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 skills add prasad-vennam/Awesome-Android-AI-Agent-Skills --skill android-macrobenchmarkgit clone --depth 1 https://github.com/prasad-vennam/Awesome-Android-AI-Agent-SkillsWrote 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/prasad-vennam/awesome-android-ai-agent-skills/android-macrobenchmark)<a href="https://agentmods.dev/skills/prasad-vennam/awesome-android-ai-agent-skills/android-macrobenchmark"><img src="https://agentmods.dev/badge/skills/prasad-vennam/awesome-android-ai-agent-skills/android-macrobenchmark/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/prasad-vennam/awesome-android-ai-agent-skills/android-macrobenchmark"><img src="https://agentmods.dev/badge/skills/prasad-vennam/awesome-android-ai-agent-skills/android-macrobenchmark.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 | $0.00021 | $0.00502 |
| Opus 5 | $0.00010 | $0.00251 |
| Sonnet 5 | $0.00004 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
android-macrobenchmark 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
Android Macrobenchmark & Baseline Profiles 🏎️
App Startup Time and UI performance are crucial. Macrobenchmark allows us to write standard JUnit 4 tests to measure end-to-end user journeys (like app startup or scrolling a list) and automatically generate Baseline Profiles that Android's ART uses to pre-compile critical code.
⚡ When to Use
- When the prompt mentions "speeding up app startup time"
- When writing a Macrobenchmark module
- When generating or applying Baseline Profiles (
baseline-prof.txt)
🏗️ Core Rules / Pillars
1. Separate Macrobenchmark Module
- Pattern: Macrobenchmarks MUST be in a separate
com.android.testmodule. They launch your application by itsapplicationIdexternally. - Anti-Pattern: Do NOT attempt to run Macrobenchmark tests inside the standard
app/src/androidTestdirectory.
2. Writing a Scrolling Benchmark
- Implementation:
@RunWith(AndroidJUnit4::class) class ScrollBenchmark { @get:Rule val benchmarkRule = MacrobenchmarkRule() @Test fun scrollTimeline() = benchmarkRule.measureRepeated( packageName = "com.example.app", metrics = listOf(FrameTimingMetric()), iterations = 5, startupMode = StartupMode.COLD ) { pressHome() startActivityAndWait() // Using UIAutomator to find the scrollable list and scroll val list = device.findObject(By.res("com.example.app", "timeline_list")) list.setGestureMargin(device.displayWidth / 5) list.fling(Direction.DOWN) } }
🚧 Critical Anti-Hallucination Guards
- Trap: Baseline Profiles generation requires a rooted device OR a device running Android 13 (API 33)+.
🔗 Related Resources
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 · 65 lines · 21 tokens per session scan A 6cfe8092f1a0
android-macrobenchmark is a skill published in the GitHub repository prasad-vennam/Awesome-Android-AI-Agent-Skills (9 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 502 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.
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.
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.
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.
eas-simulator
EAS service (paid). 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…
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.