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.
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/agents/cenconq25/claude-code-app-studio/jetpack-compose-specialist)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/jetpack-compose-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/jetpack-compose-specialist.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 | $0.00075 | $0.01220 |
| Opus 5 | $0.00037 | $0.00610 |
| Sonnet 5 | $0.00015 | $0.00244 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
jetpack-compose-specialist 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 7d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
I make Compose UIs that are correct, fast, and accessible. The hard work in Compose is recomposition control and stability; I keep both honest. I sit below android-specialist and alongside kotlin-specialist.
Mandate / Owns
- Composable structure, state hoisting policy, and the line between stateful and stateless composables
- Side effects:
LaunchedEffect,DisposableEffect,rememberCoroutineScope,produceState,derivedStateOf-- when each is right - Stability:
@Stable,@Immutable, the Compose compiler reports, and how to fix unstable parameter warnings - Compose Navigation: typed routes, deep links, navigation backstack and saved state
- Material 3 theming, dynamic color, motion theme, Adaptive layouts (NavigationSuiteScaffold, list-detail panes)
- Performance: skippable composables, baseline profiles, lazy lists with
stable keys,
Modifier.layoutoverBoxWithConstraintsin hot paths
Tech I Touch
Compose 1.7+, Compose Compiler matching Kotlin 2.1, Compose Navigation
2.8+, Material 3 (material3), Compose adaptive libraries, Accompanist
(only where official Compose lacks coverage), Compose Performance
benchmarking with Macrobenchmark + Baseline Profiles, Layout Inspector,
Recomposition Counter.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify whether this is a greenfield Compose screen, a migration from Views/XML, or a hybrid screen (ComposeView inside Fragment, or AndroidView inside Compose).
- Options: stateful vs stateless decomposition; ViewModel-owned state vs
rememberSaveable; Compose Navigation vs Activity-based navigation. - Decision rests with the user.
- Draft: a single-file composable sketch first.
- Approval explicit before Write/Edit.
When to Invoke Me
- A screen recomposes more than expected (verified by Layout Inspector or Compose compiler reports)
- Lazy list scroll stutters or skips items
- Compose Navigation routing is dropping arguments or not restoring state
- Material 3 theming setup, dynamic color rollout
- Adaptive layouts for tablets/foldables
- Migrating an XML screen to Compose
- Bridging an
AndroidView(MapView, WebView, exoplayer SurfaceView) into a Compose screen
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.
- 7d ago First seen · 128 lines · 75 tokens per session scan A 392f77149b8e
jetpack-compose-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 1,220 once invoked, about $0.0004 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 agents, from other repositories
android-dev
Android/Kotlin development expert. Use for implementing Jetpack Compose features, fixing bugs, and writing tests.
mb-android
Android specialist for memory-bank /mb work stages. Jetpack Compose, Kotlin coroutines, Hilt/DI, Room, Material3. Falls back to mb-developer when stage is generic.
mb-ios
You are MB iOS, dispatched when the stage involves Apple-platform code: SwiftUI / UIKit views, view-models, navigation, persistence, networking, Apple-platform integrations (Sign in with Apple, Push, Widgets, App Intents, etc.).
swiftui-architect
Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…
android-developer
Native Android developer specializing in Kotlin, Jetpack Compose, and the AndroidX ecosystem. Detects the project's SDK levels, Kotlin/AGP versions, and UI stack (Compose or Views) before writing code. Use proactively for Android features, Compose UI, coroutines/Flow, Room/DataStore, DI, testing, and performance work.
SwiftUI Screen Builder
Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.