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 jxoesneon/Ciel --skill android-kmp-architecturegit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/android-kmp-architecture)<a href="https://agentmods.dev/skills/jxoesneon/ciel/android-kmp-architecture"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/android-kmp-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/jxoesneon/ciel/android-kmp-architecture"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/android-kmp-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 | $0.00030 | $0.00552 |
| Opus 5 | $0.00015 | $0.00276 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
android-kmp-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 10d 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.
What it actually says
CIEL ADAPTATION: Android & KMP Architecture (Structural Layer)
This skill formalizes the "Structural Layer" for Android and KMP projects. It enforces module isolation and dependency inversion to ensure cross-platform portability and testability.
Recommended Module Layout
project/
├── app/ # Platform entry point (Android), DI wiring.
├── domain/ # Pure Kotlin. UseCases, Domain Models, Repository Interfaces.
├── data/ # Repository Impls, DataSources (Room/SQLDelight), Network (Ktor).
├── presentation/ # ViewModels, UI State, Flow collection.
└── core/ # Shared utilities, error types, base classes.
Dependency Rules (Immutable)
- Domain Isolation:
domainMUST NEVER depend ondata,presentation, or any platform framework. - One-Way Flow:
app->presentation->domain<-data. - Mappers: Keep mappers (e.g.,
Entity -> Domain) as extension functions in thedatalayer.
Core Patterns
- UseCase: Single business operation. Use
operator fun invokefor clean call sites. - Result/Try: Use a sealed interface (e.g.,
Result<T>) for all repository/use-case returns to avoid unchecked exceptions. - DI: Standardize on Koin (KMP-friendly) or Hilt (Android-only).
Anti-Patterns
- Context Leaking: Passing Android
Contextor framework classes into thedomainlayer. - Fat ViewModels: Putting business logic in ViewModels instead of UseCases.
- Circular Deps: Allowing
domainto know aboutdataimplementations.
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.
- 10d ago First seen · 55 lines · 30 tokens per session scan A 2cb499da3705
android-kmp-architecture is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 30 tokens to every session and 552 once invoked, about $0.0002 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 skills, from other repositories
SwiftUI Conventions
@State/@Binding/@ObservedObject usage, view composition, preview-driven development.
Jetpack Compose Conventions
State hoisting, remember/derivedStateOf patterns, modifier ordering, and preview annotations.
Play Store Readiness
App signing, keystore management, API level targeting, privacy policy, and review guideline checks.
android-compose-starter
Step-by-step guide to scaffold a new Android + Jetpack Compose project from scratch. Covers project creation in Android Studio, Gradle version catalog setup, core library selection, feature-first MVVM architecture, and Compose UI best practices. Use when starting a greenfield Android project or setting up a new app…
dart-flutter-patterns
Production-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation, and clean architecture.
android-clean-architecture
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.