android-compose-pro

android-compose-pro is a skill for Claude Code, Codex from kelvinkosbab/AppBootstrapAI. It costs 56 tokens per session (883 once invoked), scanned A, original, MIT.

A code reviewer for Jetpack Compose, Android’s toolkit for building screens with Kotlin. It examines how screen state, updates, side effects, and scrolling lists are implemented.

In plain words
What is it for?
Use it to review or write non-trivial Compose screens, especially when investigating lag, repeated recomposition, effect bugs, state-flow problems, or slow lazy lists.
Why use it?
It helps find screens that redraw too often, become slow, run effects at the wrong time, or lose track of who owns their state. It also checks basic accessibility details without doing a full accessibility review.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kelvinkosbab/appbootstrapai/android-compose-pro
Any agent
npx skills add kelvinkosbab/AppBootstrapAI --skill android-compose-pro
Clone the repo
git clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAI

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 android-compose-pro

README.md
[![agentmods](https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-compose-pro.svg)](https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/android-compose-pro)
Your own site
<a href="https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/android-compose-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-compose-pro.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00056 $0.00883
Opus 5 $0.00028 $0.00441
Sonnet 5 $0.00011 $0.00177
Haiku 4.5 $0.00006 $0.00088

Measured 5d ago against content hash df847a2e5933, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

android-compose-pro 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 5d 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.

.claude/skills/android-compose-pro/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Jetpack Compose code for correctness and performance. This is the deep-review companion to the always-on android-compose-best-practices.md rule — the rule steers while writing; this skill audits what was written. Report only genuine problems; don't nitpick or invent issues.

Review process:

  1. Check state modeling and hoisting using references/state-modeling.md — where state lives, who owns it, how it flows.
  2. Check recomposition stability using references/stability.md — unstable parameters, lambda churn, skippability.
  3. Audit every side effect using references/side-effects.md — keys, teardown, stale captures.
  4. Check lazy-layout performance using references/lazy-performance.md — keys, contentType, scroll-driven state.
  5. Spot-check semantics against the android-accessibility-best-practices.md rule (merged nodes, roles, contentDescription) — don't duplicate a full a11y audit here.

If doing a partial review, load only the relevant reference files.

Core Instructions

  • Target Kotlin 2.x with the Compose Compiler Gradle plugin; assume Material 3.
  • Recomposition is the lens. Most Compose bugs and jank reduce to "this runs more often than the author thinks" — composition, effect launch, or lambda allocation. Trace the actual invalidation, don't guess.
  • Don't recommend @Stable/@Immutable as a reflex. First check whether strong skipping (default under Kotlin 2.0.20+ Compose compilers) already covers the case; annotations are for genuine contracts, not cargo cult.
  • Side effects are guilty until proven keyed correctly. Every LaunchedEffect/DisposableEffect gets the question: what restarts you, and is that the author's intent?
  • Business state never lives in remember { }. ViewModel + StateFlow + collectAsStateWithLifecycle() is the boundary; flag exceptions.
  • Performance claims need a mechanism. When flagging a perf issue, name the mechanism (per-frame recomposition, missing keys forcing re-layout, unstable lambda defeating skipping) — not just "this could be slow."

Read the full file on GitHub · 56 lines

Files

What ships with it

4 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.

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. 5d ago First seen · 56 lines · 56 tokens per session scan A df847a2e5933

Subscribe to this mod's changes

android-compose-pro is a skill published in the GitHub repository kelvinkosbab/AppBootstrapAI (5 stars, last pushed 14d ago), licensed MIT. It adds 56 tokens to every session and 883 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

kmp-glassmorphism-ui

Implements a production-grade Glassmorphism design system for Kotlin Multiplatform (KMP) Compose Multiplatform projects. Use when the user asks for glass UI, frosted glass effects, glassmorphism theme, translucent/transparent UI components, liquid/blob animated backgrounds, or premium modern dark-mode design in a…

Aks-4125/kmp-glassmorphism-skill · 81 tokens

flutter-cherry-pick

How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel. Only use for flutter/flutter landed pull requests. Only use when the cherry pick request is into "stable", "beta" or a branch that has the format with flutter- . -candidate.0.

flutter/flutter · 72 tokens

updating-android-sdk

Upgrades Flutter's Android SDK dependency to a new Android API version (or preview/canary release) in packages.txt, verifies CIPD tag uniqueness, and packages/uploads the binaries using createcipdpackages.sh across macOS, Linux, and Windows. Use whenever a user wants to pick up a new version of Android or upload…

flutter/flutter · 80 tokens

analyze-github-flake

Expertise in analyzing flake github issues in the flutter/flutter repository. Use when a user wants to analyze the flakiness of a specific link to a flutter github issue.

flutter/flutter · 42 tokens

upgrade-browser

Upgrade browser versions (Chrome or Firefox) in the Flutter Web Engine and/or Framework tests. Use when asked to roll or upgrade Chrome or Firefox to a newer version.

flutter/flutter · 36 tokens

run-devicelab-with-led

Run DeviceLab tests for Flutter PRs using LUCI's led CLI tool. Use when asked to run, launch, try, or deflake a post-submit or devicelab test against a PR using led.

flutter/flutter · 55 tokens