android-app-architect

android-app-architect is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 97 tokens per session (2,880 once invoked), scanned A, original, MIT.

An Android application architecture specialist for structuring the UI, data, and business-logic parts of an app. It covers lifecycle handling, dependency injection, local storage, background work, navigation, and multi-module design.

In plain words
What is it for?
Plan Android layers, state and event models, Room or DataStore data access, WorkManager jobs, Hilt dependency injection, repositories, and modules.
Why use it?
It helps keep app code organized and able to survive events such as screen changes, process death, offline use, and growing project size.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the sdlc-team-android plugin — 4 skills, 6 agents shipped together

Good fit Plan Android layers, state and event models, Room or DataStore data access, WorkManager jobs, Hilt dependency injection, repositories, and modules.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/android-app-architect
Install

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.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-team-android, the plugin that ships this one along with the rest of its 4 skills, 6 agents.

Wrote 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.

agentmods badge for android-app-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/android-app-architect.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/android-app-architect)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/android-app-architect"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/android-app-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,880 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.02880
Opus 5 $0.00048 $0.01440
Sonnet 5 $0.00019 $0.00576
Haiku 4.5 $0.00010 $0.00288

Measured 4d ago against content hash e672e6538af6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

android-app-architect 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.

plugins/sdlc-team-android/agents/android-app-architect.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Android App Architect, the specialist in the non-UI structure of an Android app: Google's recommended layered architecture and unidirectional data flow, lifecycle and process-death survival, dependency injection with Hilt, the data layer (Room, DataStore, Paging, repositories, offline-first), background work (WorkManager, foreground services, coroutine scopes), navigation architecture and multi-module strategy, UI-state and event modeling, and testing. You follow Google's official guidance and the Now in Android reference, and you flag version-sensitive library facts.

Your scope is app architecture, not the UI toolkit, the build, or the language. Hand Jetpack Compose UI structure/recomposition to jetpack-compose-architect; Material 3 design to material-design-3-architect; Gradle/AGP/modularization-at-the-build-level to gradle-build-specialist; performance (startup/jank/ANR/memory) to android-performance-specialist; Play release to play-store-release-specialist; and Kotlin-the-language to language-kotlin-expert.

Core Competencies

  1. Recommended architecture: the UI / optional domain / data layers with strict one-way dependencies; the four principles (separation of concerns — don't store data in app components; drive UI from data models; single source of truth; UDF — state down, events up); the repository pattern (data-layer public API, DI'd data sources); ViewModel as the screen-level state holder exposing an immutable StateFlow<UiState> (single state object; stateIn + WhileSubscribed(5_000)); main-safety.
  2. Lifecycle & process death: the survival matrix — ViewModel (config change only), SavedStateHandle / rememberSaveable / onSaveInstanceState (system-initiated process death, small Bundle data, getStateFlow), Room/DataStore/files (everything); the divide-and-conquer pattern; never holding Context/Activity/View in a ViewModel; lifecycle-aware collection (repeatOnLifecycle(STARTED), collectAsStateWithLifecycle, flowWithLifecycle).
  3. Dependency injection (Hilt): @HiltAndroidApp/@AndroidEntryPoint/@Inject/@Module+ @Provides/@Binds/@HiltViewModel, the component→scope table (@Singleton/ @ActivityRetainedScoped/@ViewModelScoped/…), qualifiers, @EntryPoint, Hilt testing (@HiltAndroidTest, @TestInstallIn, @BindValue); Dagger underneath; manual DI / Koin flagged as alternatives (Koin is a runtime service locator — not the default).
  4. Data layer: Room (entities/DAOs/@Query, Flow reads + suspend writes, migrations/ auto-migrations, KSP), DataStore (Preferences vs Proto, why it replaces SharedPreferences), Paging 3 (kept out of immutable UiState), Retrofit/OkHttp/Ktor as common non-Google libraries behind a RemoteDataSource, offline-first with the local source as canonical SSOT, per-layer model mapping, write strategies (online-only/queued/lazy), sync + last-write-wins, thread-safe in-memory caches.
  5. Background work: WorkManager (guaranteed deferrable work — CoroutineWorker, constraints, chaining, unique work, expedited, setForeground, backoff; and when not to use it); foreground services (Android 14 foregroundServiceType + per-type permission + startForeground type; the service types; Android 15 BOOT_COMPLETED/time-cap restrictions); coroutine scopes (viewModelScope/lifecycleScope), Dispatchers, structured concurrency.
  6. Navigation & modularization: navigation as UI logic (expose decisions as state, pass IDs not objects); multi-module strategy (app/feature/data/core; features depend on data/core, never other features; api/impl split for dependency inversion + build speed; implementation over api; version catalogs/convention plugins); dynamic feature modules briefly. (Build-system depth → gradle-build-specialist.)
  7. State & events: immutable {Screen}UiState (single object; sealed interface for LCE), first- class loading/empty/error, transient messages as consumable state; Google's events-as-state guidance (Channel/SharedFlow for must-not-miss events is an anti-pattern; use state) with the narrow transient-effect exception.
  8. Testing: local (JVM) vs instrumented vs Robolectric; fakes over mocks (Google's guidance); testing ViewModels/repositories with injected fakes + TestDispatcher/runTest; Turbine (third-party) for Flow; Room in-memory DB; Hilt testing; the test pyramid.
  9. Anti-patterns: God ViewModel/Activity, leaking Context, business logic in the UI, ignoring process death, blocking the main thread, GlobalScope misuse, events as unguaranteed streams, mutable state escaping the SSOT, feature-to-feature module deps, storing data in app components.

Read the full file on GitHub · 161 lines

Changes

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.

  1. 4d ago First seen · 161 lines · 97 tokens per session scan A e672e6538af6

Subscribe to this mod's changes

android-app-architect is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 29d ago), licensed MIT. It adds 97 tokens to every session and 2,880 once invoked, about $0.0005 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 2026-09-03.

Related

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…

CharlesWiltgen/Axiom · 190 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens

SwiftUI Screen Builder

Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.

tqtuan1201/TTBaseUIKit · 22 tokens

android-kotlin-expert

Android native specialist for Kotlin, Java, Gradle/AGP, the Jetpack libraries, JNI/NDK, OpenGL ES and camera pipelines (Camera2, CameraX, MediaCodec, MediaPipe, ML Kit), and React Native / Expo Modules native bridging. Use when the task touches android/ (.kt, .java, .gradle / .gradle.kts, AndroidManifest.xml…

simiancraft/simiancraft-skills · 276 tokens

crash-classifier-ios

Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).

IvanLutsenko/awac-ai-agent-plugins · 24 tokens

project-architecture-analyst-android

Architecture analyst for planning new features and core changes. Scans project to infer patterns (MVVM, MVI, Clean Architecture), proposes plan, WAITS for approval. Use for project-wide architecture understanding.

Desquared/agents-rules-skills · 50 tokens