android-modularization

android-modularization is a skill for Claude Code, Codex from krutikJain/android-agent-skills. It costs 24 tokens per session (926 once invoked), scanned A, original, MIT.

An Android repository-structure guide for splitting code into feature, shared-core, data, and build-logic modules without circular dependencies.

In plain words
What is it for?
Use it to plan module splits, fix dependency direction, control public APIs, and separate feature, data, core, and test-only code.
Why use it?
Clear module boundaries make ownership easier to understand and stop unrelated features from becoming tightly coupled.

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/krutikjain/android-agent-skills/android-modularization
Any agent
npx skills add krutikJain/android-agent-skills --skill android-modularization
Clone the repo
git clone --depth 1 https://github.com/krutikJain/android-agent-skills

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-modularization

README.md
[![agentmods](https://agentmods.dev/badge/skills/krutikjain/android-agent-skills/android-modularization.svg)](https://agentmods.dev/skills/krutikjain/android-agent-skills/android-modularization)
Your own site
<a href="https://agentmods.dev/skills/krutikjain/android-agent-skills/android-modularization"><img src="https://agentmods.dev/badge/skills/krutikjain/android-agent-skills/android-modularization.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 926 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 $0.00926
Opus 5 $0.00012 $0.00463
Sonnet 5 $0.00005 $0.00185
Haiku 4.5 $0.00002 $0.00093

Measured yesterday against content hash 6d993a6c389f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

android-modularization 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run_examples.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/android-modularization/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android Modularization

When To Use

  • Use this skill when the request is about: android module split, feature modularization in android, break cyclic module dependency.
  • Primary outcome: Design Android repositories with feature, core, and build-logic modules that scale without cyclic dependencies.
  • Reach for this skill when the problem is dependency direction, API ownership, or feature/data/core boundaries, not task-level build speed tuning.
  • Handoff skills when the scope expands:
  • android-gradle-build-logic
  • android-architecture-clean

Workflow

  1. Map the current module graph first: app, feature, data, core, build-logic, and any dynamic-feature or test-only modules.
  2. Identify which direction is wrong: feature-to-feature coupling, framework leakage into domain/data, API surface too wide, or duplicated shared code with unclear ownership.
  3. Split by ownership and change rate, not by abstract theory; create the smallest module boundary that removes the current coupling problem.
  4. Keep api vs implementation, public surface area, and test fixture ownership explicit so the new boundary stays stable.
  5. Hand off build-speed or plugin-architecture issues only after the module graph itself is coherent.

Guardrails

  • Prefer official Android and Kotlin guidance over custom local conventions when they conflict.
  • Keep public APIs boring and explicit; avoid clever abstractions that hide Android lifecycle costs.
  • Do not mix architectural cleanup with product behavior changes unless the request explicitly needs both.
  • Document any compatibility constraints that will affect old modules or generated code.
  • Avoid over-modularizing a small codebase when the real need is a single clearer ownership boundary.

Anti-Patterns

  • Sprinkling helpers across modules without a clear ownership boundary.
  • Introducing framework-specific code into pure domain or data layers.
  • Refactoring every adjacent file when only one contract needed to change.
  • Leaving migration notes implied instead of writing them down.
  • Treating module count as the goal instead of build isolation and dependency clarity.

Read the full file on GitHub · 69 lines

Files

What ships with it

5 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 · 69 lines · 24 tokens per session scan A 6d993a6c389f

Subscribe to this mod's changes

android-modularization is a skill published in the GitHub repository krutikJain/android-agent-skills (14 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 926 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 2026-09-03.

Related

Other skills, from other repositories

navigate

Call the unintent tool with the following exact parameters.

vNeeL-code/GHOST · 6 tokens

compose-kotlin-agent-skills

Enterprise Android/Kotlin skill for 2026 — Kotlin 2.x K2 compiler, AGP 9, Navigation 3, edge-to-edge Compose, strict MVI with atomic state.update, banned AI antipatterns. Jetpack Compose, Hilt, Room, KMP, CameraX/ML Kit, performance, testing. Use when writing Kotlin for Android, building Compose UI, MVVM/MVI…

haidrrrry/compose-kotlin-agent-skills · 149 tokens

android-kotlin-compose

Jetpack Compose UI engineering for 2026 — edge-to-edge, Material 3, recomposition stability, Modifier ordering, LazyColumn performance, and animations. Use when building composables, fixing jank, theming, adaptive layouts, Canvas drawing, auditing screens, or asking "why does my screen recompose", "Modifier order"…

haidrrrry/compose-kotlin-agent-skills · 90 tokens

android-kotlin-architecture

Enforces Clean Architecture, MVVM/MVI, and unidirectional data flow for Android apps. Covers UiState, UiEvent, UiEffect, UseCase boundaries, module structure, and atomic ViewModel state via state.update. Use when structuring features, refactoring ViewModels, splitting modules, or asking "MVVM vs MVI", "where does…

haidrrrry/compose-kotlin-agent-skills · 87 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

compose-expert

Compose and Compose Multiplatform expert for UI development across Android, Desktop, iOS, and Web. Use whenever the user mentions Compose APIs (@Composable, remember, LaunchedEffect, NavHost, MaterialTheme, LazyColumn, Modifier, recomposition), Compose Multiplatform (commonMain, expect/actual, Res.…

aldefy/compose-skill · 185 tokens