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 piyushverma0/android-agent-skills --skill android-architecturegit clone --depth 1 https://github.com/piyushverma0/android-agent-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/piyushverma0/android-agent-skills/android-architecture)<a href="https://agentmods.dev/skills/piyushverma0/android-agent-skills/android-architecture"><img src="https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/android-architecture/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/piyushverma0/android-agent-skills/android-architecture"><img src="https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/android-architecture.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 | $0.00136 | $0.02166 |
| Opus 5 | $0.00068 | $0.01083 |
| Sonnet 5 | $0.00027 | $0.00433 |
| Haiku 4.5 | $0.00014 | $0.00217 |
Grade A, and why
android-architecture 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 9d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Architecture
MVVM + Clean Architecture with Unidirectional Data Flow. These patterns prevent the most common structural mistakes AI agents make when building Android apps.
The three layers — strict separation
Presentation (UI) → only depends on Domain
ViewModel → calls UseCases, exposes UiState + Events
Composables → observes ViewModel, sends user actions
Domain (Business Logic) → pure Kotlin, zero Android dependencies
UseCases → orchestrate one business operation
Repository interfaces → contracts, implemented in Data layer
Domain models → pure data classes
Data → implements Domain interfaces
Repository impls → coordinate local + remote sources
Remote DataSource → Retrofit API calls
Local DataSource → Room DAO calls
DTOs / Mappers → never expose DTOs to Domain
Rule: Domain layer must never import android.*. If it does, the architecture is broken.
Package structure
com.company.app/
├── di/ ← Hilt modules only
│ ├── AppModule.kt
│ └── NetworkModule.kt
├── ui/
│ ├── theme/
│ ├── navigation/
│ │ └── AppNavGraph.kt
│ └── feature/
│ └── home/
│ ├── HomeScreen.kt ← Composable
│ ├── HomeViewModel.kt
│ └── HomeUiState.kt
├── domain/
│ ├── model/
│ │ └── Item.kt ← pure data class
│ ├── repository/
│ │ └── ItemRepository.kt ← interface
│ └── usecase/
│ └── GetItemsUseCase.kt
└── data/
├── repository/
│ └── ItemRepositoryImpl.kt
├── remote/
│ ├── ItemApiService.kt
│ └── dto/
│ └── ItemDto.kt
└── local/
├── ItemDao.kt
└── entity/
└── ItemEntity.kt
ViewModel — complete pattern
@HiltViewModel
class HomeViewModel @Inject constructor(
private val getItems: GetItemsUseCase,
private val toggleFavorite: ToggleFavoriteUseCase
) : ViewModel() {
private val _uiState = MutableStateFlow<HomeUiState>(HomeUiState.Loading)
val uiState: StateFlow<HomeUiState> = _uiState.asStateFlow()
private val _events = MutableSharedFlow<HomeEvent>()
val events: SharedFlow<HomeEvent> = _events.asSharedFlow()
init {
loadItems()
}
fun loadItems() {
viewModelScope.launch {
_uiState.value = HomeUiState.Loading
getItems()
.onSuccess { items ->
_uiState.value = if (items.isEmpty()) HomeUiState.Empty
else HomeUiState.Success(items)
}
.onFailure { error ->
_uiState.value = HomeUiState.Error(error.message ?: "Unknown error")
}
}
}
fun onItemClick(itemId: String) {
viewModelScope.launch {
_events.emit(HomeEvent.NavigateToDetail(itemId))
}
}
fun onFavoriteClick(itemId: String) {
viewModelScope.launch {
toggleFavorite(itemId)
.onFailure { _events.emit(HomeEvent.ShowError("Failed to update favorite")) }
}
}
}
What ships with it
14 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.
- .gitkeep 0 B
- metadata.json 832 B
- references/architecture-decisions.md 2.9 KB
- rules/data-models-mapping.md 5.7 KB
- rules/layer-structure.md 4.4 KB
- rules/multi-module-considerations.md 4.0 KB
- rules/navigation-architecture.md 6.7 KB
- rules/package-naming.md 5.4 KB
- rules/repository-pattern.md 6.0 KB
- rules/testing-architecture.md 5.7 KB
- rules/uievent-pattern.md 4.6 KB
- rules/uistate-pattern.md 4.1 KB
- rules/usecase-layer.md 4.7 KB
- rules/viewmodel-structure.md 6.1 KB
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.
- 9d ago First seen · 292 lines · 136 tokens per session scan A 7732637bbe48
android-architecture is a skill published in the GitHub repository piyushverma0/android-agent-skills (15 stars, last pushed 4mo ago), licensed MIT. It adds 136 tokens to every session and 2,166 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 2026-08-30.
Other skills, from other repositories
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
Debroid CLI Debugger
Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.
kotlin-coroutines-expert
Expert patterns for Kotlin Coroutines and Flow, covering structured concurrency, error handling, and testing in this Android app.
android-harness
Use when working on this Android app architecture, Compose or XML UI, Room, performance, or daily checkout facts.
compose-inspector
Use when inspecting or building Jetpack Compose UI for recomposition safety, stability (@Immutable/@Stable), RTL/LTR, remember/derivedStateOf, and Lazy list keys.
gradle-build-optimizer
Use when Gradle builds hang, lock on Windows, or a targeted :app assemble/test is enough instead of a full rebuild.