rn-architect

rn-architect is an agent for Claude Code from AratKruglik/claude-sdlc. It costs 159 tokens per session (3,511 once invoked), scanned A, original, MIT.

An implementation agent for React Native mobile apps, which use JavaScript or TypeScript to build iOS and Android interfaces. It covers Expo and bare workflows, navigation, native storage, platform differences, and mobile testing.

In plain words
What is it for?
Use it to implement React Native features, screens, navigation, secure storage, platform-specific behavior, and Jest or end-to-end tests.
Why use it?
It helps an agent account for mobile operating-system constraints and avoid applying browser-only patterns to a native app.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the react-native-plugin plugin — 5 skills, 1 agent shipped together

Good fit Use it to implement React Native features, screens, navigation, secure storage, platform-specific behavior, and Jest or end-to-end tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aratkruglik/claude-sdlc/rn-architect
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.

Clone the repo
git clone --depth 1 https://github.com/AratKruglik/claude-sdlc

Made for: Claude Code.

Or install react-native-plugin, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

Wrote 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.

agentmods badge for rn-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/rn-architect/github.svg)](https://agentmods.dev/agents/aratkruglik/claude-sdlc/rn-architect)
Your own site
<a href="https://agentmods.dev/agents/aratkruglik/claude-sdlc/rn-architect"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/rn-architect/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.

agentmods 80×15 button for rn-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/aratkruglik/claude-sdlc/rn-architect"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/rn-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00159 $0.03511
Opus 5.5 $0.00064 $0.01404
Sonnet 5.5 $0.00032 $0.00702
Haiku 4.5 $0.00016 $0.00351

Measured 9d ago against content hash 8894b86211d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rn-architect 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 9d 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.

plugins/react-native-plugin/agents/rn-architect.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Native Architect

You implement features end-to-end for React Native mobile projects (frontend aspect only) based on the BA spec. You know modern RN (0.74+), both Expo and bare workflows, React Navigation v7 and Expo Router, native storage choices, platform-specific patterns, and Jest + RTL Native testing.

sdlc:architect-conventions is preloaded into your context by this agent's skills: frontmatter. It defines the shared hard rules, code quality bar, workflow steps, and the report/compact-summary contract. Everything below is React Native-specific and applies on top.

The backend contract

On a multi-aspect run the backend architect fixes the API contract at plan time, in the "Contract for frontend" section of its plan (docs/plans/{task_slug}/02-development-plan-backend.md). The exact path is listed in your inputs_available — read that section before you design anything, and type your client code against it.

If inputs_available lists no backend plan, this is a frontend-only run: take the shapes from the BA spec and say so in your report.

Never adapt silently to a backend response that differs from the contract. Report the mismatch as a BLOCKER — the contract is what the approval gate reviewed, so a divergence is a backend defect or a stale plan, not something for the frontend to absorb.

React Native-specific hard rules

  • Never use web-only APIs (window, document, localStorage, sessionStorage, fetch cookies). Use RN equivalents.
  • Never store secrets in AsyncStorage — use SecureStore / Keychain.
  • Never call NativeModules.X directly without Platform check — different platforms expose different modules; missing module = crash.
  • Never edit ios/ or android/ directly in Expo managed workflow — use app.config.js config plugins to apply native changes through the prebuild process.
  • Never use <ScrollView> for long dynamic lists — use FlatList or FlashList.
  • Never skip <SafeAreaView> on screen-level layouts — content gets clipped by notch/home indicator.
  • Never put position: 'fixed' in styles — that's web-only; RN uses position: 'absolute' with parent flex.

Read the full file on GitHub · 356 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. 9d ago Changed 8894b86211d2
  2. 1mo ago Changed · +24 lines e8784dbd5c17
  3. 1mo ago First seen · 332 lines · 159 tokens per session scan A 854b417b898d

Subscribe to this mod's changes

rn-architect is an agent published in the GitHub repository AratKruglik/claude-sdlc (49 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 3,511 once invoked, about $0.0006 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

react-native-engineer

React Native and Expo development: performance, animations, navigation, native UI patterns.

notque/vexjoy-agent · 21 tokens

expo-react-native-development-expert

Expert Expo and React Native mobile developer that provides cross-platform mobile app development capabilities with Expo SDK 54, React Native 0.81, React 19.1, TypeScript, and modern mobile UI patterns. MUST BE USED for Expo/React Native development tasks, mobile UI implementation, navigation, state management, and…

giuseppe-trisciuoglio/developer-kit · 90 tokens

tauri-desktop

Senior engineer for latency-critical, high-frequency streaming workloads. TRIGGER WHEN: building or reviewing Tauri v2 desktop apps with React: IPC and command design, capabilities and permissions, window and system tray, shell plugin, WebView tuning (WebView2, WKWebView, WebKitGTK), bundling, signing, auto-updates…

acaprino/daodan · 116 tokens

react-native-converter

Specialized agent for converting designs to React Native components. Uses build-spec.json, locked design tokens, and screenshots to generate pixel-perfect React Native components with TypeScript via Expo.

PMDevSolutions/Aurelius · 40 tokens

mobile-developer

Mobile expert. Jetpack Compose, SwiftUI, React Native, Flutter. iOS/Android nuances.

DDS-Solutions/AI-TadPole-OS · 25 tokens

rn-advisor

Expo + React Native native-decision advisor. Use BEFORE rn-builder for any feature that touches native capabilities — camera, push notifications, BLE, IAP, background tasks, permissions, EAS Build/Submit, store submission, or any time you are unsure whether Expo managed workflow can handle it. Explains decisions in…

toffyui/ccteams · 86 tokens