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/noqa-ai/noqa/noqa-testingnpx skills add noqa-ai/noqa --skill noqa-testinggit clone --depth 1 https://github.com/noqa-ai/noqaWrote 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/noqa-ai/noqa/noqa-testing)<a href="https://agentmods.dev/skills/noqa-ai/noqa/noqa-testing"><img src="https://agentmods.dev/badge/skills/noqa-ai/noqa/noqa-testing.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 | $0.00047 | $0.00935 |
| Opus 5 | $0.00023 | $0.00467 |
| Sonnet 5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
noqa-testing 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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
noqa Device Testing
noqa controls iOS/Android devices and simulators through the noqa CLI. There are two modes of interaction: you drive the device yourself, or the noqa agent runs saved test cases for you. Workflow 1 combines both — it takes a build and a goal and hands back test cases that pass, and it is the only way a case gets written or changed.
Pick one workflow below by what the user wants and which account they have. Follow that workflow's file — it links to the exact commands in references/.
Before you start
Every workflow needs the user to be signed in (noqa status shows an account). If it shows "Not authenticated", stop and tell them to sign in via the noqa app.
-
Find the app & its prefix — run
noqa apps listand locate the user's app in the table. Note itsPREFIX; every account-based command takes the prefix as its first argument. See Apps, Cases & Flows. -
Determine the account type — run
noqa statusand read off which workflows are available:noqa statusshowsAccount type Available workflows signed in, no subscription, credits = $0.00 Free 2 — and 1 up to saving the cases active subscription or credits > $0.00 Paid 1, 2, 3 If a workflow needs a paid account and the user is on a free account, stop and tell them to add credits or subscribe at https://noqa.ai.
Workflows
1. Generate test cases — from build to passing tests
The whole job in one workflow: the user says what to cover — the whole app, a few features, a single scenario — or what to change in an existing case, and you learn the app from past runs, from the code and from the running build, walk the scenarios on a device, save the cases, and run them until they pass. Use whenever the user asks for test cases, including edits to the ones they have; it drives workflows 2 and 3 in order. Free up to saving the cases; the final run needs credits.
- Workflow: Generate test cases
- Concepts: Test Cases, Flows & App Context · Writing Good Test Cases
What ships with it
16 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.
- concepts/test-cases.md 3.0 KB
- concepts/writing-test-cases.md 6.6 KB
- references/actions.md 5.3 KB
- references/apps-cases-and-flows.md 4.5 KB
- references/builds-android.md 1.8 KB
- references/builds-ios-native.md 2.3 KB
- references/builds-react-native.md 1.4 KB
- references/builds.md 1.8 KB
- references/devices.md 861 B
- references/install-android.md 1.1 KB
- references/install-ios.md 1.7 KB
- references/run.md 2.8 KB
- references/screen.md 1.3 KB
- workflows/device-control.md 2.7 KB
- workflows/generate-test-cases.md 7.7 KB
- workflows/run-tests.md 3.2 KB
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.
- 3d ago First seen · 56 lines · 47 tokens per session scan A 80da402c25cb
noqa-testing is a skill published in the GitHub repository noqa-ai/noqa (185 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 935 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
aco
Drive a live Appium session from the shell with the aco CLI. Use when the user wants to interact with a running mobile app on an iOS simulator, Android emulator, or connected real device — tap, swipe, type, screenshot, read the screen/page source, find UI elements, switch to a WebView context, or call iOS/Android…
bump-android-version
Use when bumping Maestro's Android compileSdk/targetSdk to a new API level and validating end-to-end against the test-e2e GHA workflow until the test-android job is green.
argent-test-ui-flow
Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running end-to-end UI test scenarios, manual QA steps, visible UI changes, or visual behavior.
mobile-automation
Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.
mobile-automation
MCP (dart-mcp + Marionette) を使ったFlutterアプリのE2E自動化・UI検証ガイド。シミュレーターでのUI動作確認、モックプレビュー検証、Bridge経由のE2Eテスト、スクリーンショット撮影など、アプリの動作検証が必要なときに使う。「動作確認して」「UIを検証して」「E2Eテスト」「シミュレーターで確認」「モックで確認」と言われたときや、UI変更後の検証フェーズで使用すること。.
argent-create-flow
Create, record, edit, replay, or repair reusable Argent flow YAML files. Use when the user asks to record or replay a repeatable device path, set up profiling or an A/B comparison, or invoke the authoring engine behind argent-qa-flows. Also use before repeating three or more interactions. For one-off UI checks…