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 skills add e-t-y-b/etyb-skills --skill expogit clone --depth 1 https://github.com/e-t-y-b/etyb-skillsWrote 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/e-t-y-b/etyb-skills/expo)<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/expo"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/expo/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/skills/e-t-y-b/etyb-skills/expo"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/expo.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 | $0.00240 | $0.03470 |
| Opus 5 | $0.00120 | $0.01735 |
| Sonnet 5 | $0.00048 | $0.00694 |
| Haiku 4.5 | $0.00024 | $0.00347 |
Grade A, and why
stack-expo 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expo Stack — Team Briefing
This is a knowledge overlay, not a new specialist. The existing ETYB team does the work — backend-architect writes the backend code, devops-engineer wires the deploys, security-engineer enforces the boundary. This pack tells each role where the current Expo knowledge lives.
Where the full briefing lives
The full Stack briefing lives in this same folder. Per-product and per-role pages are siblings of this SKILL.md. Every page carries last_verified_on stamps and authoritative-source URLs in its frontmatter; see skills/etyb/core/knowledge-currency.md for the drift-check protocol that uses them.
- Stack briefing:
stacks/expo/index.md - Per-product pages:
stacks/expo/<product>.md— one per entry inproducts_coveredabove - Per-role views:
stacks/expo/<role>.md— one per role inapplies_to_rolesabove
When ETYB is installed locally these are read directly from disk. For third-party agents without the install, the same content is reachable as raw markdown at https://raw.githubusercontent.com/e-t-y-b/etyb-skills/main/stacks/expo/<page>.md.
When delegate_to_skills (frontmatter above) lists a first-party vendor MCP/skill that's installed in the user's environment, ETYB defers to it first. The in-repo Stack content is the curated fallback.
What changed in 2025-2026 that older training data misses
Critical context — an LLM with a 2024 cutoff will get these wrong:
- The New Architecture is mandatory. SDK 51 made Fabric + TurboModules the default; SDK 53 made the old architecture opt-out impossible inside Expo; React Native 0.82 forced bridgeless mode platform-wide. As of SDK 55 / RN 0.83 you cannot opt out. Any answer that says "you can disable the new architecture" is wrong for current SDKs.
- Hermes is the only JS engine. JavaScriptCore was removed from React Native; Hermes V1 is default and only. No
jsEngine: 'jsc'inapp.json. expoCLI replacesreact-nativeCLI for everything in managed and prebuild workflows.npx expo start,npx expo run:ios,npx expo prebuild,npx expo install. The oldreact-native run-iosis bare-only and inferior. Do not recommend it for Expo projects.expo-cli(the global v0–v6) is dead. Usenpx expoper-project. Don'tnpm i -g expo-cli.- EAS Update replaces CodePush. Microsoft App Center retired March 2025; for any Expo project, EAS Update with Hermes bytecode diffing + branch-based channels is the answer.
- EAS Hosting is GA. Launched 2024-2025, GA in 2025. Expo Router web + API routes deploy here; the runtime is Cloudflare Workers. Plumbing differs from Vercel/Node.
- Continuous Native Generation (CNG) is the recommended workflow. Do not commit
ios/andandroid/folders. The native projects are regenerated bynpx expo prebuild, configured by config plugins, and built by EAS Build. - Expo Router is the default router in
create-expo-appsince SDK 50, stable since SDK 51. Typed routes are GA. Data loaders are experimental in SDK 55. SSR/static rendering for web is GA. - Expo API Routes (
+api.tsfiles inapp/) deploy as EAS Hosting workers. They are not Node — they're Cloudflare-Workers-compatible. Many Node-only packages won't work. - Expo Push uses FCMv1 only since June 2024. Legacy FCM HTTP API is retired. APNs must use token auth (
.p8key) — certificate auth is deprecated. - The Expo Go limitations are real. Expo Go cannot load arbitrary native modules; it ships a fixed set. Any third-party library with native code that isn't already in Expo Go requires a dev client. Default new projects to a dev client unless the work is genuinely a throwaway demo.
- React 19.2 in SDK 55 means: actions,
useFormStatus,useOptimistic,use(), server components groundwork, the new<Activity>API. React 19 also broke a number of older RN libraries.
What ships with it
34 files 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.
- app-config.md 5.5 KB
- continuous-native-generation.md 5.6 KB
- custom-dev-clients.md 5.7 KB
- devops-engineer.md 16 KB
- eas-build.md 6.6 KB
- eas-cli.md 4.4 KB
- eas-hosting.md 6.5 KB
- eas-submit.md 5.9 KB
- eas-update.md 7.5 KB
- eas-workflows.md 5.9 KB
- expo-api-routes.md 6.8 KB
- expo-auth-session.md 6.0 KB
- expo-camera.md 5.3 KB
- expo-cli.md 4.6 KB
- expo-dev-client.md 3.4 KB
- expo-doctor.md 3.7 KB
- expo-dom-components.md 5.7 KB
- expo-file-system.md 4.5 KB
- expo-go.md 4.6 KB
- expo-image.md 4.3 KB
- expo-location.md 5.2 KB
- expo-modules.md 5.3 KB
- expo-notifications.md 6.5 KB
- expo-router.md 7.2 KB
- expo-sdk.md 5.5 KB
- expo-secure-store.md 4.8 KB
- frontend-architect.md 14 KB
- hermes.md 4.2 KB
- index.md 16 KB
- metro-bundler.md 4.8 KB
- mobile-architect.md 15 KB
- new-architecture.md 5.6 KB
- qa-engineer.md 16 KB
- snack.md 3.4 KB
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.
- 12d ago First seen · 127 lines · 240 tokens per session scan A 20113ee4a2bc
stack-expo is a skill published in the GitHub repository e-t-y-b/etyb-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 240 tokens to every session and 3,470 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
design-first
Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or…
deploy-edge-ai-model
Deploy machine learning models to edge devices using Google AI Edge Gallery, TensorFlow Lite, ONNX Runtime, and MediaPipe. Covers model quantization (INT8/INT4), on-device inference with Gemma 4 models, Android/iOS deployment via AI Edge Gallery, hardware delegate selection (GPU/NPU/DSP), and performance benchmarking…
mobile-development
Build, test, sign, and ship mobile apps across iOS, Android, Flutter, and React Native — project scaffolding, builds and code signing, device and emulator testing, store submission (App Store and Play Store), app lifecycle and backgrounding, offline and sync, and mobile-specific testing. Use when the task involves…
bmob-database-android
Use when implementing Bmob NoSQL database CRUD in an Android Native project (Java or Kotlin). Triggers: io.github.bmob:android-sdk, Bmob.initialize(this, ...), BmobObject, BmobQuery, BmobUser, BmobInstallation, BmobFile, BmobRelation, BmobGeoPoint, BmobDate, SaveListener, UpdateListener, FindListener, QueryListener…
bmob-database-flutter
Use when implementing Bmob NoSQL database CRUD in a Flutter / Dart project with the official bmobplugin package. Triggers: flutter pub add bmobplugin, package:bmobplugin/bmobplugin.dart, Bmob.initialize, BmobQuery, BmobObject, BmobUser, BmobFile, BmobGeoPoint, BmobRelation, BmobAcl, BmobError.convert, blog.save()…
bmob-database-ios
Use when implementing Bmob NoSQL database CRUD in an iOS native project — both Objective-C and Swift / SwiftUI / UIKit. Triggers: BmobSDK, BmobSDK.xcframework, pod 'BmobSDK', #import , Bmob registerWithAppKey, [Bmob register(withAppKey:)], BmobObject objectWithClassName, BmobQuery queryWithClassName, BmobUser…