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 GDvega/super-android-kotlin-firebase-skill --skill macrobenchmark-baseline-profilesgit clone --depth 1 https://github.com/GDvega/super-android-kotlin-firebase-skillWrote 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/gdvega/super-android-kotlin-firebase-skill/macrobenchmark-baseline-profiles)<a href="https://agentmods.dev/skills/gdvega/super-android-kotlin-firebase-skill/macrobenchmark-baseline-profiles"><img src="https://agentmods.dev/badge/skills/gdvega/super-android-kotlin-firebase-skill/macrobenchmark-baseline-profiles/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/gdvega/super-android-kotlin-firebase-skill/macrobenchmark-baseline-profiles"><img src="https://agentmods.dev/badge/skills/gdvega/super-android-kotlin-firebase-skill/macrobenchmark-baseline-profiles.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 | $0.00030 | $0.00688 |
| Opus 5 | $0.00015 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
macrobenchmark-baseline-profiles 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Measure real release-like performance and create Baseline Profiles for user-critical journeys.
When to use
- Improving startup time.
- Measuring scroll jank or Compose performance in release.
- Adding a macrobenchmark module.
- Generating or validating Baseline Profiles.
- Comparing before/after performance changes.
Inputs to inspect
settings.gradle.kts- Benchmark module setup
- App build types and profileable config
baseline-prof.txt- Startup path and critical screens
- CI benchmark workflow
Required workflow
- Identify a real user journey to measure.
- Create or update macrobenchmark module.
- Run release/profileable benchmarks.
- Generate Baseline Profile for startup and critical paths.
- Report results and tradeoffs clearly.
Rules
- Do not measure only debug builds.
- Do not optimize without baseline numbers.
- Do not benchmark unrealistic flows.
- Keep benchmark code separate from production code.
- Explain device and build conditions.
Related existing skills
Local skills to invoke
- compose-performance
- gradle-build
- play-store-release
- testing
External companion skills to use when installed
Do not assume these companion skills are installed. Prefer the local skills above first, then consult Companion Skills for install and verification commands.
- skydoves/android-testing-skills — use for deeper Android or Compose UI testing, semantics, assertions or test workflow guidance.
- skydoves/compose-performance-skills — use for deeper Compose performance, recomposition, stability or release-mode measurement guidance.
Files commonly touched
benchmark/build.gradle.ktssettings.gradle.ktsapp/build.gradle.ktsbaseline-prof.txt*Benchmark.ktBaselineProfileGenerator.kt
Commands to validate
./gradlew connectedBenchmarkAndroidTest
./gradlew generateBaselineProfile
./gradlew assembleRelease
Common mistakes to avoid
- Running benchmarks on debug.
- Changing multiple variables before comparison.
- Ignoring warmup and device state.
- Failing to commit generated profile updates.
What ships with it
8 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.
- references/baseline-profile-generation.md 177 B
- references/macrobenchmark-setup.md 152 B
- references/release-performance-checklist.md 144 B
- references/startup-and-scroll-benchmarks.md 154 B
- templates/baseline-profile-generator-template.kt 154 B
- templates/macrobenchmark-module-template.md 126 B
- templates/scroll-benchmark-template.kt 96 B
- templates/startup-benchmark-template.kt 193 B
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 First seen · 111 lines · 30 tokens per session scan A 334555a5604e
macrobenchmark-baseline-profiles is a skill published in the GitHub repository GDvega/super-android-kotlin-firebase-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 688 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 2026-08-31.
Other skills, from other repositories
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
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.
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.
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…
argent-ios-device-interact
Drive a physical iPhone through argent. Use when a physical iPhone is involved (a list-devices iOS entry with kind "device") and ONLY then; never for a simulator. For cable, trust, or signing problems read argent-ios-device-setup.