agentmods.dev

wear-compose-m3

wear-compose-m3 is a skill for Claude Code from ArisGuimera/MobiAI-Core. It costs 91 tokens per session (8,841 once invoked), scanned A, original, MIT.

An Android guide for building and migrating Wear OS watch apps with Compose Material 3, Google's component library for modern Android interfaces. It covers watch-specific components, navigation, dependencies, and compatibility requirements.

In plain words
What is it for?
Use it when creating, updating, or migrating a Wear OS app that uses Compose Material 3, including projects moving from Material 2.5 or Horologist.
Why use it?
It helps avoid setup and version mismatches when moving between older and newer Wear OS Compose libraries.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the android plugin — 35 skills shipped together

not rated 489repo +3 yesterday A scan 91 tokens original MIT

Good fit Use it when creating, updating, or migrating a Wear OS app that uses Compose Material 3, including projects moving from Material 2.5 or Horologist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arisguimera/mobiai-core/wear-compose-m3
View source ↗ ArisGuimera/MobiAI-Core
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.

Any agent
npx skills add ArisGuimera/MobiAI-Core --skill wear-compose-m3
Clone the repo
git clone --depth 1 https://github.com/ArisGuimera/MobiAI-Core

Made for: Claude Code.

Or install android, the plugin that ships this one along with the rest of its 35 skills.

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 wear-compose-m3

README.md
[![agentmods](https://agentmods.dev/badge/skills/arisguimera/mobiai-core/wear-compose-m3/github.svg)](https://agentmods.dev/skills/arisguimera/mobiai-core/wear-compose-m3)
Your own site
<a href="https://agentmods.dev/skills/arisguimera/mobiai-core/wear-compose-m3"><img src="https://agentmods.dev/badge/skills/arisguimera/mobiai-core/wear-compose-m3/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 wear-compose-m3

Your own site · 80×15
<a href="https://agentmods.dev/skills/arisguimera/mobiai-core/wear-compose-m3"><img src="https://agentmods.dev/badge/skills/arisguimera/mobiai-core/wear-compose-m3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,841 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 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 5.1 $0.00091 $0.08841
Opus 5.5 $0.00036 $0.03536
Sonnet 5.5 $0.00018 $0.01768
Haiku 4.5 $0.00009 $0.00884

Measured yesterday against content hash be1bf34b468f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wear-compose-m3 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.

skills/android/skills/google/wear-compose-m3/SKILL.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prerequisites and compatibility

  1. Current Wear OS Compose version in-use: To find the installed library version, read gradle/libs.versions.toml or build.gradle.kts directly. Don't run ./gradlew dependencies or other shell commands to resolve versions.
  2. Wear OS Compose Material3 version: If an internal tool is available to establish the latest stable version {VERSION} of androidx.wear.compose:compose-material3, use that tool.
  3. Strict compliance: If a version is listed as stable, you MUST use it, unless overridden by the user. Do not downgrade based on initial "Unresolved reference" errors in the editor or outdated web search results.
  4. Kotlin & Compose compiler: Use Kotlin 2.0.0+ with the org.jetbrains.kotlin.plugin.compose Gradle plugin.
  5. Min SDK: Ensure minSdk is at least 25.
  6. Compile SDK & AGP: Ensure compileSdk and AGP meet the library's AAR metadata floors (compileSdk >= 35 and AGP >= 8.6.0 for 1.6.x; compileSdk >= 37 and AGP >= 9.1.0 for 1.7.x).

Gotchas

  1. Mandatory sync and validation: After updating versions in libs.versions.toml or build.gradle.kts, perform a Gradle sync (or ./gradlew assembleDebug) before refactoring, and run ./gradlew assembleDebug after refactoring to verify the build.
  2. Prohibition of guessing (error protocol): If you encounter an 'Unresolved Reference' or API mismatch after a successful sync, do not attempt to 'fix' it by downgrading the library version.

Capabilities and tools

Capability 1: Migration, updates, and adding features

Use this guidance when migrating from an older version of Wear OS Compose or Horologist, updating an existing Wear Compose Material3 project, or adding features.

  1. Unless otherwise indicated by the developer, use the latest stable version of Wear Compose Material3 from {VERSION} (superseding any literal version strings in the migration guide).
  2. When migrating from Material 2.5 or Horologist, read the migration guide and use its official component mappings.
  3. Before refactoring any component (for example, Chip -> Button), check the parameter names, slot types, and "Expressive" design tokens.
  4. Do not use the Horologist Composables, Compose Layout, or Compose Material libraries; replace Horologist components with Wear Compose M3 equivalents (AppScaffold -> M3 AppScaffold, ScreenScaffold -> M3 ScreenScaffold, ScalingLazyColumn -> TransformingLazyColumn, ResponsiveListHeader -> ListHeader, PagerScreen -> HorizontalPagerScaffold, Chip -> Button, Confirmation -> ConfirmationDialog).
  5. Always check against the component guidance in Capability 3.
  6. Expect screenshot tests to fail when migrating or updating components: expected defaults for padding and positioning will have changed. Do not seek to artificially match the previous screenshot, but give preference to the Material3 defaults.

Read the full file on GitHub · 352 lines

Files

What ships with it

52 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. yesterday First seen · 352 lines · 91 tokens per session scan A be1bf34b468f

Subscribe to this mod's changes

wear-compose-m3 is a skill published in the GitHub repository ArisGuimera/MobiAI-Core (489 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 8,841 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-22.

FrontendMobile
Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp: publish the Windows head first, then point packaging at the resolved resizetizer manifest. Use for a MAUI MSIX or signed unpackaged build, MAUI packaging in CI, or 'manifest contains unresolved placeholders' errors from winapp package.

microsoft/winappCli · 68 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens