Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/textura-agency/next16-claude-starternpx agentmods add skills/textura-agency/next16-claude-starter/mobile-device-qaWrote 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/textura-agency/next16-claude-starter/mobile-device-qa)<a href="https://agentmods.dev/skills/textura-agency/next16-claude-starter/mobile-device-qa"><img src="https://agentmods.dev/badge/skills/textura-agency/next16-claude-starter/mobile-device-qa/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/textura-agency/next16-claude-starter/mobile-device-qa"><img src="https://agentmods.dev/badge/skills/textura-agency/next16-claude-starter/mobile-device-qa.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 | $0.00235 | $0.05390 |
| Opus 5.5 | $0.00094 | $0.02156 |
| Sonnet 5.5 | $0.00047 | $0.01078 |
| Haiku 4.5 | $0.00023 | $0.00539 |
Grade A, and why
mobile-device-qa 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 10d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile device QA
Lighthouse loads a page nobody touches; the scroll test scrolls it in desktop Chrome with a phone's viewport and a throttled CPU. Neither has Safari's collapsing toolbar, a 120 Hz panel, a finger, a gyroscope, iOS's memory pressure or a phone in dark mode. Every item below passed both instruments on production sites and was then found by a person holding an iPhone. This skill is that person's checklist, with the mechanism, the fix and a way to prove it without the phone — and an honest line for what still needs one.
Each item: symptom (what a reviewer saw) → cause → fix → prove it. Rule = held on ≥ 3 sites; observed = 1–2.
Setup. yarn build && yarn start, yarn qa:setup once. Every tool takes
--url (tools/qa/README.md). Probes run with a person's UA — the default
headless UA gets the robot form (no motion, no scene, no cursor) and "proves"
a bug gone that a person still sees. Look at every screenshot (Read the image).
Copy-paste probes and code shapes: references/recipes.md.
When the bug is iOS-only, reproduce it in WebKit first. Twice a fix passed
every headless-Chrome probe and failed on the phone (a hero scene vanishing
after scroll). node tools/qa/webkit-probe.mjs --url … runs Playwright's WebKit
with an iPhone profile and touch. Reproduce → fix → the same probe passes. If
WebKit can't reproduce it either, ship a fix that removes the mechanism and a
self-check that recovers the state, and say plainly it is unverified on iOS.
1. The iOS toolbar resizes the viewport mid-scroll
Symptom: "the scene flickers when I scroll", "the hero re-renders when I change scroll direction", "the section resizes on iOS", balls in a physics scene jump. Rule (5 sites).
Cause: Safari's URL bar collapses and expands as you scroll: innerHeight
changes and resize fires. Boxes sized 100dvh / 100vh-via-JS /
fixed inset-0 / innerHeight change height; a WebGL renderer that follows
reallocates its drawing buffer (cleared → a blank frame) and redraws; code that
re-randomises or re-lays-out on resize visibly jumps. r3f's <Canvas frameloop="never"> re-applies the prop on each re-render — after the second
resize one scene stayed black.
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.
- 10d ago Changed · +18 lines 8a08c6b5f379
- 11d ago First seen · 303 lines · 235 tokens per session scan A e519a0fe92de
mobile-device-qa is a skill published in the GitHub repository textura-agency/next16-claude-starter (137 stars, last pushed 3d ago), licensed Unlicense. It adds 235 tokens to every session and 5,390 once invoked, about $0.0009 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 2026-10-07.
Other skills, from other repositories
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
eas-simulator
Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any eas simulator: commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas simulator to…
flutter-add-widget-test
Implement a component-level test using WidgetTester to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected.