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.
npx skills add tmj-90/gaffer --skill kotlin-conventionsgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/skills/tmj-90/gaffer/kotlin-conventions)<a href="https://agentmods.dev/skills/tmj-90/gaffer/kotlin-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/kotlin-conventions/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/skills/tmj-90/gaffer/kotlin-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/kotlin-conventions.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 | $0.00115 | $0.02011 |
| Opus 5.5 | $0.00046 | $0.00804 |
| Sonnet 5.5 | $0.00023 | $0.00402 |
| Haiku 4.5 | $0.00012 | $0.00201 |
Grade A, and why
kotlin-conventions 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 16d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write idiomatic Kotlin
Kotlin's value is safety made concise: nullability in the type, immutability by default, structured concurrency that cannot leak. For the builder and the reviewer of a Kotlin diff; the module's config and existing code win over it.
Procedure
- Discover the module's conventions first. Call
search_lorefor Kotlin conventions. Readbuild.gradle.kts,gradle/libs.versions.toml(Kotlin, coroutines, AGP versions),jvmToolchain, whetherexplicitApi()is on,.editorconfig(ktlint readsktlint_code_styleand rule toggles there),detekt.ymland its baseline, and Androidlint.xml. Identify Android vs server vs multiplatform, the DI framework (Hilt/Koin/Spring), how dispatchers are injected, and the state pattern (MVVM/MVI withStateFlow, or a service layer). Copy a sibling class and its test. - Pin the exact commands from CI (the
run-testsandrun-lintskills). Use the defaults below only when the repo defines none; never add to a detekt baseline to pass. - Write the change with the idioms below, then walk the concurrency section for every coroutine, flow, shared value and resource you touched.
- Test each acceptance criterion's own behaviour. One test per AC that fails without
your change, plus its error path, using
runTestwith the test dispatcher and Turbine for flows. If the AC involves shared state or persistence, add a test that launches N concurrent coroutines on a multi-threaded dispatcher (Dispatchers.Default) and asserts the invariant. - Verify, then stop. Done when: ktlint and detekt are clean at the repo's config, the
compiler reports no new warnings where
allWarningsAsErrorsis set, tests are green, and every AC has a test. Record the output with therecord-evidenceskill; the runner submits the work.
Commands
- All checks:
./gradlew check(runs tests plus wired-in linters). - Style:
./gradlew ktlintCheck(ktlint Gradle plugin) orktlint "src/**/*.kt";./gradlew detekt. - Tests:
./gradlew test; one class:./gradlew test --tests 'pkg.ClassTest'. - Android:
./gradlew lint testDebugUnitTest(or the repo's variant). - Dependencies: a new or bumped entry in
libs.versions.tomlor the build file is a blocker (thedependency-upgradeskill).
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.
- 16d ago Changed · +47 lines · +10 tokens per session c97e9229bd3f
- 19d ago First seen · 74 lines · 105 tokens per session scan A c4488aab8abe
kotlin-conventions is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,011 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 2026-09-28.
Other skills, from other repositories
sota-jvm
State-of-the-art JVM engineering rules for Java and Kotlin that Claude applies when writing or auditing JVM code. Java LTS releases (virtual threads final since 21; structured concurrency still preview), modern Kotlin. Covers modern idioms (records, sealed types, pattern matching, Kotlin null-safety/coroutines)…
sota-swift
State-of-the-art Swift engineering rules (Swift 6 language mode) that Claude applies when writing or auditing Swift on ANY target — server-side services (Vapor, Hummingbird, SwiftNIO), CLIs, libraries, packages and apps. Covers optionals and error handling, value types and API design, Swift 6 data-race safety…
maven-gradle-guide
Maven and Gradle build tool patterns including pom.xml structure, build.gradle.kts configuration, multi-module projects, dependency management, plugins, and BOMs. Use when the user is setting up Java/Kotlin build configurations, managing dependencies, creating multi-module projects, or troubleshooting build issues.…
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
android-development
Android development guidelines for Kotlin with clean architecture, MVI pattern, Material Design, and best practices for building robust mobile applications.
kotlin-patterns
Kotlin: coroutines, Flow, sealed/data classes, null safety, Ktor, Compose, KMP. Triggers: Kotlin, coroutine, Flow, suspend, Ktor, Jetpack Compose, KMP, kotlinx.