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 compose-multiplatformgit 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/compose-multiplatform)<a href="https://agentmods.dev/skills/jxoesneon/ciel/compose-multiplatform"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/compose-multiplatform/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/compose-multiplatform"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/compose-multiplatform.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 | $0.00025 | $0.00397 |
| Opus 5.5 | $0.00010 | $0.00159 |
| Sonnet 5.5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
compose-multiplatform 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 1mo 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: Compose Multiplatform (Shared UI)
This skill formalizes cross-platform UI development using Compose. It focuses on skippable recomposition and platform-agnostic state management.
State Management
- Single Source of Truth: Use a single data class for screen state (e.g.,
ItemListState). - ViewModel: Expose state as
StateFlow. Collect in Compose usingcollectAsStateWithLifecycle(). - Event Sinks: Use a sealed interface for screen events (e.g.,
ItemListEvent) to minimize callback lambda count.
Design Patterns
- Slot-Based APIs: Design components with
@Composablelambda parameters for maximum flexibility. - Modifier Discipline: Apply modifiers in order: Layout -> Shape -> Background -> Interaction.
- Expect/Actual: Use for platform-specific UI features (e.g., Status Bar control, native share sheets).
Performance & Theming
- Stability: Mark UI models as
@Stableor@Immutableto enable skippable recomposition. - Keys: Use
key()in lists to ensure stable item reuse. - Material 3: Enforce dynamic theming using
MaterialThemecolor schemes.
Anti-Patterns
- Deep Nav Injection: Passing
NavControllerdeep into the tree. Pass lambda callbacks instead. - MutableState in VM: Using
mutableStateOfin ViewModels (useStateFlowfor lifecycle safety). - Heavy Recomposition: Performing allocations or filters directly in the
@Composablefunction.
What ships with it
1 file 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.
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.
- 1mo ago Changed · -13 lines f74a2bb8364c
- 1mo ago First seen · 50 lines · 25 tokens per session scan A 3e2ce182740c
compose-multiplatform is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 25 tokens to every session and 397 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
app-store-screenshot-optimizer
Screenshots are your app's billboard. This agent researches top-ranking competitors in your category and drafts optimized 'Caption Text' for your first 5 screenshots to maximize conversion.
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
camera-skill
Control Android camera - get camera info, take photos, and access camera capabilities.
screen-control-skill
Control Android screen - brightness, wake screen, auto-brightness toggle, and screen timeout settings.
android-personality
Android device assistant personality. Use when the user wants to interact with their Android phone or tablet in a natural, conversational way.
flutter-state-management
Use when a Flutter screen needs app state or data - separate presentation from state, keep business logic out of widgets, and follow the app's existing state solution (Riverpod 3 Notifier/AsyncNotifier, or the official ChangeNotifier+ListenableBuilder MVVM pattern).