mcp-react-native-toolkit copilot-instructions.md

A set of GitHub Copilot instructions for React Native and Expo mobile projects. React Native builds mobile apps with JavaScript or TypeScript, while Expo provides tools and services around React Native.

In plain words
What is it for?
Use it to check project context, validate React Native and Expo APIs, choose correct imports, write typed functional components, and apply mobile performance practices.
Why use it?
It reduces mistakes caused by using APIs or third-party libraries that do not match the project's versions and platform needs.

Instructions file for GitHub Copilot

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 instructions/itamiforge/mcp-react-native-toolkit/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/ItamiForge/mcp-react-native-toolkit

Made for: GitHub Copilot.

Per session 1,296 This file is loaded in full into every session.
When invoked 1,296 The same file — it is already loaded in full.
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 $0.01296 $0.01296
Opus 5 $0.00648 $0.00648
Sonnet 5 $0.00259 $0.00259
Haiku 4.5 $0.00130 $0.00130

Measured yesterday against content hash 4245c0005cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-react-native-toolkit copilot-instructions.md 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.

templates/.github/copilot-instructions.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot (VS Code) Instructions

Project Context

React Native/Expo Mobile Development Project

This project uses React Native and/or Expo for cross-platform mobile development. Follow these guidelines to provide accurate and helpful assistance.

Core Rules

  • Always detect project context before suggesting code (check package.json for versions)
  • Verify APIs exist for the detected React Native/Expo version before suggesting
  • Use TypeScript with proper type annotations unless the project uses JavaScript
  • Follow React Native performance best practices (memo, useCallback, FlatList optimization)
  • Prefer functional components with hooks over class components
  • Handle platform differences when necessary using Platform.OS or platform-specific files

API Validation

  • Check React Native version before using new APIs (e.g., useWindowDimensions requires RN 0.61+)
  • Check Expo SDK version for Expo-specific APIs
  • Verify third-party library versions (React Navigation, Reanimated, Gesture Handler, etc.)
  • Use optional chaining and nullish coalescing for safer code
  • Import from correct packages (react-native vs expo-* vs @react-navigation/*)

Best Practices

  • Use FlatList/SectionList for long lists, never ScrollView with many items
  • Implement proper loading states and error handling
  • Use React.memo() for pure components that render often
  • Avoid inline functions in render for frequently re-rendering components
  • Use StyleSheet.create() instead of inline styles for performance
  • Handle keyboard avoiding behavior for forms
  • Test on both iOS and Android platforms
  • Use proper accessibility labels and hints
  • Use React Navigation for routing (@react-navigation/native)
  • Properly type navigation props with TypeScript
  • Use navigation.navigate() with proper screen names
  • Handle deep linking when required
  • Configure proper header options for screens

State Management

  • Use React Context for simple state sharing
  • Consider Zustand, Jotai, or Redux Toolkit for complex state
  • Use React Query or SWR for server state
  • Persist state with MMKV or AsyncStorage as appropriate
  • Avoid prop drilling more than 2-3 levels deep

Read the full file on GitHub · 194 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 · 194 lines · 1,296 tokens per session scan A 4245c0005cfa

Subscribe to this mod's changes

mcp-react-native-toolkit copilot-instructions.md is an instructions file published in the GitHub repository ItamiForge/mcp-react-native-toolkit (0 stars, last pushed 14d ago), licensed MIT. It adds 1,296 tokens to every session, about $0.0065 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.