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 compose-performancegit 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/compose-performance)<a href="https://agentmods.dev/skills/gdvega/super-android-kotlin-firebase-skill/compose-performance"><img src="https://agentmods.dev/badge/skills/gdvega/super-android-kotlin-firebase-skill/compose-performance/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/compose-performance"><img src="https://agentmods.dev/badge/skills/gdvega/super-android-kotlin-firebase-skill/compose-performance.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 | $0.00033 | $0.00642 |
| Opus 5.5 | $0.00013 | $0.00257 |
| Sonnet 5.5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
compose-performance 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 1mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Diagnose and fix measurable Compose performance issues without guessing.
When to use
- A screen scrolls poorly or drops frames.
- Recomposition counts spike unexpectedly.
- Lazy lists, side effects or state reads are suspected performance causes.
- Baseline profiles, tracing or performance CI are needed.
Inputs to inspect
- Affected composables and state models.
- Profiler, compiler report or benchmark evidence if available.
- Lazy list item models and keys.
- Build variants and benchmark tasks.
Required workflow
- Reproduce or describe the performance symptom.
- Inspect state reads, stability, keys and side effects.
- Apply the smallest targeted fix.
- Measure again with available tools.
- Document residual risks and validation gaps.
Rules
- Measure before large rewrites.
- Do not add remember everywhere blindly.
- Do not use @Stable/@Immutable unless the contract is true.
- Use stable lazy keys and content types when needed.
- Prefer release-mode measurement for meaningful performance claims.
Related existing skills
Local skills to invoke
- jetpack-compose
- macrobenchmark-baseline-profiles
- screen-ux-audit
- 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.
- aldefy/compose-skill — use for deeper Jetpack Compose, Material 3, design-to-code, theming or Compose architecture guidance.
- skydoves/compose-performance-skills — use for deeper Compose performance, recomposition, stability or release-mode measurement guidance.
Files commonly touched
Compose screensUI modelsbenchmark modulebaseline-prof.txtbuild.gradle.kts
Commands to validate
./gradlew assembleRelease
./gradlew connectedBenchmarkAndroidTest
./gradlew test
adb shell am profile start
Common mistakes to avoid
- Optimizing from intuition only.
- Ignoring image size/loading.
- Using unstable mutable models as parameters.
- Missing lazy item keys.
What ships with it
3 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.
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.
- 1mo ago First seen · 102 lines · 33 tokens per session scan A 560d67980f66
compose-performance is a skill published in the GitHub repository GDvega/super-android-kotlin-firebase-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 642 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 2026-08-31.
Other skills, from other repositories
android-studio
Configure Android Studio Gradle projects, emulators, build variants, and signing; diagnose build and runtime failures with AGP and Logcat.
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.
analyzing-android-malware-with-apktool
Perform static analysis of Android APK malware using apktool for resource decompilation, jadx for Java source recovery, and androguard for manifest inspection, dangerous permission-combination detection, and identification of obfuscated code, dynamic code loading, and reflection-based API calls. Use to statically…
argent-tv-interact
Control and inspect TV apps via argent, Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
simvyn
Operate iOS Simulators, Android Emulators, and connected mobile devices with Simvyn. Use for device discovery, app installation and launch, screenshots, logs, deep links, location simulation, app data inspection, device settings, and reusable device workflows through the Simvyn CLI or dashboard.
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…