What is gradle-build-optimizer?

A set of instructions for running Gradle, the build system commonly used for Android and Java projects, efficiently. It focuses on reusing Gradle’s background process and running only the needed app tasks.

Use it for targeted Android app builds and tests, checking real build results, and installing or launching a newly built app on a device.

It helps avoid stalled builds, Windows file-lock errors, unnecessary full rebuilds, short timeouts, and accidentally treating an unfinished build as successful.

gradle-build-optimizer — Skill for Claude Code and Codex by rabee-elkh

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 rabee-elkholy/android-harness-kit --skill gradle-build-optimizer

Clone the repo

git clone --depth 1 https://github.com/rabee-elkholy/android-harness-kit

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rabee-elkholy/android-harness-kit/gradle-build-optimizer.svg)](https://agentmods.dev/skills/rabee-elkholy/android-harness-kit/gradle-build-optimizer)

Your own site

<a href="https://agentmods.dev/skills/rabee-elkholy/android-harness-kit/gradle-build-optimizer"><img src="https://agentmods.dev/badge/skills/rabee-elkholy/android-harness-kit/gradle-build-optimizer.svg" alt="Measured on agentmods" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 447 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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.00447
Opus 5	$0.00016	$0.00224
Sonnet 5	$0.00006	$0.00089
Haiku 4.5	$0.00003	$0.00045

Measured 7d ago against content hash 3781ed1c359e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gradle-build-optimizer 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 7d 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.

agents/skills/gradle-build-optimizer/SKILL.md · 26 lines

What it actually says

Gradle Build Optimizer

Daemon reuse

Use the repo-root wrapper (gradlew.bat / ./gradlew). Do not use app/gradlew.
Do not start a second wrapper if a Gradle daemon for this checkout is already running.
Prefer python3 .agents/scripts/run_gradle_task.py :app:assembleDebug / :app:testDebugUnitTest --tests when only :app changed (python on Windows is fine). Do not run raw gradlew / gradlew.bat from the agent — the wrapper picks the OS script, streams executing tasks, and a 10s heartbeat. An empty task log means the process never started, not "still compiling silently".
Device install/launch: python .agents/scripts/run_device.py install-start (live adb output).
Raise the command wait high enough for a real compile (minutes, not 10 seconds). Success is the log line BUILD SUCCESSFUL on that same command. A timeout/early return is not success and is not a reason to start a second assemble. If the log shows BUILD FAILED, fix then start one new assemble. Do not install a leftover APK.
Daily builds are debug. Do not assemble staging or release unless asked (those minify and need keystore properties).

Windows file locks

If assemble fails with AccessDeniedException or kapt tmp delete errors, tell the developer.
Use ./gradlew --stop only with explicit developer agreement (it is not project-local).

Worktrees

This project does not use Git worktrees for AI subagents. Do not copy local.properties into a worktree or spawn Workspace="share".

Dependencies

Check transitive conflicts before adding libraries.
Avoid duplicating deps across :app, :base, :gdpr, :fat-burner.

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.

7d ago First seen · 26 lines · 32 tokens per session scan A 3781ed1c359e

Subscribe to this mod's changes

gradle-build-optimizer is a skill published in the GitHub repository rabee-elkholy/android-harness-kit (3 stars, last pushed 8d ago), licensed MIT. It adds 32 tokens to every session and 447 once invoked, about $0.0002 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 2026-08-31.

Claude Code DevOps and cloud Mobile ai-agents android antigravity copilot

android-ui-journey-testing

XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.

sickn33/agentic-awesome-skills · 27 tokens

Debroid CLI Debugger

Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.

PatilShreyas/debroid · 61 tokens

react-native-expert

Senior React Native and Expo engineer for building production-ready cross-platform mobile apps. Use when building React Native components, implementing navigation with Expo Router, optimizing list and scroll performance, working with animations via Reanimated, handling platform-specific code (iOS/Android), integrating…

tech-leads-club/agent-skills · 127 tokens

compose-navigation

Jetpack Compose Navigation for Android AI agents. Use this skill whenever implementing navigation, NavHost, NavController, back stack, deep links, navigation arguments, routes, type-safe navigation, @Serializable routes, navController.navigate, popBackStack, navigateUp, bottom navigation, tab navigation, nested…

piyushverma0/android-agent-skills · 138 tokens

design-system

Global-level design system for Android AI agents — Material 3 Expressive. Use this skill for visual consistency: spacing tokens, 8dp grid, M3 typography scale (15 styles), HCT color system, dynamic color Material You, shape system with morphing, motion tokens, physics-based spring animations, design tokens…

piyushverma0/android-agent-skills · 144 tokens

adaptive-ui

Adaptive UI for Android — responsive layouts for phones, tablets, foldables, Chromebooks, and large screens. Use this skill for EVERY screen you build. Triggers on: WindowSizeClass, ListDetailPaneScaffold, SupportingPaneScaffold, ThreePaneScaffold, NavigationSuiteScaffold, NavigationRail, NavigationDrawer, adaptive…

piyushverma0/android-agent-skills · 157 tokens