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 skmtc/skmtc --skill skmtc-lang-kotlingit clone --depth 1 https://github.com/skmtc/skmtcWrote 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/skmtc/skmtc/skmtc-lang-kotlin)<a href="https://agentmods.dev/skills/skmtc/skmtc/skmtc-lang-kotlin"><img src="https://agentmods.dev/badge/skills/skmtc/skmtc/skmtc-lang-kotlin/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/skmtc/skmtc/skmtc-lang-kotlin"><img src="https://agentmods.dev/badge/skills/skmtc/skmtc/skmtc-lang-kotlin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00117 | $0.04420 |
| Opus 5.5 | $0.00047 | $0.01768 |
| Sonnet 5.5 | $0.00023 | $0.00884 |
| Haiku 4.5 | $0.00012 | $0.00442 |
Grade A, and why
skmtc-lang-kotlin 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Kotlin layer (@skmtc/lang-kotlin)
Read skmtc-generator first.
Drift warning. The API of record is the workspace
skmtc/deno/lang-kotlinand its tests. The shippedgen-kotlin-*generators predate the 0.9.11 flattening: they callnew KtAnnotation('Name', [args])positionally and importisKtAnnotated/isKtSupertyped(no longer exported; supertype clauses now render inline in the value). Clone their structure only; take call shapes from THIS skill's example (§8), which is pinned byte-for-byte against the engine bylang-kotlin/src/skill-example.test.ts.
1. Declaring the language
Same pattern as TypeScript — the import graph declares it. Two
factories: toKtModelProjectionBase, toKtOasOperationProjectionBase;
snippets extend KtSnippet.
export const KtModelBase = toKtModelProjectionBase<EnrichmentSchema>({
id: denoJson.name,
toEnrichmentSchema,
toIdentifierName({ refName, enrichments }) {
return enrichments?.subject?.name ?? capitalize(camelCase(refName))
},
// Kotlin's identifier KIND depends on schema shape → may read context
// (runs only on cache-miss; the NAME stays pure):
toIdentifierType(refName, context) {
return { type: toShape(context, peekSchema(context, refName)) }
},
toExportPath({ refName, enrichments }) {
const name = enrichments?.subject?.name ?? capitalize(camelCase(refName))
return `@/${enrichments.generator.basePackage.replaceAll('.', '/')}/${name}.generated.kt`
}
})
The export path's directory segments ARE the Kotlin package (§4). Make
basePackage a required generator-scope enrichment with no default;
validate segments with isKtIdentifierName + ktHardKeywords. Put the
shape dispatch (object+props → data-class; string+enums →
enum-class; qualifying discriminated union → sealed-interface; else
typealias) in ONE deterministic function read by both
toIdentifierType and the constructor, so kind and value can't disagree.
2. Register shapes — Kotlin differences
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed c8debf12e5f9
- 2mo ago First seen · 353 lines · 117 tokens per session scan A eb92930aee17
skmtc-lang-kotlin is a skill published in the GitHub repository skmtc/skmtc (19 stars, last pushed 6d ago), licensed Apache-2.0. It adds 117 tokens to every session and 4,420 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 2026-08-30.
skmtc-lang-kotlin compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skmtc-lang-kotlinskmtc/skmtc | Skill | 19 | 6d ago | Apache-2.0 | A | 117 | Claude Code |
| lathelathe-cli/lathe | Skill | 87 | yesterday | Apache-2.0 | A | 39 | Claude Code, Codex |
| ocli-apiEvilFreelancer/openapi-to-cli | Skill | 267 | 1mo ago | MIT | A | 38 | Claude Code |
| api-documentation-generatorcuriositech/windags-skills | Skill | 18 | 6d ago | none | A | 129 | Claude Code |
| orvalorval-labs/orval | Skill | 6.6k | yesterday | MIT | A | 83 | Claude Code, Codex |
| configkubb-labs/kubb | Skill | 1.8k | yesterday | MIT | A | 49 | Claude Code |
| outputkubb-labs/kubb | Skill | 1.8k | yesterday | MIT | A | 35 | Claude Code |