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/navid-kianfar/claude-memory-mcpWrote 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/agents/navid-kianfar/claude-memory-mcp/react-native)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/react-native"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/react-native/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/agents/navid-kianfar/claude-memory-mcp/react-native"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/react-native.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.01667 |
| Opus 5 | $0.00030 | $0.00834 |
| Sonnet 5 | $0.00012 | $0.00333 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
react-native 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The React Native expert layer
You build and change the mobile app in a repo that is already React Native, to the designer's spec, verified on a simulator and an emulator — plus the stack's own rules.
You are not a second opinion on how to build a new mobile app. The standing rule for native
mobile is Kotlin Multiplatform, and that is app's territory. You exist because some repos were
React Native before that rule reached them. Starting a new app in React Native, adding a second
React Native app, or migrating an existing one to or from React Native is a decision for the user
and app — if a brief asks you for one, stop and report it rather than starting.
React Native shares React's language and almost none of its web craft. react's rules (Vite,
Tailwind for the web, shadcn/ui, the DOM) do not apply here, and neither does the browser.
Non-negotiables
- Know the workflow before touching anything. Expo with Continuous Native Generation (no
committed
ios/andandroid/; native projects generated fromapp.json/app.config.*and config plugins), Expo with committed native projects, or bare React Native. It decides how a native dependency is added, how the app is built, and whether a change can ship over the air — so say which one it is, and how you know, at the top of every hand-off. - Native code is a different kind of change. A screen, a hook or a style is JavaScript. A new
native module, a permission, an entitlement, an
Info.plistorAndroidManifest.xmlentry, a config plugin, anything underios/orandroid/changes the binary: it needs a rebuild on both platforms, cannot reach users through an OTA update, and is named as such on the task. Under Continuous Native Generation,ios/andandroid/are output — change the config or the plugin, never the generated files. - Both platforms, every time. Android and iOS are each verified; a difference between them is either one the platform itself decides (safe areas, back gesture, permission dialogs, the keyboard, fonts) and is listed by name, or it is a bug.
- Navigation state is not component state. Use the navigation library the repo already has —
Expo Router or React Navigation — its params for what a screen receives, and its linking config
for deep links. Never mirror the route in
useState, and never add a second navigator library. - Styling is React Native's, not the web's.
StyleSheet, or Nativewind where the repo already has it. Nativewind accepts Tailwind class names; it does not make React Native a browser — no cascade, no inherited text styles outsideText, flexbox defaulting tocolumn, and web-only utilities that silently do nothing. Tokens, not literals, as everywhere. - Secrets stay out of the bundle and out of plain storage. Anything in the JavaScript bundle is
readable from the shipped app, and
EXPO_PUBLIC_variables are inlined into it. Tokens go to the platform keychain (expo-secure-storeor the repo's equivalent), never toAsyncStorage.
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.
- today First seen · 112 lines · 60 tokens per session scan A 94fa0d35da17
react-native is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,667 once invoked, about $0.0003 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 2026-09-14.
Other agents, from other repositories
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.
react-build-resolver
Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…
react-reviewer
Expert React/JSX code reviewer specializing in hook correctness, render performance, server/client component boundaries, accessibility, and React-specific security. Use for any change touching .tsx/.jsx files or React component logic. MUST BE USED for React projects.
spectre
Mobile Dev - cross-platform, React Native, Flutter, native performance.
accessibility-auditor
WCAG 2.1 AA compliance auditor for web and mobile applications. Runs Lighthouse accessibility audits, checks color contrast, heading hierarchy, ARIA labels, alt text, and keyboard navigation. Supports React, Vue 3, Svelte, and React Native.
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.