android-modularization-pro

android-modularization-pro is a skill for Claude Code from kelvinkosbab/AppBootstrapAI. It costs 109 tokens per session (1,807 once invoked), scanned A, original, MIT.

A toolkit for splitting an Android app into several Gradle modules, which are separately organised build units. It plans, reviews, and carries out the move from a large app module into feature, data, domain, model, and shared core modules.

In plain words
What is it for?
Use it to plan, audit, or migrate an Android project to a multi-module build.
Why use it?
A single oversized app module makes dependencies and changes harder to understand. Separating modules makes the dependency structure explicit and allows a migration to be checked one step at a time.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Good fit Use it to plan, audit, or migrate an Android project to a multi-module build.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kelvinkosbab/appbootstrapai/android-modularization-pro
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 kelvinkosbab/AppBootstrapAI --skill android-modularization-pro
Clone the repo
git clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAI

Made for: Claude Code.

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-modularization-pro

README.md
[![agentmods](https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-modularization-pro/github.svg)](https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/android-modularization-pro)
Your own site
<a href="https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/android-modularization-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-modularization-pro/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 android-modularization-pro

Your own site · 80×15
<a href="https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/android-modularization-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-modularization-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,807 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 $0.00109 $0.01807
Opus 5.5 $0.00044 $0.00723
Sonnet 5.5 $0.00022 $0.00361
Haiku 4.5 $0.00011 $0.00181

Measured 6d ago against content hash f6d826850887, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

android-modularization-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 6d 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-modularization-pro/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn an Android app into a thin :app over many small Gradle modules, or check one that already is. This is the deep companion to the always-on android-modular-architecture.md rule. The rule steers while writing; this skill plans a graph, audits a whole build, and drives a migration one module at a time.

Pick the mode from the request:

  • Plan: a new app, or a single-module app before any move. Produce a module map (module · type · purpose · dependencies) and the extraction order, using references/module-graph.md. Start small (:core:model, :core:data, :core:designsystem, one feature) and say which later splits you'd expect.
  • Migrate: move code out of :app, or out of an oversized module, following references/migration.md. One module per step, the app building and tests passing after each.
  • Audit: an app that already has modules. Run the checks in references/audit.md, then report findings ranked by severity.

Review process (audit mode):

  1. Inventory: settings.gradle.kts includes, each module's plugins and Kotlin file count, :app's Kotlin files, and gradle.properties build flags. Use references/audit.md ("Inventory").
  2. Check the graph with references/module-graph.md and the dependency report in references/audit.md: feature→feature impl edges, features reaching data sources, api(...) overuse, :impl modules consumed outside :app, oversized or near-empty modules.
  3. Check navigation and DI with references/navigation-and-di.md: how features reach each other, where the NavHost lives, Hilt module visibility, test bindings.
  4. Check resources, visibility, and build flags: non-transitive R, resource prefixes, internal/explicit API, configuration cache and build cache.
  5. Check enforcement: is there a module-graph assertion in CI, and a module table in CLAUDE.md?

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

Core Instructions

  • :app is an assembler. It keeps the Application, MainActivity, the top-level NavHost, the manifest, and launcher resources. Screens, ViewModels, and repositories belong in modules.
  • Direction is the architecture. :app → features → domain → data → data sources → model. Features never depend on another feature's impl; shared needs move down into :core:*.
  • Navigation goes through :app. Features expose a NavGraphBuilder entry and navigation lambdas; the api module holds routes. :app connects them.
  • Incremental, never big-bang. Every step leaves the app building and shippable. Convention plugins come first so each new module costs a few lines.
  • implementation and internal by default. api(...) and public symbols are deliberate, reviewed choices.
  • Granularity follows real boundaries. Split for a second owner, a heavy dependency only part of the code needs, reuse by another app (Wear, TV), or slow builds. Don't split speculatively.
  • Enforce what you decide. A graph rule without a CI check is a suggestion.
  • Severity by cost: broken (a missing Hilt binding at runtime because a module never reaches :app, resources resolving through a transitive R that breaks when non-transitive R is on, a dynamic feature with a missing split) > boundary leak (feature→feature impl edge, features importing :core:database or :core:network, logic in :app, api leaks) > shape (oversized or near-empty modules, missing graph check or module table).
  • Cross-reference, don't duplicate: convention plugins, catalogs, and AGP versions go to android-gradle-architecture-pro; ViewModel and UiState shape to android-mvvm-architecture.md; repositories to android-repository-pattern.md; design-system contents to android-design-system-pro; Compose performance to android-compose-pro.

Read the full file on GitHub · 97 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. 6d ago First seen · 97 lines · 109 tokens per session scan A f6d826850887

Subscribe to this mod's changes

android-modularization-pro is a skill published in the GitHub repository kelvinkosbab/AppBootstrapAI (7 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,807 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 2026-10-11.

Related

Other skills, from other repositories

compose-animations

Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.

chrisbanes/skills · 64 tokens

compose-focus-navigation

Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.

chrisbanes/skills · 41 tokens

android-slim-bindings

Create Android slim bindings for MAUI/.NET Android. USE FOR: Native Library Interop, thin Kotlin/Java wrapper design, building wrapper AARs with Gradle, Java-friendly callbacks, @JvmStatic, and dependencies of slim wrappers. DO NOT USE FOR: direct/full Java/Kotlin bindings or generated-code/Metadata.xml repairs (use…

dotnet/maui-labs · 96 tokens

android-java-bindings

Write and repair C# bindings for Java/Kotlin Android libraries with .NET for Android. USE FOR: direct/full AAR or JAR bindings, AndroidMavenLibrary, Metadata.xml, Additions, missing generated APIs, Kotlin JVM signatures, binding-generator warnings, CS0535/CS0738/CS0534, duplicate members, EventArgs, listener Handler…

dotnet/maui-labs · 134 tokens

ios-slim-bindings

Create iOS slim bindings for MAUI. USE FOR: slim iOS binding, Native Library Interop, Swift/Objective-C wrappers, XcodeGen project.yml, Podfile, CocoaPods static linking, BUILDLIBRARYFORDISTRIBUTION, XcodeProject MSBuild, @objc/[Export] selector crashes, async completion handlers. DO NOT USE FOR: Android bindings…

dotnet/maui-labs · 97 tokens

maui-notifications-deep-links

Implement MAUI notifications and deep links. USE FOR: local/push notifications, FCM HTTP v1 migration, APNs/Azure Notification Hubs, permission UX, Android channels/POSTNOTIFICATIONS, iOS UNUserNotificationCenter, token lifecycle, notification tap navigation, app links/universal links/URI schemes. DO NOT USE FOR…

dotnet/maui-labs · 90 tokens