android-build

android-build is a skill for Claude Code from hyperb1iss/hyperdroid-skill. It costs 72 tokens per session (2,282 once invoked), scanned C, original, MIT.

Build instructions for Android applications and custom Android-based systems such as AOSP or LineageOS. They cover Gradle builds, tests, lint checks, and ROM commands such as `lunch` and `brunch`.

In plain words
What is it for?
Use them to build APKs or app bundles, run unit and device tests, perform linting, or compile Android ROMs and kernels.
Why use it?
They give a coding assistant known commands and conventions for compiling, testing, and checking Android projects.

Skill for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./prebuilts/sdk/tools/jack-admin kill-server.

Part of the hyperdroid plugin — 4 skills, 1 agent shipped together

Good fit Use them to build APKs or app bundles, run unit and device tests, perform linting, or compile Android ROMs and kernels.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/hyperb1iss/hyperdroid-skill
agentmods
npx agentmods add skills/hyperb1iss/hyperdroid-skill/android-build

Made for: Claude Code.

Or install hyperdroid, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

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-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyperb1iss/hyperdroid-skill/android-build/github.svg)](https://agentmods.dev/skills/hyperb1iss/hyperdroid-skill/android-build)
Your own site
<a href="https://agentmods.dev/skills/hyperb1iss/hyperdroid-skill/android-build"><img src="https://agentmods.dev/badge/skills/hyperb1iss/hyperdroid-skill/android-build/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-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/hyperb1iss/hyperdroid-skill/android-build"><img src="https://agentmods.dev/badge/skills/hyperb1iss/hyperdroid-skill/android-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00072 $0.02282
Opus 5.5 $0.00029 $0.00913
Sonnet 5.5 $0.00014 $0.00456
Haiku 4.5 $0.00007 $0.00228

Measured 1mo ago against content hash a5ee8253c80a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

android-build scanned grade C with 2 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 1mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.gradle/daemon

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://storage.googleapis.com/git-repo-downloads/repo > ~/.bin/repo
skills/android-build/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android Build Systems

This skill covers building Android apps via Gradle CLI and building custom ROMs via AOSP/LineageOS.


App Building (Gradle CLI)

Essential Commands

./gradlew tasks                     # List available tasks
./gradlew assembleDebug             # Build debug APK
./gradlew assembleRelease           # Build release APK
./gradlew installDebug              # Build + install to device
./gradlew bundleRelease             # Build AAB (App Bundle)

# APK output location
# app/build/outputs/apk/debug/app-debug.apk
# app/build/outputs/apk/release/app-release.apk

Build Variants

./gradlew assembleFreeDebug         # Flavor + build type
./gradlew assemblePaidRelease
./gradlew assembleDebug --info      # Verbose output
./gradlew assembleRelease -x test   # Skip tests

Testing

./gradlew test                      # Unit tests
./gradlew testDebugUnitTest         # Debug unit tests only
./gradlew connectedAndroidTest      # Instrumented tests
./gradlew connectedCheck            # All connected tests

# Run specific test
./gradlew test --tests "*.MyTestClass"

Linting & Analysis

./gradlew lint                      # Run lint
./gradlew lintDebug                 # Debug only (faster)
./gradlew ktlintCheck               # Kotlin style (if configured)
./gradlew detekt                    # Detekt analysis (if configured)

Clean & Refresh

./gradlew clean                     # Clean build
./gradlew clean assembleDebug       # Clean + build
./gradlew --refresh-dependencies    # Force dependency refresh
./gradlew --stop                    # Stop Gradle daemon

Dependencies

./gradlew dependencies              # All dependencies
./gradlew app:dependencies          # Module dependencies
./gradlew dependencyInsight --dependency <name>

Signing

Debug keystore location:

  • Linux: ~/.android/debug.keystore
  • macOS: ~/.android/debug.keystore
  • Windows: C:\Users\<user>\.android\debug.keystore

Read the full file on GitHub · 384 lines

Files

What ships with it

2 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. 1mo ago First seen · 384 lines · 72 tokens per session scan C a5ee8253c80a

Subscribe to this mod's changes

android-build is a skill published in the GitHub repository hyperb1iss/hyperdroid-skill (49 stars, last pushed 9mo ago), licensed MIT. It adds 72 tokens to every session and 2,282 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

dagger-hilt-expert

Expert guidance for Dagger and Hilt dependency injection in Android. Use when implementing DI, creating modules, configuring scopes, optimizing performance, testing with Hilt, setting up multi-module architecture, using assisted injection, or debugging DI issues. Triggers on "dagger", "hilt", "dependency injection"…

JosephSanjaya/skills · 145 tokens

kotlin-mcp-server-expert

Expert guidance for building production-grade MCP (Model Context Protocol) servers in Kotlin using the official Kotlin Multiplatform SDK. Use this skill whenever the user is building, designing, debugging, or improving an MCP server in Kotlin — including tool registration, resource templates, prompt handling…

JosephSanjaya/skills · 169 tokens

koog-expert

Expert guide for JetBrains Koog (Kotlin AI agents). Use whenever the user mentions Koog, AIAgent, ToolRegistry, strategy graphs, koog-ktor, history compression, MCP tools, structured LLM output, or building agents in a Ktor backend, Spring Boot service, Android/iOS/desktop KMP app, JS, or WasmJS. Also use for…

JosephSanjaya/skills · 122 tokens

kotlin-coroutine-expert

Expert guidance on Kotlin Coroutines — structured concurrency, dispatcher selection, race condition prevention (Mutex/Channel/StateFlow), error propagation, Flow patterns, testing with runTest/TestDispatcher, and production optimization. Use this skill whenever the user writes coroutine code, asks about async Kotlin…

JosephSanjaya/skills · 89 tokens

solid-expert

Kotlin & Compose Multiplatform SOLID Expert. Applies SOLID principles with a strong preference for composition over inheritance (COI) to build professional, clean, maintainable, and testable mobile/multiplatform applications. Use when: designing architectures, refactoring deep class hierarchies, debugging class…

JosephSanjaya/skills · 97 tokens

kotlin-k2-expert

Expert knowledge for Kotlin K2 compiler plugin development, architecture, optimization, and Kotlin 2.4.0 compatibility. Use when: building K2 compiler plugins (FIR + IR), debugging FIR/IR generation issues, implementing FirDeclarationGenerationExtension or IrGenerationExtension, migrating K1 plugins to K2…

JosephSanjaya/skills · 193 tokens