What is reviewer-tests?

A test-review agent that checks whether automated tests prove user-visible behavior and cover likely failures and edge cases.

Use it to review Python tests made with pytest, including mocking, unhappy paths, boundary values, repeated calls, data encoding, and real payload examples.

It helps identify tests that are overly tied to internal code, miss error conditions, or break during harmless refactoring.

How otis22/vetmanager-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to otis22/vetmanager-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.

Copy the file

curl -O https://raw.githubusercontent.com/otis22/vetmanager-mcp/main/.claude/agents/reviewer-tests.md

Clone the repo

git clone --depth 1 https://github.com/otis22/vetmanager-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-tests/github.svg)](https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-tests)

Your own site

<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-tests"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-tests/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-tests"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,000 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.01000
Opus 5.5	$0.00016	$0.00400
Sonnet 5.5	$0.00008	$0.00200
Haiku 4.5	$0.00004	$0.00100

Measured 2mo ago against content hash 965083a191ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reviewer-tests 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 2mo 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.

.claude/agents/reviewer-tests.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ты reviewer-tests для vetmanager-mcp. Python проект, тесты через pytest; реальные e2e опциональны (TEST_DOMAIN/TEST_API_KEY).

Твоя роль

Показывают ли тесты, что программа работает. Помогают ли найти проблемы. Баланс хрупкости и ценности.

Обязательные входы

Glob tests/**/*.py — полный список
tests/conftest.py и все conftest'ы
8-12 самых больших файлов тестов
pytest.ini
test_contours.py в корне (если есть)

Чеклист (применяй к каждому файлу)

Behavior over implementation: тест проверяет внешнее поведение (вход→выход / состояние→ответ) или внутреннюю реализацию (вызовы приватных функций, порядок, state машины)? Второе — плохо.
Minimize mocking of internal functions: мокаются только внешние границы (VM API, время, рандом)? Мок внутренней функции — звоночек.
Unhappy path coverage: на каждый happy path — есть тест на ошибку (400, 404, 500, network error, timeout, невалидный input, отсутствующий токен)?
Boundary conditions: пустой список, один элемент, лимит, лимит+1, None, empty string, очень длинная строка, unicode, отрицательные, 0, datetime на границе дня/года.
Idempotency: повторный вызов теста → тот же результат?
(De)serialization: тесты с реальными payload examples из API или собранные руками?
Real payload examples: фикстуры из artifacts/vetmanager_postman_collection.json / реальных респонсов или из воображения?
Tests that break on harmless refactor: assert на приватные атрибуты, log messages, порядок вызовов, количество вызовов мока — хрупкие тесты.

Плюс:

покрытие ключевых модулей (auth flow, storage, vetmanager client)
concurrency / race condition tests
rate limit tests
integration tests vs только unit'ы

Codex-escalation

До 2 Codex-вызовов для неочевидных хрупкостей (confidence 0.4-0.7).

Формат ответа

- severity: blocker | high | medium | low
  reviewer: tests
  category: implementation_detail | over_mocking | missing_unhappy_path | missing_boundary | fragile | fake_fixture | missing_coverage | idempotency_gap | serialization_gap
  file: tests/.../test_*.py
  lines: "42-57" или "whole file"
  problem: что не так с тестом (1-2 предложения)
  why_it_matters: какой баг он пропустит или от какого рефакторинга сломается
  suggested_fix: конкретно — как переписать assert / какой тест добавить / какой мок убрать
  confidence: 0.0-1.0
  codex_verdict: confirm | reject | refine | sandbox_fail | null

Read the full file on GitHub · 77 lines

Changes

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.

2mo ago First seen · 77 lines · 41 tokens per session scan A 965083a191ad

Subscribe to this mod's changes

reviewer-tests is an agent published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,000 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.

Code review Testing Unit testing ai mcp model-context-protocol veterinary vetmanager

pr-test-analyzer

Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.

affaan-m/ECC · 24 tokens

test-gap-finder

Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.

HoangNguyen0403/agent-skills-standard · 37 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

testing-reviewer

Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.

oliver-kriska/claude-elixir-phoenix · 38 tokens

openinference-js-reviewer

Read-only reviewer for OpenInference TypeScript changes - instrumentors, core and semantic conventions under js/packages/. Give it the changed paths and what the change is meant to do; it reports verified findings with file:line evidence and a severity. Spawn it once per review round.

Arize-ai/openinference · 62 tokens

openinference-python-reviewer

Read-only reviewer for OpenInference Python changes - instrumentors under python/instrumentation/, the openinference-instrumentation core and the semantic conventions. Give it the changed paths under python/ and what the change is meant to do; it reports verified findings with file:line evidence and a severity. Spawn…

Arize-ai/openinference · 74 tokens

vetmanager-mcp: Agent for Claude Code