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/droid-ash/finalrun-agent/finalrun-generate-testnpx skills add droid-ash/finalrun-agent --skill finalrun-generate-testgit clone --depth 1 https://github.com/droid-ash/finalrun-agentWrote 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/droid-ash/finalrun-agent/finalrun-generate-test)<a href="https://agentmods.dev/skills/droid-ash/finalrun-agent/finalrun-generate-test"><img src="https://agentmods.dev/badge/skills/droid-ash/finalrun-agent/finalrun-generate-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 | $0.00051 | $0.05087 |
| Opus 5 | $0.00026 | $0.02544 |
| Sonnet 5 | $0.00010 | $0.01017 |
| Haiku 4.5 | $0.00005 | $0.00509 |
Grade A, and why
finalrun-generate-test 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 4d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FinalRun Test and Suite Generator
You are an expert QA Automation Engineer. Generate FinalRun YAML artifacts with extreme precision. This skill guides you through planning new testing campaigns, finding existing test assets grouped by feature, presenting a proposed plan to the user, and saving approved tests in strict YAML format.
Core Principles
Test user-facing functionality only:
- ✅ User interactions, gestures, and navigation (tap, swipe, scroll, back navigation)
- ✅ End-to-end screen and feature functionality
- ✅ Form input, validation, search, filters, and interactive UI elements
- ✅ Mobile-specific behaviors (keyboard input, screen transitions, orientation changes)
- ❌ APIs, backend endpoints, or server-side logic
- ❌ Validating third-party authentication provider internals (OAuth, Google, Facebook, GitHub)
Variables & secrets (no hardcoding):
- Prerequisite: The
finalrunCLI must be installed and available onPATH(the same binary the user will use to run tests). Declarations in.finalrun/env/<env>.yamlare validated and resolved byfinalrun checkand at run time; without the CLI you cannot confirm bindings are correct. - NEVER guess or fabricate credentials, emails, passwords, or account-specific values.
- NEVER hardcode plaintext secrets into a test file.
- Use
${variables.KEY}and${secrets.KEY}in tests. Both must be declared undervariablesandsecretsin.finalrun/env/<env>.yaml(one file per environment name). - Secrets in YAML use the FinalRun form
secrets.logical_key: "${SHELL_ENV_VAR}"(placeholder only). Real values are supplied by the shell or CI environment atfinalrun checkand run time. - Do not assert or require that
.finalrun/.env.*files exist; do not treat secret storage files as part of validation. Do not read or write.env.*files.
App configuration (required):
- FinalRun runs require
.finalrun/config.yamlto define the default app identity for the repo. - Use
app.packageNamefor Android andapp.bundleIdfor iOS. - Infer app identifiers from the codebase before asking the user to type them manually.
- Treat repo inspection as autofill, not silent truth: propose what you found and ask only when the repo is ambiguous.
- Ask whether the app identifier changes by environment.
- If the identifier is the same everywhere, keep app identity only in
.finalrun/config.yaml. - If the identifier differs by environment, keep the default app identity in
.finalrun/config.yamland replace it with a full env-specificappblock under.finalrun/env/<env>.yaml.
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.
- 4d ago First seen · 312 lines · 51 tokens per session scan A 07b31af0e095
finalrun-generate-test is a skill published in the GitHub repository droid-ash/finalrun-agent (305 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 5,087 once invoked, about $0.0003 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
playwright-for-android
End-to-end Android debug loop on an emulator. Builds the APK with a Gradle task, boots a named AVD, installs and launches the target package, then drives a single feature via adb-injected UI actions while capturing a unified logcat-and-actions timeline plus a developer-facing test report. Use when the user wants to…
solopi-ai
通过 SoloPi 的机器可读 CLI 编译和执行 AI 验证计划,管理签名端侧 ExecuTorch 决策模型、持久设备池、无人值守任务、安卓设备、应用、动作、配置、用例步骤与交互录制、回放及性能历史、动态 Agent、批量与重复执行、性能监控、压力测试和证据。适用于需求/AC 到 Result Judge 三态结论、cloud/on-device 决策切换、模型发布门禁,以及 generation 租约的多设备 CI 执行。.
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。.
test-flutter
Flutter App のテスト実行・静的解析・フォーマット・テスト記述ガイド.
web-preview
Flutter Web版をビルド → サーバー起動 → Playwright でアクセス確認 → URLをユーザーに案内する。.
roborazzi
Use when working with Roborazzi screenshot tests on Android/JVM — setting up the Roborazzi Gradle plugin, running record/compare/verify tasks, writing tests with captureRoboImage or RoborazziRule, Compose Preview screenshot testing (ComposablePreviewScanner), Compose Multiplatform (iOS/desktop) screenshots, AI-powered…