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/using-stability-analyzer-ide-pluginnpx skills add skydoves/compose-performance-skills --skill using-stability-analyzer-ide-plugingit 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/using-stability-analyzer-ide-plugin)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/using-stability-analyzer-ide-plugin"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/using-stability-analyzer-ide-plugin.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 | $0.00187 | $0.04008 |
| Opus 5 | $0.00093 | $0.02004 |
| Sonnet 5 | $0.00037 | $0.00802 |
| Haiku 4.5 | $0.00019 | $0.00401 |
Grade A, and why
using-stability-analyzer-ide-plugin 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the Stability Analyzer IDE Plugin — live in-editor stability feedback
The Compose Compiler reports tell the developer about stability after a build completes. The skydoves/compose-stability-analyzer IntelliJ plugin tells them while they edit. Gutter icons mark every @Composable with a color, hover docs render the per-parameter table with reasons, inline hints render colored badges next to each parameter type, and the UnstableComposable weak-warning inspection surfaces actionable problems with quick fixes.
The plugin uses the Kotlin K2 Analysis API to evaluate the same stability rules that drive ../understanding-stability-inference/SKILL.md, so editor feedback agrees with what ../diagnosing-compose-stability/SKILL.md would later show in the compiler reports. This shortens the loop from "ship → build → read reports" to "type → see the gutter".
When to use this skill
- The developer wants real-time stability feedback while editing a Composable file.
- A reviewer is reading a PR locally and wants the inline signal next to each composable.
- A new joiner wants to see at a glance which composables in the file are non-skippable.
- The user asks why the editor flagged a function with a weak warning called
UnstableComposable. - The user mentions gutter icons, inline hints, the stability inspection, the IDEA plugin, the K2 Analysis API for Compose, or the
Compose Stability Analyzertool window.
When NOT to use this skill
- CI gating that fails the build on stability regressions. Use
../enforcing-stability-in-ci/SKILL.md. - Build-time Compose Compiler reports analysis. Use
../diagnosing-compose-stability/SKILL.md. - Active runtime tracing or visual cascade investigation through the plugin's tool window. Use
../visualizing-recomposition-cascades/SKILL.md. - Conceptual questions about how the compiler classifies a type. Use
../understanding-stability-inference/SKILL.md.
Prerequisites
- Android Studio 2024.2+ or IntelliJ IDEA 2024.2+ (build range 242 through 261, covering 2024.2 through the 2026.1 EAP).
- Kotlin 2.3.0 in the IDE plugin runtime, required by the K2 Analysis API the plugin relies on.
- The Compose Compiler Gradle plugin already wired in the project (
org.jetbrains.kotlin.plugin.compose). The analyzer evaluates stability against the same compiler model. - The plugin is currently installed from disk during development; the JetBrains Marketplace listing is pending.
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 · 266 lines · 187 tokens per session scan A a45b8a7d8cf2
using-stability-analyzer-ide-plugin is a skill published in the GitHub repository skydoves/compose-performance-skills (496 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 187 tokens to every session and 4,008 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…
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…