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 monkilabs/opencastle --skill expo-developmentgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/expo-development)<a href="https://agentmods.dev/skills/monkilabs/opencastle/expo-development"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/expo-development/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/monkilabs/opencastle/expo-development"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/expo-development.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 | $0.00044 | $0.00513 |
| Opus 5.5 | $0.00018 | $0.00205 |
| Sonnet 5.5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
expo-development 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 11d 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.
What it actually says
Expo Development
Continuous Native Generation
- Never eject, never edit
ios/orandroid/—npx expo prebuildregenerates both fromapp.json/app.config.ts, so hand edits vanish. Gitignore both directories.npx expo prebuild --cleanwhen native state is suspect. - Native config changes go through config plugins (
app.plugin.js, registered inexpo.plugins) applied at prebuild time.npx create-expo-modulescaffolds a Swift + Kotlin module. - Install with
npx expo install, notnpm install, so versions resolve against the SDK.npx expo install --fixrepairs an SDK version mismatch.
EAS Build / Update
eas.jsonprofiles: development =developmentClient: true+distribution: internal; preview =distribution: internal+channel; production =channel+autoIncrement: true.- Set
runtimeVersion: { policy: "fingerprint" }in app.json.eas update --channel productionships JS only — a runtimeVersion mismatch forces a new binary build, and native changes can never go OTA. - Rollback:
eas update:republish --group <previous-group-id>. Diagnose failures viaeas build:listtheneas build:view <id>. - Secrets belong in EAS environment variables with secret visibility (
eas env:create --visibility secret;eas secret:createis deprecated), neverapp.json; device-side storage viaexpo-secure-store. - iOS signing failures:
eas credentials. CI/CD lives in.eas/workflows/.
Expo Router
Files under app/ are routes; a _layout.tsx per directory supplies <Stack> / <Tabs> / <Drawer>. Parenthesized directories are groups and do not appear in the URL — app/(auth)/login.tsx serves /login. Read dynamic segments with useLocalSearchParams(). Deep links require scheme in app.json; myapp://user/123 then resolves to app/user/[id].tsx.
Docs: https://docs.expo.dev/
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.
- 11d ago Changed · -25 tokens per session 8a077bef2af2
- 12d ago First seen · 27 lines · 69 tokens per session scan A 9bd50a625c09
expo-development is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 513 once invoked, about $0.0002 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 2026-10-04.
Other skills, from other repositories
push-notification-tester
Test VoIP push notifications for Telnyx WebRTC iOS (APNs) and Android (FCM) apps. Use when debugging push notification delivery, validating certificate/credential setup, or testing that a device receives VoIP pushes correctly.
product-architect
Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…
mobile-design-android
Mobile-first Android design thinking, Jetpack Compose, Material 3 (M3), Compose Navigation 3, Compose Material 3 Adaptive layouts, StateFlow / ViewModel state management, and Android platform conventions. Synchronized with official Google Developer documentation.
mobile-design-ios
Mobile-first iOS design thinking, SwiftUI, UIKit, Apple Human Interface Guidelines (HIG), SF Symbols, NavigationStack/SplitView, @Observable macro, SwiftData/Core Data, and iOS platform conventions.
cursor-prompting
Internal guidance for composing cursor-agent prompts and picking models for coding, review, diagnosis, and research tasks inside the Cursor Claude Code plugin.
goal-runner
Use when the user asks to advance, continue, or work on the project's long-horizon goal (or to set one up) — the policy for goal-driven increments driven through the goal companion, one increment at a time, delegated via the codex/cursor delegation skills, honestly recorded.