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 avoiding-subcomposition-pitfallsgit 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/avoiding-subcomposition-pitfalls)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/avoiding-subcomposition-pitfalls"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/avoiding-subcomposition-pitfalls/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/skydoves/compose-performance-skills/avoiding-subcomposition-pitfalls"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/avoiding-subcomposition-pitfalls.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00175 | $0.04256 |
| Opus 5.5 | $0.00070 | $0.01702 |
| Sonnet 5.5 | $0.00035 | $0.00851 |
| Haiku 4.5 | $0.00017 | $0.00426 |
Grade A, and why
avoiding-subcomposition-pitfalls 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Avoiding Subcomposition Pitfalls — Keep Composition Out of the Measure Pass
SubcomposeLayout runs its content's composition during the measure pass, not during the parent's composition pass. That trades extra layout cost for the ability to use measured constraints inside the children's composition. BoxWithConstraints, material3.Scaffold, and the lazy layouts are all built on top of it, so the cost is invisible until it nests or lands inside a hot path. This skill teaches Claude how to detect the misuse, how to replace SubcomposeLayout with a cheaper primitive when its power is not needed, and how to keep it efficient when it is.
When to use this skill
- The developer wraps content in
BoxWithConstraintspurely to readmaxWidth/maxHeightand pick between a few composables, and the screen feels heavy at first frame or on configuration change (rotation, IME show). - A
BoxWithConstraintsorScaffoldis nested inside anotherBoxWithConstraintsorScaffold, multiplying subcomposition cost. - A
BoxWithConstraintssits inside aLazyColumn/LazyRowitem and the developer reports scroll jank that did not exist before the wrap was added. - The developer manually authors a
SubcomposeLayoutblock but only uses constraints to compute final positions, never to drive child composition. - The Layout Inspector or a Perfetto trace shows
Compose:applyChangesor measure-phase composition counts that scale with parent constraint changes (rotation, drag-to-resize, animated container size). - A custom
SubcomposeLayout'smeasurePolicyblock allocates a fresh composable lambda insidesubcompose(slotId) { … }on every measurement. AndroidX maintains an internal lint check namedComposableLambdaInMeasurePolicy(incompose/lint/internal-lint-checks/) that flags exactly this pattern on its own codebase; published APIs likeBoxWithConstraints,material.Scaffold, andmaterial3.TabRowsuppress that check because the trade-off is fundamental to their public contract. App-side code that reproduces the pattern pays the same cost without the suppression rationale.
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 First seen · 285 lines · 175 tokens per session scan A a71122f23983
avoiding-subcomposition-pitfalls is a skill published in the GitHub repository skydoves/compose-performance-skills (517 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 175 tokens to every session and 4,256 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
compose-performance
Use when investigating Jetpack Compose recomposition cost, compiler stability reports, skippability, unstable parameters, frame-rate State reads, cross-phase snapshot back-writing, or @ReadOnlyComposable contracts.
media-playback-footguns
Media player traps on Media3/ExoPlayer and desktop engines: crossfade, audio focus, fades, loudness, DSP, queues and shuffle, position restore, service lifecycle, group listening. Use when playback state, queue or audio levels go wrong.
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…
webview-footguns
WebView traps across device classes: startup that freezes low-RAM phones, a killed renderer that takes the app with it, devices with no usable provider, AndroidView lifecycle and cookies. Use when a web screen freezes, vanishes or crashes only on some devices.
compose-stability-diagnostics
Use when writing or reviewing Jetpack Compose parameter stability, compiler reports, skippability, unstable UI state classes, collection parameters, or Kotlin 2.0+ strong skipping behavior.
compose-recomposition-performance
Use when investigating Jetpack Compose recomposition performance, skippable/restartable composables, composables.txt or compiler reports, Layout Inspector recomposition counts, back-writing snapshot state across phases, or frame-rate State reads in composition vs layout/draw, and it is not yet clear whether the cause…