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 performancegit 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/performance)<a href="https://agentmods.dev/skills/piyushverma0/android-agent-skills/performance"><img src="https://agentmods.dev/badge/skills/piyushverma0/android-agent-skills/performance.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 | $0.00110 | $0.01367 |
| Opus 5 | $0.00055 | $0.00683 |
| Sonnet 5 | $0.00022 | $0.00273 |
| Haiku 4.5 | $0.00011 | $0.00137 |
Grade A, and why
performance 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 8d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Performance
Rule 1: Compose stability — stop unnecessary recomposition
// ✅ @Stable for classes Compose can't infer stability
@Stable
class ItemState(
val id: String,
val title: String,
var isExpanded: Boolean = false // mutable but tracked
)
// ✅ @Immutable for guaranteed-immutable data (faster than @Stable)
@Immutable
data class Item(
val id: String,
val title: String,
val tags: List<String> // List is not stable by default — @Immutable fixes it
)
// ✅ Use ImmutableList from kotlinx-collections-immutable for stable lists
implementation("org.jetbrains.kotlinx:kotlinx-collections-immutable:0.3.7")
@Composable
fun ItemList(items: ImmutableList<Item>) { // ImmutableList is stable, List is not
LazyColumn {
items(items, key = { it.id }) { item ->
ItemCard(item = item) // won't recompose unless item changes
}
}
}
// ❌ List<Item> parameter causes ItemList to recompose on every parent recomposition
@Composable
fun ItemList(items: List<Item>) { ... }
Rule 2: derivedStateOf — compute only when dependencies change
// ✅ derivedStateOf — prevents recomposition when result doesn't change
@Composable
fun ItemList(items: List<Item>) {
val listState = rememberLazyListState()
// Only recomputes when scroll position crosses threshold
val showScrollToTop by remember {
derivedStateOf { listState.firstVisibleItemIndex > 3 }
}
// Only recomputes when filter changes, not on every recomposition
val activeItems by remember(items) {
derivedStateOf { items.filter { it.isActive } }
}
Box {
LazyColumn(state = listState) {
items(activeItems, key = { it.id }) { ItemCard(it) }
}
AnimatedVisibility(visible = showScrollToTop, modifier = Modifier.align(Alignment.BottomEnd)) {
ScrollToTopButton(onClick = { /* scroll to top */ })
}
}
}
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.
- 8d ago First seen · 188 lines · 110 tokens per session scan A 863f40e74c86
performance is a skill published in the GitHub repository piyushverma0/android-agent-skills (15 stars, last pushed 4mo ago), licensed MIT. It adds 110 tokens to every session and 1,367 once invoked, about $0.0006 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
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
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.
kotlin-coroutines-expert
Expert patterns for Kotlin Coroutines and Flow, covering structured concurrency, error handling, and testing in this Android app.
compose-inspector
Use when inspecting or building Jetpack Compose UI for recomposition safety, stability (@Immutable/@Stable), RTL/LTR, remember/derivedStateOf, and Lazy list keys.
gradle-build-optimizer
Use when Gradle builds hang, lock on Windows, or a targeted :app assemble/test is enough instead of a full rebuild.
android-harness
Use when working on this Android app architecture, Compose or XML UI, Room, performance, or daily checkout facts.