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.
git clone --depth 1 https://github.com/AnilBurcu/claude-code-react-nativeWrote 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/plugins/anilburcu/claude-code-react-native/rn)<a href="https://agentmods.dev/plugins/anilburcu/claude-code-react-native/rn"><img src="https://agentmods.dev/badge/plugins/anilburcu/claude-code-react-native/rn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/anilburcu/claude-code-react-native/rn"><img src="https://agentmods.dev/badge/plugins/anilburcu/claude-code-react-native/rn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rn 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 1mo 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.
What it actually says
{
"name": "rn",
"displayName": "React Native Toolkit",
"version": "1.0.0",
"description": "Skills and agents that teach Claude Code how React Native apps actually break in production, and how to fix them.",
"author": {
"name": "Anil Burcu",
"url": "https://github.com/AnilBurcu"
},
"repository": "https://github.com/AnilBurcu/claude-code-react-native",
"license": "MIT",
"keywords": [
"react-native",
"expo",
"mobile",
"ios",
"android",
"eas",
"hermes"
]
}
What it installs
The manifest is a name and a version. 18 skills, 4 agents travel with it, and installing the plugin installs all of them — 881 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill deep-linking A 49 tokens
- Skill hermes-crashes A 51 tokens
- Skill eas-release A 40 tokens
- Skill in-app-purchases A 37 tokens
- Skill push-notifications A 48 tokens
- Skill supabase-mobile-auth A 48 tokens
- Skill monorepo-metro A 52 tokens
- Skill new-architecture A 50 tokens
- Skill rn-performance A 0 tokens
- Skill log-triage A 51 tokens
- Skill patching-libraries A 47 tokens
- Skill perf-audit A 37 tokens
- Skill prep-release A 40 tokens
- Skill fix-build A 40 tokens
- Skill new-arch-check A 33 tokens
- Skill upgrade-sdk A 25 tokens
- Skill expo-sdk-upgrade C 0 tokens
- Skill native-build-errors C 46 tokens
- Agent build-doctor A 48 tokens
- Agent crash-analyst A 52 tokens
- Agent perf-auditor A 44 tokens
- Agent release-checker A 43 tokens
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.
- 1mo ago Changed · +9 lines 8d40dc31049e
- 1mo ago First seen · 13 lines scan A c9703dc0adb6
rn is a plugin published in the GitHub repository AnilBurcu/claude-code-react-native (3 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
expo-56
Authoritative, version-pinned offline reference for Expo SDK 56 and SDK 57. One skill, 21 bundled API references, covering both building on either release and the 55→56 / 56→57 migrations. SDK 57 is current (57.0.8, RN 0.86); SDK 56 is the previous supported release (56.0.17, RN 0.85). Audited against expo/expo source.
metro-mcp
Plugin-based MCP server for React Native/Expo runtime debugging, inspection, and automation via Metro/CDP.
rn-devtools-hub
Drive a running React Native or Expo app from inside its JS runtime: semantic UI perception with source locations, actions without coordinates, structured assertions, deterministic time and network, and correlated session export.
flutter-slipstream
Live Flutter app introspection for coding agents: screenshots, widget-tree inspection, tap/type/scroll, and error capture. Dart package API summarization for agents.
expo-launchpad
Idea-to-playable harness for Expo (React Native + TypeScript) apps and games: research, plan, design, contract, and a generator-evaluator build loop with skeptical QA. --kind app|game.
playwright-for-android
MCP version of the Android debug skill. Exposes adb / emulator / logcat / screenshot / UI-tree as MCP tools; the host LLM (Claude Code) selects each UI action itself. No separate LLM API key required.