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 aoreshkov/kotlin-lib-mcp --skill library-ground-truthgit clone --depth 1 https://github.com/aoreshkov/kotlin-lib-mcpWrote 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/aoreshkov/kotlin-lib-mcp/library-ground-truth)<a href="https://agentmods.dev/skills/aoreshkov/kotlin-lib-mcp/library-ground-truth"><img src="https://agentmods.dev/badge/skills/aoreshkov/kotlin-lib-mcp/library-ground-truth/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/aoreshkov/kotlin-lib-mcp/library-ground-truth"><img src="https://agentmods.dev/badge/skills/aoreshkov/kotlin-lib-mcp/library-ground-truth.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 | $0.00086 | $0.00859 |
| Opus 5 | $0.00043 | $0.00430 |
| Sonnet 5 | $0.00017 | $0.00172 |
| Haiku 4.5 | $0.00009 | $0.00086 |
Grade A, and why
library-ground-truth 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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library ground truth
Model memory of third-party JVM APIs is unreliable: names drift between versions, overloads are
invented, nullability and generics get lost. The kotlin-lib MCP server answers from the
published sources jar for the exact version the project depends on. Prefer it over recall.
1. Pin the coordinate first
Never guess the version. Read it from the project:
gradle/libs.versions.toml— version catalog ([libraries]/[versions])build.gradle.kts/build.gradle—implementation("group:artifact:version")pom.xml—<dependency>blocksgradle.lockfile/gradle/verification-metadata.xmlif present — these carry the resolved version, which is what actually ends up on the classpath
If the project pins no version, or you're evaluating a library it doesn't use yet, pass
group:artifact (or group:artifact:latest) and the server resolves the latest stable release.
2. Warm the cache
Call fetch_library with the coordinate once per library and version. It downloads, extracts
and analyzes the sources; every other tool then answers from the on-disk cache, offline and fast.
All other tools fail until it has run for that coordinate.
3. Ask the narrow question
| You need | Tool |
|---|---|
| What's in this library at all | list_packages |
| What's in this package | list_declarations (package, visibility, maxResults, offset) |
| The exact signature of one symbol | get_api_signature (fqName) |
What it does / params / @throws |
get_kdoc (fqName) |
| How it's actually implemented | get_source (fqName or path) |
| Where a thing is used or defined | search_source (query, regex) |
| What it drags onto the classpath | get_dependencies (depth 1–5) |
| Which versions exist / newest stable | list_versions, get_latest_version |
Start narrow. list_declarations on a large package is a wall of text; a search_source for the
concept, then get_api_signature on the two or three hits, is usually the cheaper path.
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.
- 9d ago First seen · 65 lines · 86 tokens per session scan A f4cfcedd2b90
library-ground-truth is a skill published in the GitHub repository aoreshkov/kotlin-lib-mcp (8 stars, last pushed 5d ago), licensed Apache-2.0. It adds 86 tokens to every session and 859 once invoked, about $0.0004 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.
Other skills, from other repositories
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
kotlin-control-flow
Use when writing or reviewing Kotlin branching and control flow: when expressions, guard conditions, sealed type exhaustiveness, smart casts, nullable branching, early returns, or replacing complex if/else chains.
release-kotlin-library
Use when preparing, publishing, or checking readiness for a new Kotlin library version in a repository using gradle-maven-publish-plugin, including release changelog reconciliation, API snapshots, and publication verification.
using-chrisbanes-skills
Use when debugging, benchmarking, or profiling leads into Kotlin or Jetpack Compose source before the cause is known, or when one task spans multiple Kotlin or Compose concerns, especially plain Kotlin Flow or navigation delivery plus sealed branching.
kotlin-concurrency-and-flow
Use when writing or reviewing Kotlin coroutine scope ownership, raw Thread or Executor work, init launches, non-suspending launch APIs, runBlocking, cancellation, StateFlow, SharedFlow, Channel, stateIn, SharingStarted, state updates, or one-shot events.