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 skydoves/compose-performance-skills --skill configuring-lazy-prefetchgit clone --depth 1 https://github.com/skydoves/compose-performance-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/skydoves/compose-performance-skills/configuring-lazy-prefetch)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/configuring-lazy-prefetch"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/configuring-lazy-prefetch.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00177 | $0.03559 |
| Opus 5 | $0.00088 | $0.01780 |
| Sonnet 5 | $0.00035 | $0.00712 |
| Haiku 4.5 | $0.00018 | $0.00356 |
Grade A, and why
configuring-lazy-prefetch 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuring Lazy Prefetch — Cache Window and Pausable Composition
Lazy layouts pre-compose items just outside the viewport so they're ready when the user scrolls. Compose Foundation 1.9 added LazyLayoutCacheWindow for configurable ahead/behind extents. Compose Foundation 1.10 made prefetch composition pausable by default — work spreads across multiple frames instead of one. Most apps still rely on legacy single-frame prefetch and unknowingly pay for it during heavy scrolling. This skill teaches Claude when (and only when) to widen the window or implement nested prefetch, and how to validate the change with Macrobenchmark.
When to use this skill
- Macrobenchmark
FrameTimingMetricshows dropped frames at high scroll velocity even though item composables are skippable. - Items are content-heavy: large images, decoded videos, nested grids, or expensive measurement work.
- The developer wants composition retained for items the user scrolled past briefly (e.g. flick-back gesture).
- An outer lazy layout contains items with their own inner lazy layouts (e.g.
LazyColumnrows that each host aHorizontalPageror innerLazyRow). - The developer mentions
LazyLayoutCacheWindow,NestedPrefetchScope, "prefetch window", "ahead extent", or "pausable composition for prefetch".
When NOT to use this skill
- Items are cheap and short; default behavior is sufficient — do not pre-emptively configure a window.
- Item composables are non-skippable / unstable; widening the window only spreads the same waste over more frames. First fix
../optimizing-lazy-layouts/SKILL.mdand the underlying stability via../../stability/diagnosing-compose-stability/SKILL.md. - The bottleneck is per-item layout or draw rather than composition. Use Android Studio Profiler / Layout Inspector to confirm; if measure or draw dominates, prefetch tuning will not help — adjust item content instead.
- Wrong-phase state reads inside items (animation reads
state.valuein Composition) — use../../recomposition/deferring-state-reads/SKILL.md.
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 · 220 lines · 177 tokens per session scan A ab55da2363f4
configuring-lazy-prefetch is a skill published in the GitHub repository skydoves/compose-performance-skills (499 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 177 tokens to every session and 3,559 once invoked, about $0.0009 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
claude-android-ninja
Build and migrate Android apps with Kotlin, Jetpack Compose, MVVM, Hilt, Room 3 (KSP, SQLiteDriver, Flow/suspend DAOs), Navigation3, and multi-module Gradle. Use for new projects or modules, Compose screens and ViewModels, Room 3 and RemoteMediator, API 37 / targetSdk migration, Play Integrity client wiring…
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
kotlin-android
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).
compose-side-effects
Use when writing or reviewing Jetpack Compose code with LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, snapshotFlow, snackbar, navigation, focus requests, analytics, or event Flow collection.
kotlin-multiplatform-expect-actual
Use when designing Kotlin Multiplatform expect/actual or interface boundaries for platform services, native SDKs, source sets, Compose Multiplatform UI, permissions, files, settings, sensors, or platform interop.