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 compose-uigit 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/compose-ui)<a href="https://agentmods.dev/skills/piyushverma0/android-agent-skills/compose-ui"><img src="https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/compose-ui/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/compose-ui"><img src="https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/compose-ui.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 | $0.00131 | $0.03039 |
| Opus 5 | $0.00066 | $0.01520 |
| Sonnet 5 | $0.00026 | $0.00608 |
| Haiku 4.5 | $0.00013 | $0.00304 |
Grade A, and why
compose-ui 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 — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose UI
24 rules that fix what AI agents consistently get wrong in Jetpack Compose.
CRITICAL rules — get these wrong and the app is broken
1. Edge-to-edge + Scaffold innerPadding
// ✅ Always consume Scaffold's innerPadding
Scaffold(
topBar = { TopAppBar(title = { Text("Screen") }) },
bottomBar = { BottomNavBar() }
) { innerPadding ->
LazyColumn(
modifier = Modifier.fillMaxSize(),
contentPadding = innerPadding // ← pass to content, never ignore
) { ... }
}
// ❌ Never ignore innerPadding — content hides under bars
Scaffold { _ ->
LazyColumn { ... } // content hidden under top/bottom bars
}
2. ModalBottomSheet navigation bar padding
// ✅ Always add navigationBarsPadding inside BottomSheet content
ModalBottomSheet(onDismissRequest = { ... }) {
Column(
modifier = Modifier
.fillMaxWidth()
.navigationBarsPadding() // ← required, content shifts above nav bar
.padding(16.dp)
) { ... }
}
// ❌ Missing navigationBarsPadding — content hidden behind gesture nav bar
ModalBottomSheet(onDismissRequest = { ... }) {
Column(modifier = Modifier.padding(16.dp)) { ... }
}
3. Single UiState sealed class per screen
// ✅ One sealed class represents all screen states
sealed interface HomeUiState {
data object Loading : HomeUiState
data class Success(val items: List<Item>) : HomeUiState
data class Error(val message: String) : HomeUiState
data object Empty : HomeUiState
}
// ✅ Always handle all states in the Composable
@Composable
fun HomeScreen(uiState: HomeUiState) {
when (uiState) {
is HomeUiState.Loading -> LoadingIndicator()
is HomeUiState.Success -> ItemList(uiState.items)
is HomeUiState.Error -> ErrorMessage(uiState.message)
is HomeUiState.Empty -> EmptyState()
}
}
// ❌ Never use multiple booleans for state — causes impossible states
data class HomeState(
val isLoading: Boolean = false,
val isError: Boolean = false,
val isEmpty: Boolean = false,
val items: List<Item> = emptyList()
)
What ships with it
30 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 994 B
- references/.gitkeep 0 B
- references/animations.md 11 KB
- references/testing.md 9.7 KB
- rules/.gitkeep 0 B
- rules/a11y-semantics-content-description.md 5.0 KB
- rules/adaptive-layouts-pager-tabs.md 5.7 KB
- rules/animation-animated-visibility.md 2.9 KB
- rules/bottomsheet-navigation-bar-padding.md 2.4 KB
- rules/effects-disposable-effect.md 2.0 KB
- rules/effects-launched-effect-key.md 1.7 KB
- rules/image-loading-coil-permissions.md 5.4 KB
- rules/layout-edge-to-edge.md 4.3 KB
- rules/layout-ime-keyboard.md 4.1 KB
- rules/lists-content-padding.md 1.7 KB
- rules/lists-stable-keys.md 2.4 KB
- rules/m3-theming-expressive.md 6.6 KB
- rules/modifier-order-matters.md 2.8 KB
- rules/navigation-type-safe-routes.md 3.4 KB
- rules/perf-no-logic-in-composition.md 2.7 KB
- rules/perf-one-shot-events.md 3.1 KB
- rules/preview-multi-preview.md 2.9 KB
- rules/scaffold-consume-inner-padding.md 2.5 KB
- rules/state-derived-state-of.md 1.7 KB
- rules/state-hoist-to-lowest-ancestor.md 1.4 KB
- rules/state-remember-correct-variant.md 1.8 KB
- rules/state-single-ui-state-class.md 2.1 KB
- rules/textfield-forms-security.md 6.2 KB
- rules/ux-loading-error-empty-states.md 6.4 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 · 449 lines · 131 tokens per session scan A 1f690fc09e61
compose-ui is a skill published in the GitHub repository piyushverma0/android-agent-skills (15 stars, last pushed 4mo ago), licensed MIT. It adds 131 tokens to every session and 3,039 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
compose-inspector
Use when inspecting or building Jetpack Compose UI for recomposition safety, stability (@Immutable/@Stable), RTL/LTR, remember/derivedStateOf, and Lazy list keys.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
compose-component-design
Use when designing or reviewing reusable Jetpack Compose component APIs with modifier parameters, root layout placement, caller-provided variable content, primitive content parameters, optional content, or boolean shape flags.
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.
maui-accessibility
Improve MAUI accessibility. USE FOR: semantic labels, hints, headings, screen-reader focus/announcements, AutomationProperties, touch targets, decorative content, TalkBack/VoiceOver/Narrator checks. DO NOT USE FOR: general layout, automation-only tests, performance.
flutter-design-system
Enforce Design Language System adherence in Flutter. Use when implementing design tokens, preventing hardcoded colors/spacing, or building a DLS.