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 ashtanko/compose-android-template --skill compose-stability-diagnosticsgit clone --depth 1 https://github.com/ashtanko/compose-android-templateWrote 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/ashtanko/compose-android-template/compose-stability-diagnostics)<a href="https://agentmods.dev/skills/ashtanko/compose-android-template/compose-stability-diagnostics"><img src="https://agentmods.dev/badge/skills/ashtanko/compose-android-template/compose-stability-diagnostics/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/ashtanko/compose-android-template/compose-stability-diagnostics"><img src="https://agentmods.dev/badge/skills/ashtanko/compose-android-template/compose-stability-diagnostics.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 | $0.00043 | $0.01662 |
| Opus 5.5 | $0.00017 | $0.00665 |
| Sonnet 5.5 | $0.00009 | $0.00332 |
| Haiku 4.5 | $0.00004 | $0.00166 |
Grade A, and why
compose-stability-diagnostics 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose stability diagnostics
Core principle
Compose parameter fixes start from evidence. First identify the compiler mode and the parameter comparison behavior, then change the model or call site that is actually defeating skipping.
With Kotlin 2.0.20+ strong skipping is enabled by default. Unstable parameters no longer automatically make restartable composables non-skippable, but unstable parameters compare by instance identity (===) while stable parameters compare by equality (equals). Churny unstable instances can still defeat skipping.
Diagnostic procedure
- Confirm the symptom: recomposition counts, compiler report output, or a suspected churny parameter.
- Identify compiler mode: Kotlin/Compose compiler version and whether strong skipping is enabled.
- Generate or read the Compose compiler reports for the shipped variant.
- For each suspicious parameter, decide whether the problem is stability semantics, instance churn, or a caller-created lambda/derived value.
- Apply the lightest fix that makes the type/call site truthful.
- Re-measure the same interaction or re-read the same report before claiming the issue is fixed.
1. Interpret strong skipping first
On Kotlin 2.0.20+, strong skipping is enabled by default. In that mode:
- Restartable composables are skippable even when parameters are unstable, unless explicitly opted out.
- Stable parameters compare with
equals. - Unstable parameters compare with instance equality (
===). - Lambdas inside composables are automatically remembered based on captures.
Ask: "will these parameters compare the way I expect, and are callers creating new unstable instances every frame?"
For older compiler setups or strong skipping disabled, the legacy rule still matters: a restartable composable with unstable parameters may be restartable but not skippable.
2. Generate compiler reports
With Kotlin 2.0+ the Compose Compiler is configured through the Kotlin Gradle plugin:
plugins {
alias(libs.plugins.android.application) // or android.library / jvm
alias(libs.plugins.kotlin.android) // or kotlin.multiplatform / kotlin.jvm
alias(libs.plugins.compose.compiler)
}
if (providers.gradleProperty("composeReports").orNull == "true") {
composeCompiler {
reportsDestination = layout.buildDirectory.dir("compose_compiler")
metricsDestination = layout.buildDirectory.dir("compose_compiler")
}
}
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 · 172 lines · 43 tokens per session scan A ba9e5581d70e
compose-stability-diagnostics is a skill published in the GitHub repository ashtanko/compose-android-template (13 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 1,662 once invoked, about $0.0002 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 2026-08-31.
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.
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.
auditing-compose-performance
Use this skill to run an end-to-end Jetpack Compose performance audit when the symptom is broad ("the app feels sluggish", "scroll is rough everywhere", "we're starting a perf sprint", "what should we fix first?"). Orchestrates the four-phase Measure → Diagnose → Fix → Verify loop by sequencing the 25 focused skills…
tracing-recompositions-at-runtime
Use this skill to instrument a Jetpack Compose composable with @TraceRecomposition from skydoves/compose-stability-analyzer so per-recomposition diffs (which state or parameter changed, what value transition) print to logcat under the Recomposition tag. Works in release-with-debug-symbols builds where Android Studio…
avoiding-subcomposition-pitfalls
Use this skill when a Compose tree uses SubcomposeLayout, BoxWithConstraints, or Scaffold and the developer reports extra measure passes, slow first frame, or layout passes running content composition repeatedly. Covers why SubcomposeLayout composes its slots during the measure phase, why BoxWithConstraints forces a…