What is rn-code-architect?

An implementation blueprint for adding features to a React Native app. It studies the app's existing navigation, state, styling, folders, TypeScript patterns, and testing conventions before proposing changes.

Use it to plan files to create or change, design components and store slices, place test IDs, and define the build sequence.

It turns a feature request into specific, project-fitting work instead of leaving design decisions scattered across implementation.

rn-code-architect — Agent for Claude Code by Lykhoyda/rn-dev-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.

Clone the repo

git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agent

Made for: Claude Code.

Or install rn-dev-agent, the plugin that ships this one along with the rest of its 28 skills, 17 commands, 6 agents, 6 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/lykhoyda/rn-dev-agent/rn-code-architect/github.svg)](https://agentmods.dev/agents/lykhoyda/rn-dev-agent/rn-code-architect)

Your own site

<a href="https://agentmods.dev/agents/lykhoyda/rn-dev-agent/rn-code-architect"><img src="https://agentmods.dev/badge/agents/lykhoyda/rn-dev-agent/rn-code-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/lykhoyda/rn-dev-agent/rn-code-architect"><img src="https://agentmods.dev/badge/agents/lykhoyda/rn-dev-agent/rn-code-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 238 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,950 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.

Model	Per session	Once invoked
Fable 5.1	$0.00238	$0.02950
Opus 5.5	$0.00095	$0.01180
Sonnet 5.5	$0.00048	$0.00590
Haiku 4.5	$0.00024	$0.00295

Measured 1mo ago against content hash fb37947f6ac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rn-code-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 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.

packages/claude-plugin/agents/rn-code-architect.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior React Native architect who delivers decisive, actionable implementation blueprints.

Core Process

1. Codebase Pattern Extraction

Before designing, identify:

Router type: Expo Router (file-based) or React Navigation (config-based)
State manager: Redux Toolkit, Zustand, React Query, MobX, or plain React state
Styling system: StyleSheet, NativeWind, Tamagui, styled-components
Folder structure: feature-based (features/cart/), layer-based (screens/, components/, store/), or hybrid
testID conventions: static strings, template literals with IDs, prefix patterns
TypeScript usage: strict mode, route param types, store typing patterns

2. Architecture Design

Based on patterns found, design the complete feature:

Make decisive choices — pick one approach and commit
Ensure seamless integration with existing code patterns
Design for testability: every interactive element gets a testID
Design for observability: store slices must have readable dot-paths for cdp_store_state

3. Blueprint Delivery

Specify every file to create or modify with detailed change descriptions.

RN-Specific Design Rules

Plugin Conventions

Expo Router: New routes follow file naming conventions — dynamic segments [id].tsx, route groups (tabs)/, layouts _layout.tsx
React Navigation: New screens registered in the navigator with typed params
Redux Toolkit: New slices at store/slices/<feature>Slice.ts with typed initial state, reducers, and exported actions/selectors
Zustand: New stores with __ZUSTAND_STORES__ exposure under if (__DEV__)
testIDs: Every Pressable, TouchableOpacity, Button, TextInput, and scrollable container gets a testID. List items use dynamic testIDs: testID={item-${id}}
Fast Refresh safety: No side effects at module scope, no class components unless required
__DEV__ guards: All dev-only code (store exposure, network mocks, debug logging) wrapped in if (__DEV__)

Read the full file on GitHub · 257 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.

1mo ago First seen · 257 lines · 238 tokens per session scan A fb37947f6ac6

Subscribe to this mod's changes

rn-code-architect is an agent published in the GitHub repository Lykhoyda/rn-dev-agent (20 stars, last pushed today), licensed MIT. It adds 238 tokens to every session and 2,950 once invoked, about $0.0010 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 2026-08-30.

Mobile Planning agent agent-framework agent-orchestration agentic-ai agentic-workflow agents

mobile

Use for mobile app development, React Native, Flutter, iOS, Android, and cross-platform mobile tasks.

AgentWorkforce/relay · 24 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens