react-native-savant

A specialist guide for building React Native mobile apps, including projects using Expo, iOS, and Android. React Native lets developers create mobile interfaces with JavaScript and React.

In plain words
What is it for?
Use it to choose app architecture, state management, navigation, databases, authentication, and notification systems, or to investigate performance, memory, native-module, compatibility, and app-size issues.
Why use it?
It helps with architectural choices and difficult mobile-development problems where platform differences, native code, performance, or deployment can complicate the work.

Agent

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/rcdelacruz/claude-code-agents/react-native-savant
Clone the repo
git clone --depth 1 https://github.com/rcdelacruz/claude-code-agents
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,538 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 $0.00000 $0.03538
Opus 5 $0.00000 $0.01769
Sonnet 5 $0.00000 $0.00708
Haiku 4.5 $0.00000 $0.00354

Measured 2d ago against content hash 96ee366c3cb7, 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-savant 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 2d ago.

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.

docs/agents/react-native-savant.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Native Savant

Overview

The React Native Savant is a master expert with comprehensive, deep knowledge across the entire React Native and mobile development ecosystem. This Tier 1 orchestrator agent guides mobile application development from architecture to deployment, with expertise spanning React Native, Expo, iOS, Android, and modern mobile development practices.

When to Use

Use the React Native Savant when you need:

Architecture Decisions

  • Choosing between Expo managed vs bare workflow
  • State management architecture (Redux vs Zustand vs Context)
  • Navigation architecture (Expo Router vs React Navigation)
  • Offline-first architecture design
  • Microservices vs monolithic mobile backend

Complex Mobile Problems

  • Performance bottlenecks and optimization
  • Native module integration (Swift/Kotlin)
  • Cross-platform compatibility issues
  • App size optimization and code splitting
  • Memory leak detection and resolution

High-Level Technical Decisions

  • Technology stack selection (Expo vs React Native CLI)
  • Database choice (SQLite vs Realm vs WatermelonDB)
  • Authentication strategy (OAuth, biometrics, JWT)
  • Push notification architecture
  • CI/CD pipeline setup

Full-Stack Mobile Applications

  • End-to-end mobile app development
  • Backend integration (GraphQL, REST, WebSockets)
  • Real-time features (chat, live updates, notifications)
  • E-commerce mobile apps
  • Social media applications

Native Platform Integration

  • iOS-specific features (HealthKit, ARKit, Widgets)
  • Android-specific features (WorkManager, Widgets, Android Auto)
  • Platform-specific UI/UX patterns
  • Native code bridging and optimization

Migration & Modernization

  • Expo SDK upgrades
  • React Native version upgrades
  • New Architecture migration (Fabric, Turbo Modules)
  • Web-to-mobile code sharing (React Native Web)

Core Expertise

React Native Framework (0.73+)

  • Core Architecture: Fabric renderer, Turbo Modules, JSI (JavaScript Interface), Bridge architecture
  • Components: View, Text, Image, ScrollView, FlatList, SectionList, Pressable, Modal, SafeAreaView
  • Hooks: useState, useEffect, useCallback, useMemo, useRef, useContext, useReducer
  • Native Modules: Bridging native code, Turbo Modules, JSI modules, Platform-specific code
  • Styling: StyleSheet, Flexbox, Platform-specific styles, appearance APIs
  • Performance: React.memo, useMemo, useCallback, FlatList optimization, Hermes engine
  • New Architecture: Fabric renderer, Turbo Modules, JSI, CodeGen, TurboModuleProvider

Read the full file on GitHub · 427 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. 2d ago First seen · 427 lines · 0 tokens per session scan A 96ee366c3cb7

Subscribe to this mod's changes

react-native-savant is an agent published in the GitHub repository rcdelacruz/claude-code-agents (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,538 tokens. 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.