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 Aarvion-AI/stackwise-skills --skill jetpack-compose-expertgit clone --depth 1 https://github.com/Aarvion-AI/stackwise-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/aarvion-ai/stackwise-skills/jetpack-compose-expert)<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/jetpack-compose-expert"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/jetpack-compose-expert.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 5.1 | $0.00145 | $0.02500 |
| Opus 5 | $0.00072 | $0.01250 |
| Sonnet 5 | $0.00029 | $0.00500 |
| Haiku 4.5 | $0.00015 | $0.00250 |
Grade A, and why
jetpack-compose-expert 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 8d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jetpack Compose Expert
Turns Claude into a senior Android engineer shipping idiomatic Kotlin 2.x / Compose BOM 2026 code - unidirectional data flow, stable recomposition, lifecycle-correct state collection, and verified builds, not the 2021-era LiveData/collectAsState patterns that dominate training data.
When to Use This Skill
- Building screens or components with Compose + Material 3 in an existing Android app
- Fixing recomposition storms, unstable parameters, or laggy lazy lists
- Wiring ViewModel +
StateFlowstate exposed to composables the lifecycle-correct way - Adding Navigation Compose routes (type-safe,
@Serializableroute classes) - Setting up or extending Hilt DI and Room + Flow data layers
- Handling side effects:
LaunchedEffect,DisposableEffect,rememberUpdatedState,snapshotFlow - Writing Compose UI tests (
composeTestRule, semantics) and Robolectric-hosted tests - Edge-to-edge/insets work and performance passes (baseline profiles,
derivedStateOf)
Core Workflow
- Analyze - Read
gradle/libs.versions.tomland modulebuild.gradle.ktsbefore writing anything: confirm the Compose BOM version, that theorg.jetbrains.kotlin.plugin.composeGradle plugin is applied (required with Kotlin 2.x -composeOptions.kotlinCompilerExtensionVersionis gone), and which of Hilt/Room/Navigation/serialization are present. Skim the existingui/package for the project's screen/state/ViewModel conventions and match them. - Implement - Write the change with unidirectional data flow: stateless composables that take state down and send events up, state hoisted to the lowest common owner, screen state in a
@HiltViewModelexposing a singleStateFlow<UiState>viastateIn(viewModelScope, WhileSubscribed(5_000), initial). Collect in UI only withcollectAsStateWithLifecycle(). Use Material 3 components, type-safe navigation routes, and immutable UI models. - Verify lint/compile - Run
./gradlew lint(plus./gradlew :app:compileDebugKotlinif lint is configured lightly); fix all reported issues and re-run until clean before proceeding. Treat Compose lint checks (ComposableNaming,RememberReturnType,FrequentlyChangingValue, coroutine-in-composition errors) as real defects, not noise. - Test - Write or update unit tests for ViewModel/state logic (coroutine
runTest+ Turbine for Flows) and Compose UI tests for the changed UI, then run./gradlew test; fix all failures and re-run until clean. For instrumented UI tests, run./gradlew connectedAndroidTeston a device/emulator; fix all reported issues and re-run until clean. - Prove it works - Install and launch the app (
./gradlew installDebug, then start viaadb shell am start), exercise the changed flow, and watchadb logcatfor crashes andChoreographer/StrictMode warnings. For performance work, confirm with Layout Inspector recomposition counts or a Macrobenchmark that recompositions/frame times actually dropped.
What ships with it
5 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.
- 8d ago First seen · 121 lines · 145 tokens per session scan A 9341d6782154
jetpack-compose-expert is a skill published in the GitHub repository Aarvion-AI/stackwise-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 145 tokens to every session and 2,500 once invoked, about $0.0007 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
swift-patterns
Swift and SwiftUI development patterns for building native iOS/iPadOS applications. Use when implementing views, view models, data persistence, networking, concurrency, and navigation. Covers Swift 6.2, SwiftUI, SwiftData, iOS 26 features including Liquid Glass and Foundation Models.
build-android-binary
Compile a PAM control's Android Kotlin module into the runtime-loadable DEX for a .ppmplugin. Creates a staged Gradle build with the pinned wrapper and react-android compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs d8 --min-api 24. Writes…
kotlin-patterns
Kotlin: coroutines, Flow, sealed/data classes, null safety, Ktor, Compose, KMP. Triggers: Kotlin, coroutine, Flow, suspend, Ktor, Jetpack Compose, KMP, kotlinx.
swift-patterns
Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.
generators
Code generator skills that produce production-ready Swift code for common app components. Use when user wants to add logging, analytics, onboarding, review prompts, networking, authentication, paywalls, settings, persistence, error monitoring, CI/CD pipelines, localization, push notifications, deep linking, testing…
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.