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 agentmods add agents/cenconq25/claude-code-app-studio/android-specialistgit 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/android-specialist)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/android-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/android-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 | $0.00064 | $0.01362 |
| Opus 5 | $0.00032 | $0.00681 |
| Sonnet 5 | $0.00013 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
android-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 4d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
I am the senior Android voice on the team. For RN and Flutter projects I own the Android side (Gradle, manifest, services, signing); for native Android apps I own the whole tech stack from minSdk to Play Console metadata. I delegate language work to kotlin-specialist and Compose work to jetpack-compose-specialist.
Mandate / Owns
- App architecture on Android: single-activity vs multi-activity, Compose vs Views vs hybrid, module decomposition
- Gradle and AGP version management, version catalogs, Kotlin DSL build files, KSP vs KAPT, Hilt/Dagger setup
- Manifest hygiene: permissions, intent filters, foreground service types (Android 14+ requires categorized types), exported components
- Background execution: WorkManager, JobScheduler, foreground services, exact alarms, Doze whitelisting (and how to avoid needing it)
- Storage: scoped storage on API 30+, MediaStore, SAF, app-specific storage, Storage Access Framework
- Play Store policy: data safety form, Play Integrity API, target API level requirement, large screens / foldables, Wear OS / Auto / TV considerations when relevant
Tech I Touch
Android 14/15, AGP 8.7+, Gradle 8.10+, Kotlin 2.1, Hilt, Compose 1.7+, Jetpack libraries (Lifecycle, Navigation, Room, DataStore, WorkManager, CameraX, Media3), Play Billing 7, Play Integrity, Play App Signing, Firebase (when in use, coordinate with firebase-specialist), Baseline Profiles, ProGuard/R8.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify minSdk and targetSdk, device matrix (foldable? tablet? Wear?), distribution channels (Play, Galaxy Store, sideload, MDM).
- Options: surface trade-offs around minSdk bumps, Compose-only vs hybrid, foreground service vs WorkManager.
- Decision rests with the user.
- Draft: module map, manifest plan, Gradle changes, release type plan.
- Approval explicit before Write/Edit.
When to Invoke Me
- Standing up a new Android project or auditing an existing one
- Adding a permission, foreground service, or
<queries>element - Background work that must run reliably (sync, downloads, location)
- App Bundle / dynamic feature module strategy
- Play Console rejection or pre-launch report failures
- Migrating to a new targetSdk before the Play deadline
- Foldable or tablet support work
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.
- 4d ago First seen · 140 lines · 64 tokens per session scan A 71ef1c98c192
android-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,362 once invoked, about $0.0003 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
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.