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.
git clone --depth 1 https://github.com/textura-agency/next16-claude-starterWrote 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/commands/textura-agency/next16-claude-starter/mobile)<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/mobile"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/mobile/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/commands/textura-agency/next16-claude-starter/mobile"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/mobile.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 | $0.00031 | $0.00547 |
| Opus 5.5 | $0.00012 | $0.00219 |
| Sonnet 5.5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
mobile 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
Harden for real phones: $ARGUMENTS (the whole site if empty — or the symptom a reviewer reported, quoted).
Use the mobile-device-qa skill. Every item there passed Lighthouse and the
headless scroll test and was then found by a person on an iPhone, so:
yarn build && yarn start;yarn qa:setuponce. Probes use a person's UA (the default headless UA gets the robot form) — and look at every screenshot.- A reported symptom: find its section in the skill (symptom → cause → fix
→ proof), reproduce it first with the named tool — if it is iOS-only and
Chrome can't reproduce it,
node tools/qa/webkit-probe.mjs --url …. - A full sweep:
ios-toolbar-probe.mjsandcontext-loss-probe.mjsfor any live scene;fps-probe.mjs(no fixed phone caps; motion dt-scaled for 120 Hz); the mobile menu at 390×844 closed / mid-open / open / closing in light and dark scheme (dvh + safe area, portal under<body>, focus in and back); overflow at 320–430; split headlines; touch sliders; custom cursors off on touch; the first scroll after the loader;resize-check.mjs. - Fix one thing, prove it with the same probe (FAIL → PASS), then
node tools/qa/scroll-test.mjs --url …andnode tools/qa/lighthouse.mjs --url …— no regression in phone scroll, A11y/BP/SEO stay 100. .claude/scripts/verify.sh,yarn lint,npx tsc --noEmit -p .,yarn build.
Gyroscope hero motion is opt-in — ask before adding it. Never remove a 3D scene on mobile without the client's sign-off.
Report per item: cause, fix, the proof (tool + result), and what could only be
checked in emulation — then ask the client (or a teammate) to open a preview on their phone,
naming exactly what to try. New iOS lessons → obsidian/knowledge/pitfalls.md.
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 · 34 lines · 31 tokens per session scan A 060c4eab98e6
mobile is a command published in the GitHub repository textura-agency/next16-claude-starter (137 stars, last pushed 3d ago), licensed Unlicense. It adds 31 tokens to every session and 547 once invoked, about $0.0001 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 commands, from other repositories
xcode-test
Build and test iOS apps on simulator using XcodeBuildMCP.
axiom-ui
Drive simulator UI with an external xcui or AXe installation when available.
generate-widget
Génération Widget Flutter avec Tests.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
flutter-test
Run Flutter tests with coverage reporting (unit, widget, integration).
dev-flutter
Create Flutter widgets, screens and features with Clean Architecture.