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/RanaNadeemAslam/android-ai-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/rules/rananadeemaslam/android-ai-skills/architecture)<a href="https://agentmods.dev/rules/rananadeemaslam/android-ai-skills/architecture"><img src="https://agentmods.dev/badge/rules/rananadeemaslam/android-ai-skills/architecture.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 | $0.01470 | $0.01470 |
| Opus 5 | $0.00735 | $0.00735 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
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 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Android developer. Follow Google's official app architecture guidance strictly. Every architectural decision must prioritize testability, separation of concerns, and unidirectional data flow.
Layered Architecture
Follow the recommended layered architecture: UI Layer -> Domain Layer (optional) -> Data Layer.
DO:
- Separate the app into UI, Domain (optional), and Data layers
- Each layer should only depend on the layer directly below it
- UI layer never accesses data sources directly — always through a repository
- Domain layer is optional — only add it when multiple ViewModels share business logic
DON'T:
- Let UI layer call data sources, APIs, or DAOs directly
- Let Data layer reference UI or ViewModel classes
- Create circular dependencies between layers
- Add a Domain layer "just in case" — add it when you need it
UI Layer (Compose + ViewModel)
↕
Domain Layer (UseCases) — optional
↕
Data Layer (Repositories + DataSources)
Source: https://developer.android.com/topic/architecture#recommended-app-arch
UI Layer & State Management
Source: https://developer.android.com/topic/architecture/ui-layer
DO:
- Model UI state as a single immutable data class per screen:
data class ProfileUiState(
val isLoading: Boolean = false,
val profile: Profile? = null,
val errorMessage: String? = null,
)
- Or use a sealed interface when states are mutually exclusive:
sealed interface ProfileUiState {
data object Loading : ProfileUiState
data class Success(val profile: Profile) : ProfileUiState
data class Error(val message: String) : ProfileUiState
}
- Expose UI state from ViewModel as
StateFlow:
private val _uiState = MutableStateFlow(ProfileUiState())
val uiState: StateFlow<ProfileUiState> = _uiState.asStateFlow()
- Collect state in Compose with
collectAsStateWithLifecycle():
val uiState by viewModel.uiState.collectAsStateWithLifecycle()
- Model user actions as events/intents passed to ViewModel via function calls
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 · 180 lines · 1,470 tokens per session scan A bb0b0825d09c
architecture is a cursor rule published in the GitHub repository RanaNadeemAslam/android-ai-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 1,470 tokens to every session, about $0.0073 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 cursor rules, from other repositories
kotlin
Android finance precision, RTL/i18n, and Kotlin AI skill rules.
coding-guidelines
React Native Expo SDK 54 project with TypeScript, Expo Router v6, Redux Toolkit, and modern development practices.
swiftui-accessibility
SwiftUI accessibility rules for VoiceOver — labels, hints, traits, values, and attribute preservation.
android-gradle-build-logic
Shape Android build logic with Gradle, version catalogs, plugins, convention patterns, and toolchain compatibility.
android-kotlin-core
Use Kotlin idioms safely in Android apps, including nullability, data classes, sealed types, extension functions, and collection pipelines.
android-networking-retrofit-okhttp
Build Android networking stacks with Retrofit, OkHttp, interceptors, API contracts, and resilient error handling.