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 simiancraft/simiancraft-skills --skill expo-ios-simulatorgit clone --depth 1 https://github.com/simiancraft/simiancraft-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/simiancraft/simiancraft-skills/expo-ios-simulator)<a href="https://agentmods.dev/skills/simiancraft/simiancraft-skills/expo-ios-simulator"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/expo-ios-simulator/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/simiancraft/simiancraft-skills/expo-ios-simulator"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/expo-ios-simulator.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 | $0.00153 | $0.00927 |
| Opus 5 | $0.00077 | $0.00464 |
| Sonnet 5 | $0.00031 | $0.00185 |
| Haiku 4.5 | $0.00015 | $0.00093 |
Grade A, and why
expo-ios-simulator scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Metro serving (`curl /status`) and the first bundle finishing (the tree grows labels); both How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expo on the iOS Simulator (layer on top of ios-simulator)
Everything here is Expo / React-Native runtime behavior, not the simulator itself (that is ios-simulator, which boots devices, captures screenshots, and grants permissions). This skill gets an Expo app running on a booted simulator and clears the Expo-specific overlays that stall automation. For "make the app driveable" see mobile-accessibility.
Before anything
A booted simulator and AXe installed; that is ios-simulator prerequisites.md. This
skill discovers everything app-specific (bundle id, scheme) from the app config; it never
hardcodes a project's nouns.
The loop
- Pick an execution mode (
references/execution-modes.md): Expo Go, a development build (dev client), Storybook-mobile, or web-on-mobile. The choice is forced by whether the app has custom native code. - Get the app on the device. Pure-JS app: Expo Go installs and launches it for you
(
references/expo-go.md). Anything with native modules or a config plugin: build and install a dev client (references/development-builds.md), then serve Metro and connect by deep link. - Clear the recurring prompts (
references/known-prompts.md): the "Open in app?" deep-link dialog, the push-token alert that re-fires and stacks on each reload, and the dev menu; avoid the element-inspector trap. Clear each by accessibility, never coordinates. - Drive it. The driving primitive is ios-simulator
references/driving.md(axe tap --id/--label); what makes the app addressable is mobile-accessibility.
Rules
- Discover bundle id and scheme from the app config; never hardcode them.
- Never drive a bundling app. Two readiness gates sit between "launched" and "driveable":
Metro serving (
curl /status) and the first bundle finishing (the tree grows labels); both recipes are inreferences/development-builds.md. Taps dispatched before them report success and do nothing. - Clear every Expo dialog and overlay by accessibility (
axe tap --label), not coordinates. - Every factual claim here and in the references cites a primary source (Expo, Apple, AXe's own help); a prior-art skill is never a source.
What ships with it
4 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.
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 First seen · 72 lines · 153 tokens per session scan A 6605902316f0
expo-ios-simulator is a skill published in the GitHub repository simiancraft/simiancraft-skills (7 stars, last pushed 8d ago), licensed MIT. It adds 153 tokens to every session and 927 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-mobile-app
Use when the user wants to start a new Power Apps mobile app (Expo / React Native / TypeScript, targeting iOS and Android) from scratch.
stitch-react-native-components
Converts a Stitch mobile screen, a local HTML file, or a URL into React Native / Expo components — TypeScript, StyleSheet, Expo Router, dark mode via useColorScheme, and proper touch targets. Cross-platform iOS and Android. Only the Stitch route needs an API key.
frontend
Use when building React components, optimizing performance, analyzing bundle sizes, scaffolding projects, implementing accessibility, reviewing frontend code quality, performing visual overhauls, or designing UI/UX systems.
mobile-native-bestpractices
Build or review React Native / Expo code for architecture, UX, performance and native best practices. Use when writing or reviewing a React Native / Expo app. Triggers on: react native, expo, app nativo, boas praticas mobile nativo, arquitetura react native, performance no app nativo, react native review.
expo-56
Authoritative, version-pinned reference for Expo SDK 56 and SDK 57 — both postdate your training, so defer to this skill over memory for anything Expo. SDK 57 is the current release (2026-07-08, React Native 0.86); SDK 56 is the previous, still-supported release (React Native 0.85). Use it whenever the user is…
new-architecture
Reference for React Native New Architecture (Fabric, TurboModules, bridgeless) compatibility work. Use when a library breaks under the New Architecture, when deciding whether to enable or disable newArchEnabled, or when errors mention codegen, Fabric, ViewPropTypes or requireNativeComponent.