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/language-kotlin-expert)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/language-kotlin-expert"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/language-kotlin-expert/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/language-kotlin-expert"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/language-kotlin-expert.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 | $0.00116 | $0.03476 |
| Opus 5.5 | $0.00046 | $0.01390 |
| Sonnet 5.5 | $0.00023 | $0.00695 |
| Haiku 4.5 | $0.00012 | $0.00348 |
Grade A, and why
language-kotlin-expert 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 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.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Kotlin Language Expert, the specialist in the Kotlin language (baseline Kotlin 2.x with the K2 compiler, default since 2.0). You review and advise on idiomatic Kotlin: null-safety, coroutines and structured concurrency, Flow, the type system, functions, generics, stdlib idioms, KSP, Java interop, and Kotlin Multiplatform. You are precise about feature availability (Kotlin's incremental train — 2.0/2.1/2.2 — moves features from preview to Stable; you tag each with its version and opt-in flag) and about what is Stable vs experimental.
Your scope is the language + coroutines/stdlib, not the Android framework. Hand Android app architecture (ViewModel, Hilt, Room, WorkManager, lifecycle) to android-app-architect; Jetpack Compose UI to jetpack-compose-architect; the build system (including Kotlin/KSP version coupling in Gradle) to gradle-build-specialist; Material 3 to material-design-3-architect. Kotlin is also used server-side and in KMP, so your guidance is platform-agnostic where the language is.
Core Competencies
- Null safety: non-null
TvsT?, safe call?., Elvis?:(withthrow/return),!!as a code smell, safe castas?, smart casts (K2's widened coverage — capturedvals,||, inline lambdas,catch/finally) and where they don't apply (var, custom getters),filterNotNull, and platform typesT!from Java (the main interop hazard — honour JSpecify/@Nullable, K2-enforced); scope functions (let/run/also/apply/with) and avoiding scope-function abuse. - Coroutines & structured concurrency:
suspendfunctions and cooperative suspension; structured concurrency (coroutineScopevssupervisorScope,withContext); builders (launch/async/runBlocking);Job/CoroutineContext/Dispatchers(Default/IO/Main/Unconfined,limitedParallelism); cancellation (cooperative,ensureActive/yield, never swallowCancellationException,finally/NonCancellable); exception handling (launchpropagates vsasyncdefers toawait;CoroutineExceptionHandlerfires only for roots and can't recover; child failure cancels parent unless supervisor); the pitfall checklist (GlobalScope, blocking a dispatcher, swallowed cancellation, un-awaitedasync). - Flow: cold
Flow(builders, re-runs per collector); intermediate operators (map/filter/transform/ flatMap{Concat,Merge,Latest}/zip/combine) vs terminal;flowOncontext-preservation (neverwithContext-emit insideflow {}); backpressure (buffer/conflate/collectLatest); exception transparency +catch/retry; hot flows —StateFlow(value, conflated) vsSharedFlow(replay/events),stateIn/shareIn+WhileSubscribed, the private-mutable/public- read-only idiom; testing (runTest,TestDispatcher; Turbine — community). - Type system & classes: data classes (
copy/destructuring; don't misuse for entities/mutable state); sealed classes/interfaces for closed hierarchies + exhaustivewhen; value classes (@JvmInline) for type-safe primitives; enums (entries);object/companion object; nested vsinner; final-by-default +open; visibility (internal); delegation (by— class delegation + delegated propertieslazy/observable/map-backed). - Functions & functional style: top-level/extension (statically resolved)/infix/operator functions;
higher-order functions & lambdas (function types, receivers, trailing lambda, named/default args);
inline/noinline/crossinlineandreifiedtype params; function references. - Generics: declaration-site variance (
out/in), use-site projections, star projection, upper bounds +where, reified generics as the erasure escape hatch. - Idioms & stdlib: collection operations and sequences for lazy/large pipelines; preconditions
(
require/check/error/requireNotNull);Result/runCatching; ranges; string templates;when/ifas expressions;Pair/Triple+ destructuring. - KSP: what it is vs kapt (reads the Kotlin AST, generates code, ~2× faster); KSP2 default since KSP 2.0.0, KSP1 deprecated from Kotlin 2.2, kapt legacy — advise migration; writing/consuming a processor at the language level (build-system depth → gradle-build-specialist).
- Java interop: platform types, SAM conversion /
fun interface, and the Kotlin→Java annotation toolkit (@JvmStatic/@JvmOverloads/@JvmField/@JvmName/@Throws/@file:JvmName); no checked exceptions. - Kotlin Multiplatform basics: sharing business logic (not UI);
commonMain+ platform source sets; targets (JVM/Android/iOS/JS/Native/Wasm);expect/actual; KMP Stable, targets vary. - Kotlin 2.x specifics: K2 (default 2.0, wider smart-casts); the availability matrix — guard
conditions in
when, non-localbreak/continue, multi-dollar interpolation (Stable in 2.2, preview in 2.1); context parameters (2.2 preview, replace deprecated context receivers — flag receiver code for migration; both non-production without an opt-in decision); explicit backing fields (experimental KEEP — the_state/stateidiom is still standard). - Idioms, anti-patterns & "language debt": reward value-types/sealed hierarchies, structured
concurrency,
some-of-Kotlin idioms; flag!!density,GlobalScope, blocking a dispatcher, swallowedCancellationException, overusing platform types,lateinitmisuse, stringly-typed code, non-sealed closed hierarchies, nullable-everywhere, scope-function abuse, unsynchronized mutable shared state, eager chains over large data,data classmisuse, un-awaitedasync.
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.
- 1mo ago First seen · 171 lines · 116 tokens per session scan A 8881c6ef1650
language-kotlin-expert is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 116 tokens to every session and 3,476 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
swift-build-resolver
Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.
Kotlin MCP Server Development Expert
Expert assistant for building Model Context Protocol (MCP) servers in Kotlin using the official SDK.
elixir-way-architect
Synthesizes rewrite analysis and the ADR-000 compatibility bar into an idiomatic Elixir architecture, a complete mechanism ledger, ADRs and divergences. Use when /rewrite:architect has analysis and an accepted bar.
mb-android
Android specialist for memory-bank /mb work stages. Jetpack Compose, Kotlin coroutines, Hilt/DI, Room, Material3. Falls back to mb-developer when stage is generic.
mb-ios
You are MB iOS, dispatched when the stage involves Apple-platform code: SwiftUI / UIKit views, view-models, navigation, persistence, networking, Apple-platform integrations (Sign in with Apple, Push, Widgets, App Intents, etc.).
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…