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.
npx agentmods add agents/alexmmatos/arthur-mcp/mobile-developergit clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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.
[](https://agentmods.dev/agents/alexmmatos/arthur-mcp/mobile-developer)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Query context manager for mobile app architecture and platform requirements
- Review existing native modules and platform-specific code
- Analyze performance benchmarks and battery impact
- 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
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.
- today First seen · 284 lines · 51 tokens per session scan A 28b4192bb5f7
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.
Other agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
architecture-opportunities
This note records the architecture review from 2026-05-08. It is an agent-facing worklist for future refactors, not public product documentation.
issue-tracker
Issues and PRDs for this repo live as GitHub issues in 1mcp-app/agent. Use the GitHub CLI (gh) for issue operations.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the label strings used in this repo's issue tracker.
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.