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 agentmods add skills/skydoves/compose-performance-skills/stabilizing-compose-typesnpx skills add skydoves/compose-performance-skills --skill stabilizing-compose-typesgit 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/stabilizing-compose-types)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/stabilizing-compose-types"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/stabilizing-compose-types.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 | $0.00153 | $0.04142 |
| Opus 5 | $0.00077 | $0.02071 |
| Sonnet 5 | $0.00031 | $0.00828 |
| Haiku 4.5 | $0.00015 | $0.00414 |
Grade A, and why
stabilizing-compose-types 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 4d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stabilizing Compose Types — Three Tiers, In Order
Once a diagnosis (see ../diagnosing-compose-stability/SKILL.md) has named the unstable types, this skill walks Claude through fixing them. The strategy is a strict three-tier waterfall: (1) make the type truly stable by structural rewrite (val + immutable fields) — no annotation needed; (2) annotate with @Immutable or @Stable when the source is owned and the contract is honored; (3) use stabilityConfigurationFile for third-party or Java types. DO NOT invert this order — annotations are a contract, not a magic spell.
When to use this skill
- The compiler report (composables.txt / classes.txt) shows one or more
unstableparameters. - The developer asks how to stabilize a domain class, a
List<Foo>parameter,java.time.LocalDateTime, or a third-party type. - The developer mentions
@Immutable,@Stable,compose-stable-marker,compose-runtime-annotation,kotlinx.collections.immutable,stabilityConfigurationFiles, orstability_config.conf. - A
@TraceRecompositionlog shows recomposition happening because an argument is allocated fresh every recomposition.
When NOT to use this skill
- The unstable types are not yet identified — run
../diagnosing-compose-stability/SKILL.mdfirst. - The symptom is a wrong-phase state read (
Modifier.alpha(state.value)); use../../recomposition/deferring-state-reads/SKILL.md. - The symptom is a
derivedStateOfproblem; use../../recomposition/choosing-derivedstateof/SKILL.md. - A
Flow<T>parameter is the cause; the fix is to collect upstream — see../../side-effects/collecting-flows-safely/SKILL.mdrather than annotatingFlowas stable.
Prerequisites
../diagnosing-compose-stability/SKILL.mdhas been run; the developer has a concrete list of unstable types.- Kotlin 2.0.0+ with
org.jetbrains.kotlin.plugin.composeapplied. Strong Skipping is on by default. - For pure-Kotlin / data modules without
compose-runtime: eitherandroidx.compose.runtime:runtime-annotation(official) orcom.github.skydoves:compose-stable-marker(legacy) on the classpath. Both expose@Stable/@Immutable/@StableMarkerwithout dragging in the full runtime. - For tier-3 fixes: Compose Compiler 1.5.5+ for
stabilityConfigurationFilesDSL support (plural; the older singularstabilityConfigurationFileproperty is deprecated, see footnote below).
What ships with it
1 file 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.
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.
- 4d ago First seen · 339 lines · 153 tokens per session scan A 795555df1b39
stabilizing-compose-types is a skill published in the GitHub repository skydoves/compose-performance-skills (496 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 153 tokens to every session and 4,142 once invoked, about $0.0008 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…
rebrand
Rebrand a fresh clone of android-clean-template into a new app. Asks for the app name, application id, sample-feature and networking decisions, then executes docs/CLONECHECKLIST.md end to end. Use on a fresh un-rebranded clone (application id still com.mkchtv.cleantemplate) or when the user asks to set up, rename, or…
sceneview
Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…
sceneview-ios
Build 3D and AR apps on Apple platforms (iOS, macOS, visionOS) with SceneViewSwift — the SwiftUI wrapper around RealityKit. Use whenever the user asks for "3D in SwiftUI", "AR with ARKit in SwiftUI", a model viewer for iOS, or any Apple-platform 3D/AR app where the dependency is the SceneViewSwift Swift Package from…
kotlin-control-flow
Use when writing or reviewing Kotlin branching and control flow: when expressions, guard conditions, sealed type exhaustiveness, smart casts, nullable branching, early returns, or replacing complex if/else chains.
roborazzi
Use when working with Roborazzi screenshot tests on Android/JVM — setting up the Roborazzi Gradle plugin, running record/compare/verify tasks, writing tests with captureRoboImage or RoborazziRule, Compose Preview screenshot testing (ComposablePreviewScanner), Compose Multiplatform (iOS/desktop) screenshots, AI-powered…