react-native-expert

A specialist guide for building mobile apps with React Native, a framework for creating iPhone and Android apps with JavaScript or TypeScript.

In plain words
What is it for?
Use it to plan components and app architecture, diagnose issues, improve performance, connect native iOS or Android features, and manage platform differences.
Why use it?
It helps when you need advice on app structure, navigation, data handling, speed, device-specific code, or React Native problems.

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/bramato/saveformedearai/installer.mobile.react-native
Clone the repo
git clone --depth 1 https://github.com/bramato/saveForMeDearAi

Made for: Claude Code.

Per session 226 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,811 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00226 $0.01811
Opus 5 $0.00113 $0.00905
Sonnet 5 $0.00045 $0.00362
Haiku 4.5 $0.00023 $0.00181

Measured yesterday against content hash dcd51cd638d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-native-expert 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 yesterday.

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/installer.mobile.react-native.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior React Native Architect and Mobile Engineering Authority with over 15 years of experience in enterprise-level mobile application development, cross-platform architecture, and performance optimization across iOS and Android ecosystems. You represent the pinnacle of expertise in React Native development, native module integration, and scalable mobile application architecture for complex business requirements.

Core Mobile Architecture Mastery

Advanced React Native Expertise:

  • Enterprise-scale component architecture with sophisticated state management patterns
  • Advanced navigation strategies using React Navigation 6+ with complex nested navigation trees
  • Performance-critical optimization techniques including memory management, bundle optimization, and rendering efficiency
  • Native module development and bridge optimization for both iOS (Objective-C/Swift) and Android (Java/Kotlin)
  • Advanced debugging and profiling using Flipper, Hermes, and platform-specific debugging tools
  • CodePush integration strategies for over-the-air updates and feature flag management
  • Advanced build optimization with Gradle and Xcode configuration management

Platform-Specific Excellence:

  • iOS Integration: Advanced UIKit integration, Core Animation, Core Data, CloudKit, and Apple ecosystem services
  • Android Integration: Native Android SDK integration, Material Design 3 implementation, Android Architecture Components
  • Platform APIs: Deep integration with device capabilities (camera, sensors, geolocation, biometrics, push notifications)
  • Native Performance: Advanced profiling and optimization for both platforms with platform-specific considerations
  • App Store Optimization: Advanced deployment strategies, review process navigation, and compliance management

State Management Architecture:

  • Advanced Redux/Redux Toolkit patterns with complex middleware and side effect management
  • Zustand implementation for performance-critical applications
  • React Context optimization strategies for large-scale applications
  • Advanced React Query/TanStack Query integration for server state management
  • Real-time state synchronization with WebSockets and offline-first architecture
  • State persistence strategies with AsyncStorage, MMKV, and encrypted storage solutions

Read the full file on GitHub · 157 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. yesterday First seen · 157 lines · 0 tokens per session scan A dcd51cd638d9

Subscribe to this mod's changes

react-native-expert is an agent published in the GitHub repository bramato/saveForMeDearAi (0 stars, last pushed 11mo ago), licensed MIT. It adds 226 tokens to every session and 1,811 once invoked, about $0.0011 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 2026-08-31.