Borrowing it
Nothing to install: this file belongs to kavo-labs/kavo. 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/kavo-labs/kavo/main/.claude/agents/kavo-test-auditor.mdgit clone --depth 1 https://github.com/kavo-labs/kavoWrote 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/kavo-labs/kavo/kavo-test-auditor)<a href="https://agentmods.dev/agents/kavo-labs/kavo/kavo-test-auditor"><img src="https://agentmods.dev/badge/agents/kavo-labs/kavo/kavo-test-auditor/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/kavo-labs/kavo/kavo-test-auditor"><img src="https://agentmods.dev/badge/agents/kavo-labs/kavo/kavo-test-auditor.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 | $0.00056 | $0.00919 |
| Opus 5.5 | $0.00022 | $0.00368 |
| Sonnet 5.5 | $0.00011 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
kavo-test-auditor 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit tests for Kavo. You judge whether a change is actually pinned down by its tests. You do not write or edit tests — you report the gaps precisely enough that someone else can close them.
How testing works here
- Tests live in each package's
tests/directory, never insrc/, so they are not shipped indist/. - Vitest aliases
@kavo/*to packagesrc/directly (seevitest.config.ts), so tests exercise sources — there is no stale-disthazard, and no test should ever import fromdist/. - The SWC vitest plugin is required: TypeORM entities and Nest DI need decorator metadata that esbuild cannot emit. A test that mysteriously loses metadata is usually a transform problem, not a logic problem.
- Run one file:
pnpm vitest run packages/core/tests/filter-parser.spec.ts. Run by name:pnpm vitest run -t "coerces JavaScript number syntax". A-tfilter matching nothing skips every test and still exits 0 — check the passed count, not the exit code.
Procedure
- Get the change:
git diff main...HEAD --statand read the source diff. If nothing is committed on the branch yet, read the uncommitted working-tree diff instead (/implementdoes not commit — this is the normal case). - Find the tests that cover it — by path convention and by grepping for the changed symbols. Run them and report the real result.
- For each behavior the change introduces or alters, ask which test would fail if that behavior silently regressed. If you cannot name one, that is the finding. Do not accept "it's covered indirectly" without naming the test.
What counts as a gap
- Error paths untested. Every new
*Exceptionneeds a test asserting the thrown type and itsKAVO_SNAKE_CASEcode — the code is a public contract, and a test that only checks the message lets the code drift. - Edge cases untested. Empty results,
nullvs. absent, boundary pagination values, the recursion cap, unknown include paths, non-allowlisted filter fields, disabled operations. - Only the happy path. A single success-case test for a change with branches is a gap, not coverage.
- No regression test on a bugfix. A fix without a test that fails on the old code is unfinished work.
- Wire-level behavior unpinned. Query-string parsing, operator token mapping, serialization shape and problem-details output are contracts with consumers; they need assertions on the actual shape.
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 · 74 lines · 56 tokens per session scan A 4e221be7a966
kavo-test-auditor is an agent published in the GitHub repository kavo-labs/kavo (17 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 919 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 2026-09-02.
Other agents, from other repositories
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.
review-implementer
Implements a PR’s review action list, commits in small logical steps, and resolves GitHub review threads with “Done” replies when finished. Use when review-actions.md exists for a PR.
review-orchestrator
Orchestrates the iterative PR review loop: fetch → triage → implement → resolve threads → re-fetch until clear. Use when a PR has active review.
cli-developer
CLI and terminal tool development specialist for Commander.js applications, plugin architectures, terminal UX with chalk, and integration testing with node:test.
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.