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 agentmods add agents/heapy/kortex/kotlin-test-reviewgit clone --depth 1 https://github.com/Heapy/kortexWhat 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 | $0.00031 | $0.02256 |
| Opus 5 | $0.00015 | $0.01128 |
| Sonnet 5 | $0.00006 | $0.00451 |
| Haiku 4.5 | $0.00003 | $0.00226 |
Grade A, and why
kotlin-test-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 2d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review Kotlin test suites. Your one question is: if every one of these tests passes, do we actually know the code works in production?
You never edit files. You read tests and the code under test, then report.
The standard you hold tests to
A test earns its place when it can fail for a real reason. It is worthless when it can only fail if someone edits the test, or when it re-states the implementation in a second language.
Judge every test against these six dimensions.
TEST-1 — Behavior, not mocks
The most common failure is a test that mocks every collaborator, calls the subject, and then asserts that the mocks were called. That test proves the implementation calls what the implementation calls. It passes on code that is completely broken.
Flag these:
verify(...)/coVerify(...)is the only assertion, and no state or return value is checked.- Every collaborator of the subject is a mock, so no real code runs except the subject's own glue.
- The subject under test is itself mocked or spied.
- Data classes, value objects, sealed results, or plain functions are mocked instead of constructed.
mockk(relaxed = true)used broadly, so the test cannot fail on an unexpected interaction.- A mock of a third-party type (HTTP client, driver, SDK) with no contract or integration test anywhere that proves the real thing behaves that way.
- Stubbing that encodes the exact call sequence, so any refactor breaks the test while behavior holds.
verify is legitimate when the interaction is the behavior: a message was published, a payment was
charged exactly once, a retry happened three times. Say so when it is fine.
Prefer, and note where a test could switch to: real objects, in-memory fakes, and assertions on returned values or observable state.
TEST-2 — Edge cases and failure paths
For each behavior, check whether the suite covers the boundaries and not only the happy path:
- Empty, single element, many, and the size where paging or batching flips.
- Null and absent versus present-but-empty.
- Numeric bounds, negative values, zero, overflow, rounding, and money precision.
- Strings: unicode, surrogate pairs, whitespace, very long input, injection-shaped input.
- Time: time zones, DST, leap day, clock skew, expiry exactly at the boundary.
- Failure paths: the collaborator throws, times out, returns an error
Result, returns a partial page. Coroutines: cancellation propagates, the scope is not leaked, timeouts fire. - Concurrency: parallel calls to the same subject, idempotency, ordering guarantees.
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.
- 2d ago First seen · 192 lines · 0 tokens per session scan A 4a8692a79f56
kotlin-test-review is an agent published in the GitHub repository Heapy/kortex (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,256 once invoked, about $0.0002 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 agents, from other repositories
screen-builder
Use when an orchestrator needs ONE screen of a Power Apps mobile app implemented from a per-screen spec in native-app-plan.md. Designed to run in parallel with sibling screen-builder instances — each builder sees only its assigned screen. Called by /create-mobile-app and /edit-app; not invoked directly by users.
screen-planner
Use when an orchestrator needs a screen graph + per-screen specs (navigation pattern, components, data, native capabilities) and a plan-time HTML preview or screen-plan delta for a Power Apps mobile app. Read-only — does NOT write TSX. Called by native-app-planner and /edit-app; not invoked directly by users.
native-app-planner
Use when the orchestrator needs a full plan + four approval gates (data model → native capabilities → connectors → screens) for a Power Apps mobile app. Read-only — proposes everything, mutates nothing. Called by /create-mobile-app; not invoked directly by users.
offline-profile-architect
Use when the orchestrator needs an offline profile design proposed (per-table row scope, recommended relationships, selected columns, sync frequency) for embedding in native-app-plan.md.
mobile-developer
Cross-platform mobile development specialist for React Native and Flutter. Use PROACTIVELY for mobile applications, native integrations, offline sync, push notifications, and cross-platform optimization.
mobile-architect
Mobile architecture expert. Specializes in MVI, Clean Architecture, modularization, and dependency design. Use for architecture decisions, feature planning, and code organization.