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 understanding-stability-inferencegit 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/understanding-stability-inference)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/understanding-stability-inference"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/understanding-stability-inference.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 | $0.00184 | $0.04016 |
| Opus 5 | $0.00092 | $0.02008 |
| Sonnet 5 | $0.00037 | $0.00803 |
| Haiku 4.5 | $0.00018 | $0.00402 |
Grade A, and why
understanding-stability-inference 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understanding Stability Inference — read the compiler's mind
Stability is decided by a 12-phase algorithm baked into the Compose compiler. This skill teaches Claude how the algorithm walks a type so it can explain why a report says what it says, and predict classifications before the report is even generated. Pair this with ../diagnosing-compose-stability/SKILL.md (which generates the report) and ../stabilizing-compose-types/SKILL.md (which fixes obvious unstable types). Reach for this skill when the simpler skills produce a verdict that surprises the developer.
When to use this skill
- The developer asks "why is
Fooclassified asruntime stableand notstable?" - A report shows
runtimeorunknownfor a class that "looks fine". - Generics involved:
Box<T>,Wrapper<A, B>,Pair<String, Int>,ImmutableList<User>. - The class lives in another module and ships as a
.class/.kotlin_metadataartifact. - The developer asks about the
$stable: Intfield,@StabilityInferred, or cross-module classification. - A self-referential type (
class Node(val children: List<Node>)) is unstable for non-obvious reasons. - A Java type, an interface, or an abstract base appears in a parameter list and surprises the developer.
When NOT to use this skill
- The fix is mechanical (
var→val,List→ImmutableList,Flowparameter removal). Use../stabilizing-compose-types/SKILL.md. - No report exists yet. Run
../diagnosing-compose-stability/SKILL.mdfirst. - The developer wants CI enforcement of stability. Use
../enforcing-stability-in-ci/SKILL.md.
Prerequisites
- Compose Compiler reports already generated, or at least one
<module>-classes.txtand<module>-composables.txtavailable inbuild/compose_compiler/. - The developer understands the basic stability vocabulary:
stable,unstable,skippable,restartable,@Stable,@Immutable. - Kotlin 2.0+ with the Compose compiler plugin (Strong Skipping default ON).
Workflow — diagnostic question and answer tree
What ships with it
2 files 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.
- 8d ago First seen · 230 lines · 184 tokens per session scan A 84c1e7314e64
understanding-stability-inference is a skill published in the GitHub repository skydoves/compose-performance-skills (499 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 184 tokens to every session and 4,016 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
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.
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-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…
fgs-state-ended-trap
Suppress the "ended" playback state at a forwarding-player boundary while the underlying player is being replaced, so the media service is not torn down in the gap between one player finishing and the next starting. Use when background playback stops partway through a queue on some devices but never on your…
endless-queue-management
One StateFlow holds a growing playback queue but has two write paths on purpose — a full setter that resets derived snapshots, and continuation appends that write the backing field directly so those snapshots survive. Use when a feature keyed on "where the queue came from" stops working once the queue auto-extends, or…