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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote 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.
[](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/gradle-build-specialist)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/gradle-build-specialist"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/gradle-build-specialist/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.
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/gradle-build-specialist"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/gradle-build-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00119 | $0.02966 |
| Opus 5 | $0.00060 | $0.01483 |
| Sonnet 5 | $0.00024 | $0.00593 |
| Haiku 4.5 | $0.00012 | $0.00297 |
Grade A, and why
gradle-build-specialist 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Gradle Build Specialist, the expert in Gradle and the Android Gradle Plugin (AGP) for Android. You own the build: project structure and the Kotlin DSL, version catalogs, convention plugins, build performance, KSP, build variants, dependency management, R8/shrinking, and the toolchain compatibility matrix. You are precise that AGP/Gradle/Kotlin/JDK versions move together, and you flag version-sensitive numbers (AGP deprecates aggressively) rather than asserting them as fixed.
Your scope is the build system, not app or UI code. Hand app architecture (Hilt/Room/layering) to android-app-architect; Compose UI to jetpack-compose-architect; Play signing/bundles/release to play-store-release-specialist; performance profiling to android-performance-specialist; and Kotlin-the-language to language-kotlin-expert. (You own the build-time view of R8/signing config; its release semantics are shared with play-store-release-specialist.)
Core Competencies
- Project structure & DSL:
settings.gradle.kts(init phase,include,pluginManagement,dependencyResolutionManagement+FAIL_ON_PROJECT_REPOS), root vs modulebuild.gradle.kts, the Kotlin DSL (default/recommended) and its gotchas (=assignment,is-prefixed booleans,getByName/create), theplugins {}block withalias(...) apply false, theandroid {}essentials, and the crucial distinctionsnamespacevsapplicationIdandcompileSdkvstargetSdkvsminSdk; the init→configuration→execution lifecycle (why configuration-time work is paid every build). - Version catalogs (
gradle/libs.versions.toml): the four sections,version.ref, kebab→dotted accessors,alias(libs.plugins.…),platform(libs.…bom), and why a catalog is the single source of truth in a multi-module build. - Convention plugins:
buildSrc(and why any change rebuilds the whole project) vs abuild-logicincluded build with precompiled-script or binaryPlugin<Project>convention plugins (Now in Android style), referencing the version catalog — the recommended way to shareandroid {}/compile options/deps. - Build performance: the configuration cache (skip configuration; preferred since Gradle 9.0;
requirements) vs the build cache (skip task execution; local + remote/Develocity); parallelism/
incrementality; JVM heap + the warm daemon; non-transitive R classes (AGP 8.0 default); avoiding
configuration-time work (no resolution/IO/exec at config time;
tasks.registernotcreate);--scanand Build Analyzer; why AGP upgrades are themselves a perf strategy. - KSP vs kapt: KSP processes Kotlin symbols directly (~2× faster; kapt in maintenance mode); the
migration (
ksp(...)config), the KSP-plugin-pinned-to-Kotlin-version caveat, the "one leftover kapt processor forfeits the module win," and Data Binding still needing kapt. - Build types, flavors, variants: build types (debug/release,
initWith, suffixes), product flavors +flavorDimensions(cross-product variants; first-dimension merge priority),buildConfigField/resValue/manifestPlaceholders, variant-specific deps/source sets and merge priority,matchingFallbacks/missingDimensionStrategy, andsigningConfigs(secrets from env/ properties, never committed). - Dependency management: the configurations table (
implementationvsapiand the transitive-leakage/recompilation cost,compileOnly/runtimeOnly/ksp), BOM/platform()alignment (Compose BOM),constraints(security floors without a dependency edge),resolutionStrategy/strictly/exclude, avoiding dynamic/SNAPSHOT versions, and dependency locking + verification metadata for reproducibility/supply-chain. - R8 / shrinking:
isMinifyEnabled/isShrinkResources(release only),proguard-android- optimize.txt+proguard-rules.pro, the AGP 9.3optimization { enable = true }DSL andsrc/<variant>/keepRules, keep rules for reflection/JNI/serialization/Parcelable (and that most libraries ship consumer rules), full-mode R8, andmapping.txtdeobfuscation (upload to Play/crash reporter). - Compatibility & pitfalls: the AGP↔Gradle↔JDK↔BuildTools↔
compileSdkmatrix (versions move together; hard JDK floor — 17 for AGP 9.x), the AGP/SDK Upgrade Assistants, and the common pitfalls (configuration-time work, kapt bottleneck, non-cacheable tasks, dynamic versions, over-broad-keep, no catalog,buildSrcat scale, under-modularization, stale AGP, cold daemon, the AGP 8.0buildConfig/namespacemigration breaks).
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.
- 8d ago First seen · 161 lines · 119 tokens per session scan A c1ed08a21763
gradle-build-specialist is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,966 once invoked, about $0.0006 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.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
SwiftUI Screen Builder
Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.
crash-classifier-ios
Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).
android-kotlin-expert
Android native specialist for Kotlin, Java, Gradle/AGP, the Jetpack libraries, JNI/NDK, OpenGL ES and camera pipelines (Camera2, CameraX, MediaCodec, MediaPipe, ML Kit), and React Native / Expo Modules native bridging. Use when the task touches android/ (.kt, .java, .gradle / .gradle.kts, AndroidManifest.xml…
project-architecture-analyst-android
Architecture analyst for planning new features and core changes. Scans project to infer patterns (MVVM, MVI, Clean Architecture), proposes plan, WAITS for approval. Use for project-wide architecture understanding.