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-emulator-testnpx skills add kensaurus/cursor-kenji --skill mobile-emulator-testgit 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-emulator-test)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/mobile-emulator-test"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/mobile-emulator-test.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 5.1 | $0.00074 | $0.05129 |
| Opus 5 | $0.00037 | $0.02565 |
| Sonnet 5 | $0.00015 | $0.01026 |
| Haiku 4.5 | $0.00007 | $0.00513 |
Grade A, and why
mobile-emulator-test scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf "http://localhost:${METRO_PORT}/status" How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mobile-emulator-test — Native build QA on Android emulator + MCP loop
Degree of freedom: MIXED. Walk judgment and findings [HIGH freedom];
bring-up, Phase 1.5 freshness, and three-layer CRUD
[LOW freedom — run exactly].
End-to-end verification of any native mobile build through a real Android emulator session, with backend truth (Supabase MCP) and crash telemetry (Sentry MCP) wired into the same loop. Catches the failure modes that pure unit tests and CI bundle builds miss: white screens, prototype-stripped cache rehydration, missing migrations, sync-disabled empty states, infinite refetch loops, and silent error swallows.
How to reason
- Discover — stack, tabs, MCP, signed-in test account
- Freshness — source + Metro bundle + device (Phase 1.5)
- Walk — guest AND signed-in; every tab
- Three-layer — UI success + DB row + cold refetch; evidence per finding
Worked example
Discover: Expo router; five tabs; Supabase MCP live; Sentry MCP missing (mark BLOCKED). Freshness: user said "nothing changed"; bundle
grepof the patch string = 0 →--clearMetro, then reload. Walk: guest create fails closed; signed-in create shows toast. Three-layer: toast yes,execute_sqlfinds the row, kill/reopen still shows it. Finding: guest path only.
Self-critique before reporting
- Fresh build — source, bundle, and screencap all show the patched string
- Both identities — guest and signed-in walks ran; empty-state is not the only path
- Three layers — no mutation called "tested" on UI toast alone
- Right owner — bring-up only →
mobile-emulator-start; store/plugins/OTA →mobile-capacitor-platform
Critical Rules
Test as a real signed-in user AND as a brand-new guest. Walk the app the way a paying customer would — sign in, browse every tab, add a real entry, edit it, delete it — AND the way a new user would — open the app fresh, hit the guest path, drive a CRUD round-trip without any account. Both paths exercise different code (sync replica vs cloud direct vs local-only adapter) and both regress independently. While walking, watch logcat, Sentry, and the DB at the same time.
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.
- 2d ago First seen · 491 lines · 74 tokens per session scan A f34ccc05afc8
mobile-emulator-test is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 7d ago), licensed MIT. It adds 74 tokens to every session and 5,129 once invoked, about $0.0004 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 2026-09-03.
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).
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
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).