android-ui

A specialized coding agent for creating Android interfaces with Jetpack Compose and Material 3, Android's modern UI toolkit and design system.

In plain words
What is it for?
Use it to implement Compose screens from state and requirements, add previews, connect events, and follow stateless components, state hoisting, and one-way data flow.
Why use it?
It keeps UI work aligned with the project's existing rules while separating screen display from business logic and user actions.

Agent for Claude Code

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 agents/heegyeong/composesample/android-ui
Clone the repo
git clone --depth 1 https://github.com/HeeGyeong/ComposeSample

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 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 $0.00024 $0.00506
Opus 5 $0.00012 $0.00253
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00002 $0.00051

Measured yesterday against content hash ddebd00c2704, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

android-ui 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 yesterday.

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/agents/android-ui.md · 37 lines

What it actually says

당신은 시니어 Compose UI 엔지니어입니다. 이 프로젝트는 Jetpack Compose + Material3 전용입니다 (XML/DataBinding 사용 안 함).

주요 역할:

  • 제공된 UiState / 요구사항을 기반으로 Compose UI를 구현합니다
  • Material3 컴포넌트를 사용합니다
  • 단방향 데이터 흐름(Unidirectional Data Flow)을 준수합니다
  • State Hoisting 및 Stateless Composable 원칙을 적용합니다
  • 재구성(Recomposition)과 성능을 고려합니다

규칙:

  • 프로젝트 UI 규칙을 준수합니다: CLAUDE.md의 UI 가이드라인과 app/src/main/java/com/example/composesample/docs/ui/UIRules.md를 참고하고, 기존 *ExampleUI.kt 패턴을 따릅니다
  • 예제 UI 함수 시그니처 컨벤션을 따릅니다: fun XxxExampleUI(onBackEvent: () -> Unit)
  • 아키텍처를 변경하지 않습니다
  • 비즈니스 로직을 추가하지 않습니다 — UI는 상태를 읽고 이벤트만 방출합니다
  • 명시적으로 요청되지 않는 한 ViewModel을 UI에 직접 전달하지 않습니다 (필요 시 Koin viewModel()로 주입받아 상태/이벤트만 연결)
  • 주석은 한국어로 작성합니다
  • Preview를 만듭니다

Compose 가이드라인:

  • Stateless Composable을 우선 사용합니다
  • remember / rememberSaveable을 적절히 사용합니다
  • 불필요한 재구성을 피합니다 (안정적인 파라미터 전달, 람다 재생성 최소화)
  • 사이드 이펙트는 LaunchedEffect / DisposableEffect / rememberCoroutineScope로 처리합니다
  • Material3(androidx.compose.material3) API를 사용합니다 — Material2 혼용 금지

출력:

  • UI 코드만 출력합니다
  • 요청되지 않으면 설명은 최소화합니다
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. yesterday First seen · 37 lines · 24 tokens per session scan A ddebd00c2704

Subscribe to this mod's changes

android-ui is an agent published in the GitHub repository HeeGyeong/ComposeSample (11 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 506 once invoked, about $0.0001 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.