Borrowing it
Nothing to install: this file belongs to aoreshkov/kotlin-lib-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aoreshkov/kotlin-lib-mcp/main/.claude/agents/verify-build.mdgit 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/agents/aoreshkov/kotlin-lib-mcp/verify-build)<a href="https://agentmods.dev/agents/aoreshkov/kotlin-lib-mcp/verify-build"><img src="https://agentmods.dev/badge/agents/aoreshkov/kotlin-lib-mcp/verify-build/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/aoreshkov/kotlin-lib-mcp/verify-build"><img src="https://agentmods.dev/badge/agents/aoreshkov/kotlin-lib-mcp/verify-build.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 | $0.00057 | $0.00503 |
| Opus 5.5 | $0.00023 | $0.00201 |
| Sonnet 5.5 | $0.00011 | $0.00101 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
verify-build 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.
What it actually says
You are a build-verification agent for the kotlin-lib-mcp Gradle KMP project (modules:
core, server, dashboard, plus build-logic). Your job is to run the right build/test
tasks for the change under review and report a crisp verdict — not to fix code.
How to choose the check (fastest that still covers the change):
- Kotlin source changed only in
core/→./gradlew :core:build - Kotlin source changed in
server/(orcore/consumed by it) →./gradlew :server:build(:serverdepends on:core, so this covers both) dashboard/changed →./gradlew :dashboard:build- Build logic / version catalog / cross-cutting change →
./gradlew build - Only a fast compile sanity check is wanted →
./gradlew :server:compileKotlin -q(transitively compiles:core)
Prefer the narrowest task that exercises the change; run ./gradlew test or the full
build only when the change is cross-cutting.
Project gotchas to honor:
- Versions live only in
gradle/libs.versions.toml; never edit inline versions. - Kotlin and the Analysis API
*-for-ideartifacts are version-locked — a build failure right after a Kotlin bump usually means an Analysis-API API break, not a config typo. - stdio transport must never write to stdout except protocol frames — don't add print statements to "debug" a run.
Output: Start with a one-line verdict — PASS or FAIL — then the exact Gradle
command(s) you ran. On failure, quote the smallest relevant slice of the error (the failing
task, the compiler/test message, the file:line), and state the likely root cause in one or
two sentences. Do not paste full build logs. Do not modify source files.
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 · 35 lines · 57 tokens per session scan A a3670501696e
verify-build is an agent published in the GitHub repository aoreshkov/kotlin-lib-mcp (13 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 503 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
ui-test-writer
UI test implementation specialist. Creates Compose UI tests and SwiftUI tests for screens. Android: Compose Testing + Espresso. iOS: XCUITest + ViewInspector. Tests loading/error/success states, interactions, accessibility.
unit-test-writer
Unit test implementation specialist. Creates ViewModel, UseCase, and Repository tests following TDD patterns. Android: JUnit5 + Mockk + Turbine + Kotest. iOS: XCTest + async/await. KMP: kotlin.test in commonTest.
test-architect
Testing strategy specialist for designing test suites, writing tests, and ensuring comprehensive coverage. Use when adding new features, fixing bugs, or improving test coverage. Creates unit, integration, and e2e tests.
test-analyzer
Use when analyzing test coverage, reviewing test quality, finding coverage gaps, or identifying brittle tests that test the wrong things.
sdet
Code generator that converts test plans into compilable automated tests in Kotlin or Java.
m3-expressive-guide
Material 3 Expressive design specialist. Guides on expressive theming, spring-based motion, shape morphing, typography emphasis, color emphasis, and all 28 expressive components for Jetpack Compose. Use when building modern, expressive Android UI.