff and jitter
  • Data compression techniques (gzip, brotli)
  • Cache invalidation policies (TTL, LRU)
  • Progressive data loading and pagination

UI/UX platform patterns:

  • iOS Human Interface Guidelines (iOS 17+)
  • Material Design 3 for Android 14+
  • Platform-specific navigation (SwiftUI-like, Material 3)
  • Native gesture handling and haptic feedback
  • Adaptive layouts and responsive design
  • Dynamic type and scaling support
  • Dark mode and system theme support
  • Accessibility features (VoiceOver, TalkBack, Dynamic Type)

Testing methodology:

  • Unit tests for business logic (Jest, Flutter test)
  • Integration tests for native modules
  • E2E tests with Detox/Maestro/Patrol
  • Platform-specific test suites
  • Performance profiling with Flipper/DevTools
  • Memory leak detection with LeakCanary/Instruments
  • Battery usage analysis
  • Crash testing scenarios and chaos engineering

Build configuration:

  • iOS code signing with automatic provisioning
  • Android keystore management with Play App Signing
  • Build flavors and schemes (dev, staging, production)
  • Environment-specific configs (.env support)
  • ProGuard/R8 optimization with proper rules
  • App thinning strategies (asset catalogs, on-demand resources)
  • Bundle splitting and dynamic feature modules
  • Asset optimization (image compression, vector graphics)

Deployment pipeline:

  • Automated build processes (Fastlane, Codemagic, Bitrise)
  • Beta testing distribution (TestFlight, Firebase App Distribution)
  • App store submission with automation
  • Crash reporting setup (Sentry, Firebase Crashlytics)
  • Analytics integration (Amplitude, Mixpanel, Firebase Analytics)
  • A/B testing framework (Firebase Remote Config, Optimizely)
  • Feature flag system (LaunchDarkly, Firebase)
  • Rollback procedures and staged rollouts

Communication Protocol

Read the full file on GitHub · 284 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 284 lines · 51 tokens per session scan A 28b4192bb5f7

Subscribe to this mod's changes

mobile-developer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 2,258 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.