Minitask: Skill for Claude Code

.agents/skills/compose-stability-diagnostics/SKILL.md

compose-stability-diagnostics is a skill for Claude Code, Codex from costular/Minitask. It costs 43 tokens per session (1,336 once invoked), scanned A, a copy of compose-stability-diagnostics, Apache-2.0.

A diagnostic guide for Jetpack Compose, Android's Kotlin UI toolkit, that explains why UI functions run again and how their inputs affect skipping. It covers compiler reports, unstable state objects, and Kotlin's strong-skipping behavior.

In plain words
What is it for?
It helps review composable parameters, UI state classes, collections, compiler reports, and unexpected recomposition or non-skipping.
Why use it?
It helps distinguish real parameter-related performance problems from behavior caused by the Kotlin and Compose compiler version in use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is costular/Minitask's own configuration. It tells Claude Code and Codex how to work on Minitask itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Minitask configures →

Reuse

Borrowing it

Nothing to install: this file belongs to costular/Minitask. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/costular/Minitask/main/.agents/skills/compose-stability-diagnostics/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/costular/Minitask

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for compose-stability-diagnostics

README.md
[![agentmods](https://agentmods.dev/badge/skills/costular/minitask/compose-stability-diagnostics/github.svg)](https://agentmods.dev/skills/costular/minitask/compose-stability-diagnostics)
Your own site
<a href="https://agentmods.dev/skills/costular/minitask/compose-stability-diagnostics"><img src="https://agentmods.dev/badge/skills/costular/minitask/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.

agentmods 80×15 button for compose-stability-diagnostics

Your own site · 80×15
<a href="https://agentmods.dev/skills/costular/minitask/compose-stability-diagnostics"><img src="https://agentmods.dev/badge/skills/costular/minitask/compose-stability-diagnostics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01336
Opus 5.5 $0.00017 $0.00534
Sonnet 5.5 $0.00009 $0.00267
Haiku 4.5 $0.00004 $0.00134

Measured 1mo ago against content hash 1cd2d9155939, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

Origin

This is a copy

94% identical to compose-stability-diagnostics — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/compose-stability-diagnostics/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compose stability diagnostics

Core principle

Compose performance problems from parameters are about whether inputs compare cheaply and predictably across recompositions. With Kotlin 2.0.20+ strong skipping is enabled by default, so unstable parameters no longer automatically make restartable composables non-skippable. That does not make stability irrelevant: unstable parameters are compared by instance identity (===), stable parameters by equality (equals), and churny instances can still defeat skipping.

First identify the compiler mode you are on, then read reports in that context.

When to use this skill

  • A composable or screen recomposes more than expected and parameter churn is suspected.
  • A UI-state/model class is passed to composables and contains List, Set, Map, ranges, Java time/money types, or third-party types.
  • composables.txt / classes.txt shows unstable parameters or non-skippable composables.
  • A project uses Kotlin < 2.0.20, disables strong skipping, or has old Compose compiler report guidance.

1. Start with strong skipping

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.

That means the question changes from "is this composable skippable at all?" to "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")
    }
}

Read the full file on GitHub · 141 lines

Changes

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.

  1. 1mo ago First seen · 141 lines · 43 tokens per session scan A 1cd2d9155939

Subscribe to this mod's changes

compose-stability-diagnostics is a skill published in the GitHub repository costular/Minitask (12 stars, last pushed 6d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,336 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to compose-stability-diagnostics, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

kmp-architecture-footguns

Kotlin Multiplatform structure and language traps: module splits, expect/actual, Koin and ViewModel scoping, layers, version catalogs, erased overloads, Char and string-resource formatting limits. Use when shaping modules or DI, when a format specifier renders verbatim, or code misbehaves on one platform.

maxrave-dev/kotlin-footguns · 73 tokens

state-and-background-footguns

Reactive state and background-work traps: StateFlow conflation, flatMapLatest, job lifecycles, ViewModel bases, WorkManager, backups, crash reporting, logging, Glance widgets. Use when state lags or flips, or work runs twice or never.

maxrave-dev/kotlin-footguns · 60 tokens

android

Senior-level Android engineering expertise for Jetpack Compose, Material 3, shared element transitions, navigation, performance, security, background work, notifications, adaptive layouts, Coil image loading, WorkManager, FCM, Baseline Profiles, R8 optimization, accessibility, coroutines and Flow, and extraordinary UI…

ayush016/android-lead-agent-skills · 264 tokens

swift-concurrency-expert

Swift concurrency review/fix: compiler errors, Sendable, isolation, remediation.

steipete/agent-scripts · 22 tokens

axiom-analyze-swift-performance

Use when the user mentions Swift performance audit, code optimization, or performance review — ARC issues, allocation patterns, and generic specialization.

CharlesWiltgen/Axiom · 34 tokens

kotlin-tooling-native-build-performance

Diagnoses and fixes slow Kotlin/Native compilation and linking in Kotlin Multiplatform projects that target iOS. Use when the user reports slow iOS or shared-framework builds, long linkDebug/linkRelease or XCFramework tasks, cold CI builds that re-download the Kotlin/Native toolchain, KSP or other generated code on…

Kotlin/kotlin-agent-skills · 96 tokens