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 agentmods add skills/junmystery/agent-guidance-python/compose-multiplatform-patternsnpx skills add JunMystery/Agent-Guidance-Python --skill compose-multiplatform-patternsgit clone --depth 1 https://github.com/JunMystery/Agent-Guidance-PythonWhat 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 | $0.00037 | $0.01876 |
| Opus 5 | $0.00018 | $0.00938 |
| Sonnet 5 | $0.00007 | $0.00375 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
compose-multiplatform-patterns 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 yesterday.
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.
This is a copy
98% identical to compose-multiplatform-patterns — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Multiplatform Patterns
Patterns for building shared UI across Android, iOS, Desktop, and Web using Compose Multiplatform and Jetpack Compose. Covers state management, navigation, theming, and performance.
When to Activate
- Building Compose UI (Jetpack Compose or Compose Multiplatform)
- Managing UI state with ViewModels and Compose state
- Implementing navigation in KMP or Android projects
- Designing reusable composables and design systems
- Optimizing recomposition and rendering performance
State Management
ViewModel + Single State Object
Use a single data class for screen state. Expose it as StateFlow and collect in Compose:
data class ItemListState(
val items: List<Item> = emptyList(),
val isLoading: Boolean = false,
val error: String? = null,
val searchQuery: String = ""
)
class ItemListViewModel(
private val getItems: GetItemsUseCase
) : ViewModel() {
private val _state = MutableStateFlow(ItemListState())
val state: StateFlow<ItemListState> = _state.asStateFlow()
fun onSearch(query: String) {
_state.update { it.copy(searchQuery = query) }
loadItems(query)
}
private fun loadItems(query: String) {
viewModelScope.launch {
_state.update { it.copy(isLoading = true) }
getItems(query).fold(
onSuccess = { items -> _state.update { it.copy(items = items, isLoading = false) } },
onFailure = { e -> _state.update { it.copy(error = e.message, isLoading = false) } }
)
}
}
}
Collecting State in Compose
@Composable
fun ItemListScreen(viewModel: ItemListViewModel = koinViewModel()) {
val state by viewModel.state.collectAsStateWithLifecycle()
ItemListContent(
state = state,
onSearch = viewModel::onSearch
)
}
@Composable
private fun ItemListContent(
state: ItemListState,
onSearch: (String) -> Unit
) {
// Stateless composable — easy to preview and test
}
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.
- yesterday First seen · 300 lines · 37 tokens per session scan A c81cbd0422f7
compose-multiplatform-patterns is a skill published in the GitHub repository JunMystery/Agent-Guidance-Python (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,876 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to compose-multiplatform-patterns, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
common-feedback-reporter
Pre-write audit for skill violations: checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart/TS code or editing SKILL.md files with active project skills. Load as composite; on auto-fixed violation, also load +common/common-learning-log.
common-session-retrospective
Analyze conversation corrections to detect skill gaps and prepare targeted skill-library maintenance tasks. Use after any session with user corrections, rework, or retrospective requests. After finding correction loops, also load +common/common-learning-log to persist mistake entries to AGENTSLEARNING.md.
common-workflow-writing
Rules for writing concise, token-efficient workflow and skill files. Prevents over-building that requires costly optimization passes. Use when creating or editing workflow files, SKILL.md files, or new skill definitions.
typescript-language
Apply modern TypeScript standards for type safety and maintainability. Use when working with types, interfaces, generics, enums, unions, or tsconfig settings.
JavaScript Language Patterns
Modern JavaScript (ES2022+) patterns for clean, maintainable code.
JavaScript Tooling
Development tools, linting, and testing for JavaScript projects.