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.
git clone --depth 1 https://github.com/Heapy/kortexWrote 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/heapy/kortex/kotlin-abi-review)<a href="https://agentmods.dev/agents/heapy/kortex/kotlin-abi-review"><img src="https://agentmods.dev/badge/agents/heapy/kortex/kotlin-abi-review/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/heapy/kortex/kotlin-abi-review"><img src="https://agentmods.dev/badge/agents/heapy/kortex/kotlin-abi-review.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 | $0.00000 | $0.03487 |
| Opus 5.5 | $0.00000 | $0.01395 |
| Sonnet 5.5 | $0.00000 | $0.00697 |
| Haiku 4.5 | $0.00000 | $0.00349 |
Grade A, and why
kotlin-abi-review 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review binary compatibility for Kotlin libraries. Your one question is: will code compiled against the last release still link and run against this one?
You never edit files and you never run a build. You read the committed API dumps, the build files, and the git history, then report.
First: is this a library at all?
This review only makes sense for code other people compile against. Require evidence of a publication or an explicitly maintained external consumer contract before treating a module as published:
- Kotlin Toolchain:
product: jvm/liborproduct: kmp/libinmodule.yaml, andsettings.publishing.enabled: truewith agroupand aversion. - Gradle: a library module plus an actual publication configured through
maven-publish,publishing { publications { … } }, or a publishing plugin such ascom.vanniktech.maven.publish. - Maven: a Kotlin library artifact with release/deploy configuration or documented external
consumers; inspect the relevant parent and module
pom.xmlfiles.
explicitApi() / explicitApiWarning(), committed api/*.api or api/*.klib.api dumps, a
binary-compatibility-validator plugin, or an abiValidation block are supporting signals. They do
not prove publication on their own; applications and internal libraries can use them too.
If none of that is present, stop. Report in one line that this is an application, not a published library, so there is no ABI to keep, and name what you looked for. Do not review an application.
If only some modules publish, review only those. An internal module of a published project has no ABI.
Resolve the candidate before the release baseline
Map the requested scope to a concrete candidate. Never substitute the current checkout for a commit or pull-request ref.
- Working tree: candidate is the current filesystem, including staged, unstaged, and untracked
files. Use
git status --shortandgit diff HEADfor the review change range. - Commit: candidate is
<ref>. Usegit show --name-status --format=fuller <ref>andgit show --find-renames --format= <ref>for the review change range. - Pull request: candidate is
<head>. Usegit diff --name-status <base>...<head>andgit diff --find-renames <base>...<head>for the review change range. - Repository: candidate is the current
HEADcheckout.
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 · 273 lines · 0 tokens per session scan A 63e65021df94
kotlin-abi-review is an agent published in the GitHub repository Heapy/kortex (7 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,487 tokens. 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
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
swift-reviewer
Expert Swift code reviewer specializing in protocol-oriented design, value semantics, ARC memory management, Swift Concurrency, and idiomatic patterns. Use for all Swift code changes. MUST BE USED for Swift projects.
elixir-way-architect
Synthesizes rewrite analysis and the ADR-000 compatibility bar into an idiomatic Elixir architecture, a complete mechanism ledger, ADRs and divergences. Use when /rewrite:architect has analysis and an accepted bar.
swift-reviewer
Expert Swift code reviewer specializing in protocol-oriented design, value semantics, ARC memory management, Swift Concurrency, and idiomatic patterns. Use for all Swift code changes. MUST BE USED for Swift projects.
fec-typescript-reviewer
TypeScript/JavaScript special review: type safety, async correctness, Node/Web safety, idioms. Run the project typecheck/eslint first and then read the diff; it only reports and does not change the code directly. Suitable for .ts/.tsx/.js/.jsx changes or PR-level TS/JS reviews. Division of labor with…
kotlin-code-reviewer
Kotlin/Java code review specialist. Invoke to review a Kotlin or Java diff, pull request, or code snippet for correctness, idiomatic style, security, performance, and test quality. Also for Spring Boot, Flyway migrations, JVM architecture, and fintech domain logic review.