kotlin-toolchain

A guide to JetBrains Kotlin Toolchain v0.12.x, a YAML-based system for configuring Kotlin projects and their builds. Kotlin is a programming language used for applications on the JVM, Android, iOS, web, and other platforms.

In plain words
What is it for?
Setting up modules, dependencies, project templates, version libraries, platform-specific targets, publishing, and local build plugins.
Why use it?
It explains how to configure projects without confusing this tool with Gradle, Maven, or older Amper configuration files.

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/heapy/kortex/kotlin-toolchain
Any agent
npx skills add Heapy/kortex --skill kotlin-toolchain
Clone the repo
git clone --depth 1 https://github.com/Heapy/kortex

Made for: Claude Code, Codex.

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,504 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 $0.00148 $0.05504
Opus 5 $0.00074 $0.02752
Sonnet 5 $0.00030 $0.01101
Haiku 4.5 $0.00015 $0.00550

Measured 2d ago against content hash 3d32f901c92e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kotlin-toolchain 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/aggregate-upstream-docs.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.

plugins/kortex/skills/kotlin-toolchain/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kotlin Toolchain

Use this skill for JetBrains Kotlin Toolchain work: declarative YAML build configuration, the kotlin CLI, product types, dependency wiring, multiplatform layout, publishing, and local build plugins.

Do not apply this skill to Gradle or Maven build editing unless the task is explicitly about converting a Maven project to Kotlin Toolchain. Kotlin Toolchain is not Gradle, not Maven, and not the old Amper *.amper syntax.

Source Snapshot

This skill is generated from the official upstream docs for v0.12.0, the default supported version:

  • Repository: https://github.com/JetBrains/kotlin-toolchain
  • Ref: v0.12.0
  • SHA: 2039c5371bf5812f0061b2b11b6581b4e9de3a97
  • Full aggregate: generation/upstream-docs-v0.12.0.md
  • Generation notes: generation/generation-steps.md

Statements here come from those docs, from the v0.12.0 release notes, and from spot-checks against the tagged source tree. Where the docs lag the code, this skill follows the code and says so.

At v0.12.0 release time the upstream main docs matched this tag except for one line, so there is no separate main/dev snapshot. Older guidance for v0.11.x is kept in SKILL-0.11.md for projects still pinned there. Do not mix the two: the // path notation, nested templates, and KMP publishing all changed in 0.12.

The project is Alpha and the docs move quickly. Treat defaults and edge-case syntax as version-sensitive. When precision matters, inspect the local project, run ./kotlin show ..., and grep the pinned aggregate (~300 KB — search it, do not read it whole).

Internal names still contain Amper in expected places: jvm/amper-plugin, org.jetbrains.amper.plugins, and some distribution paths. Do not rename those to kotlin. The YouTrack project, however, moved from AMPER to KTC.

Reference Map

SKILL.md carries the operational base. Load a reference only when the task goes past it.

Reference Load it for
references/cli.md CLI commands and flags, wrapper install, provisioning, cache dirs, JDK provisioning
references/project-model.md project.yaml, module.yaml keys, path notation, module layout
references/product-types.md Per-product-type detail: entry points, build output, packaging limits
references/dependencies.md Dependency notation, scopes, classifiers, catalogs, repositories
references/settings.md Full settings tree, defaults table, compiler knobs
references/builtin-tech.md Compose, serialization, Ktor, Spring, RPC, DataFrame, Power Assert, KSP, Lombok, Parcelize
references/multiplatform.md Platform hierarchy, aliases, propagation, cinterop
references/templates.md Nested templates, precedence, merging, conflict resolution
references/publishing.md JVM and KMP publishing, Maven Central, mavenLocal, signing
references/plugins.md Authoring jvm/amper-plugin modules, plugin.yaml, task actions
references/maven-migration.md convert-project, mavenPlugins, migration gaps
references/migrating-0.11-to-0.12.md What breaks when a project moves from 0.11.x to 0.12.0
references/known-issues.md Tracked defects and workarounds — check before diagnosing odd behavior
references/codex-sandbox-caches.md Running the toolchain in a Codex workspace-write sandbox

Read the full file on GitHub · 395 lines

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. 2d ago First seen · 395 lines · 148 tokens per session scan A 3d32f901c92e

Subscribe to this mod's changes

kotlin-toolchain is a skill published in the GitHub repository Heapy/kortex (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 148 tokens to every session and 5,504 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

mobile-experience-report

Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.

respira-press/agent-skills-wordpress · 58 tokens

motherduck-design-dive

Design or redesign a MotherDuck Dive as a responsive, reusable analytics interface. Use when a Dive must be mobile-friendly from the start, support light and dark modes, reserve space for filters, use restrained Power BI-style information design, embed small charts inside metric components, or work across customers…

motherduckdb/agent-skills · 69 tokens

add-native

Public entry point for native device capabilities and native controls — camera, image picker, barcode/QR scanner, document picker, file picker, secure storage, file system, sharing, PDF generation/viewing, pen/signature capture, background GPS/geolocation tracking, or supported local file workflows — in a Power Apps…

microsoft/power-platform-skills · 96 tokens

compose-side-effects

Use when writing or reviewing Jetpack Compose code with LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, snapshotFlow, snackbar, navigation, focus requests, analytics, or event Flow collection. Technique-layer skill — complements the codebase-specific compose-expert.

vitorpamplona/amethyst · 62 tokens

preview-screens

Use when the user wants to preview generated screens in a browser without starting Metro / a simulator — for example after /create-mobile-app finishes or after /edit-app regenerates a screen.

microsoft/power-platform-skills · 41 tokens

sceneview

Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…

sceneview/sceneview · 156 tokens