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.
npx agentmods add skills/kensaurus/cursor-kenji/mobile-rn-screennpx skills add kensaurus/cursor-kenji --skill mobile-rn-screengit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/skills/kensaurus/cursor-kenji/mobile-rn-screen)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/mobile-rn-screen"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/mobile-rn-screen.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.05681 |
| Opus 5 | $0.00032 | $0.02840 |
| Sonnet 5 | $0.00013 | $0.01136 |
| Haiku 4.5 | $0.00006 | $0.00568 |
Grade A, and why
mobile-rn-screen 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.
How it starts
The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surface router:
/uiux. You are here:mobile-rn-screen. Native iOS/Android (SwiftUI / Compose, no web layer) is out of scope — use Apple HIG / Material directly.
Enhance Screen — React Native
Degree of freedom: MIXED. Pain, tier, and heuristic mapping
[HIGH freedom]; recon, screenshots, no-hex, and ReduceMotion
[LOW freedom — run exactly].
Turn an existing RN screen into a composed, native-feeling interface: calmer hierarchy, correct platform idioms, tight safe-area and keyboard handling, purposeful motion, and component primitives that work on both iOS and Android without forking.
How to reason
- Recon — screen file, tree, tokens, safe-area chain
- Rank — primary / secondary / metadata / actions
- Forensics — 3 sizes + keyboard + silent pains
- Primitive — fix the shared wrapper; no hex in the screen
Worked example
Recon: Home uses
ScreenContainer+ extrauseSafeAreaInsets().topon the back button. Rank: title is primary; streak count is metadata — it appears twice. Forensics: 360px back overlaps title (S1/S18); streak ×2 (S10). Primitive: drop the child inset; keep the hero streak; no new hex.
Self-critique before reporting
- Compose first — hierarchy/safe-area/targets before color or motion
- Both platforms — iOS shadow + Android elevation/ripple were both written
- Tokens only — no hex literals; ReduceMotion falls back to instant
- Right owner — FPS / bundle / Hermes →
mobile-rn-performance; emulator down →mobile-emulator-start
Vague-but-visceral native feedback ("button is weirdly big", "text gets cut off on my phone", "scrolling feels janky", "can't tap that", "looks like a web page") almost always maps to one of the Hidden Failure Modes (N1–N15) below — start there, not at decoration.
Before taking any screenshots, follow
mobile-emulator-startSKILL.md to bring up a working dev loop on the Android emulator. For iOS, trigger a CI build and install via TestFlight; the JS layer is verified on Android first (90%+ of "iOS bugs" are platform-agnostic RN/JS bugs).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 477 lines · 64 tokens per session scan A ce63554b1fe8
mobile-rn-screen is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 7d ago), licensed MIT. It adds 64 tokens to every session and 5,681 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 2026-09-03.
Other skills, from other repositories
flutter-pre-caching
Use when preloading fonts, asset/network images, Lottie/Rive animations, local JSON/config, warming initial API data, or optimizing Flutter Web startup.
bloc
Use when creating a Cubit or Bloc, modeling state with sealed classes or status enums, wiring BlocBuilder/BlocListener/BlocProvider, writing bloc tests, or choosing between Cubit and Bloc.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-database
Use when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline persistence, managing presence, sharding, or writing security rules.
flutter-app-architecture
Use when scaffolding a project, refactoring into layers, creating view models/repositories, configuring dependency injection, or implementing unidirectional data flow (MVVM).
generate-images-with-firebase-ai
Use when generating or editing images from Flutter/Dart with Firebase AI Logic and a Gemini image model (Nano Banana), making the first call work, choosing Gemini Developer API vs Vertex AI, hitting quota, billing or App Check failures, getting empty or image-only responses, sending a user photo as input, controlling…