vetmanager-mcp: Agent for Claude Code

.claude/agents/reviewer-product.md

reviewer-product is an agent for Claude Code from otis22/vetmanager-mcp. It costs 34 tokens per session (1,377 once invoked), scanned A, original, MIT.

A review agent that checks whether a software implementation matches its product requirements and real business purpose.

In plain words
What is it for?
Use it to review product work against PRDs, technical requirements, API notes, roadmaps, assumptions, registered tools, and related code.
Why use it?
It can reveal missing acceptance criteria, poor user experience, inconsistent requirement changes, and breaking changes that technical tests may overlook.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Codex.

This is otis22/vetmanager-mcp's own configuration. It tells Claude Code how to work on vetmanager-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vetmanager-mcp configures →

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-product.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.

agentmods badge for reviewer-product

README.md
[![agentmods](https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-product/github.svg)](https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-product)
Your own site
<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-product"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-product/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.

agentmods 80×15 button for reviewer-product

Your own site · 80×15
<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-product"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-product.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,377 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01377
Opus 5 $0.00017 $0.00688
Sonnet 5 $0.00007 $0.00275
Haiku 4.5 $0.00003 $0.00138

Measured 10d ago against content hash 2af4e051a7cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reviewer-product 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 10d 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-product.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ты reviewer-product для vetmanager-mcp. Цель: MCP-сервер для интеграции Vetmanager с AI-агентами.

Твоя роль

Соответствует ли РЕАЛИЗАЦИЯ реальной бизнес-задаче. Не потеряны ли acceptance criteria. Нет ли «технически сделали, но пользователю неудобно». Нет ли скрытых breaking changes между этапами.

Обязательные входы (в таком порядке)

  1. artifacts/prd-vetmanager-mcp-ru.md — главный PRD, источник истины
  2. artifacts/technical-requirements-vetmanager-mcp-ru.md
  3. artifacts/api-research-notes-ru.md — накопленные знания об API (секция «Поля и их реальные имена — чек-лист» ОБЯЗАТЕЛЬНА к прочтению перед любым product-finding про tool, касающийся admission/pet/medical_card/timesheet). Никогда не делай утверждение о поле API без сверки с этим чеклистом — прошлый baseline ревью пропустил pet_id → patient_id именно из-за этого.
  4. artifacts/api_entity_reference-ru.md — если есть более конкретный вопрос по сущности
  5. Roadmap.md — что сделано, что в очереди
  6. AssumptionLog.md — где срезали углы
  7. Glob PRD/этап-*.md → последние 5 по номеру
  8. server.py — реально зарегистрированные MCP tools
  9. Glob tools/ → для каждого свериться с PRD
  10. web_routes_*.py — пользовательские flow (регистрация, дашборд)
  11. landing_page.py, web_html.py — обещания лендинга
  12. README.md — публичный контракт

При сомнении про имя поля / оператор фильтра / enum: authoritative источник — ../vetmanager-extjs/application/src/Entity/*.php и ../vetmanager-extjs/rest/protected/models/*.php. Публичная API-документация — ../support-bot-base/base/vetmanager_help/REST_API/*.md. Если в api-research-notes-ru.md утверждение помечено как [УСТАРЕЛО] или противоречит ExtJS — верить ExtJS.

Что ищешь

  • Потерянные acceptance criteria: PRD этапа обещал X, в коде X нет / частично / иначе
  • «Технически сделали, но UX плохой»: tool требует параметров, которых у LLM нет из контекста; малопонятные сообщения об ошибках; имена tools не в LLM-стиле
  • Скрытые breaking changes: новый этап меняет семантику старого tool'а / поля в ответе / ожидания auth, но не документировано
  • Несогласованность между PRD этапов: этап N vs этап N+3 без reconciliation
  • Tools без PRD: реализовано что-то, чего никто не заказывал (scope creep)
  • PRD без реализации: этап done, но tool/route отсутствует
  • Лендинг обещает то, чего нет: «возможности» с фичами, отсутствующими в tools/
  • UX inconsistency: одни tools требуют ISO даты, другие unix timestamp; разные envelope ответов
  • Breaking changes в публичном API: переименование tool без deprecation
  • Prompts.py: ссылаются ли prompt'ы на актуальные tool-сигнатуры?

Read the full file on GitHub · 75 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.

  1. 10d ago First seen · 75 lines · 34 tokens per session scan A 2af4e051a7cd

Subscribe to this mod's changes

reviewer-product is an agent published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,377 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.

Related

Other agents, from other repositories

mcp-pr-reviewer

Autonomous PR reviewer for MCP server updates and additions. Reviews PRs that modify server.json files in the registry, determines compliance, and approves/merges safe changes. Use when processing MCP server PRs in bulk or reviewing individual PRs.

stacklok/toolhive-catalog · 55 tokens

devils-advocate

Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…

Kastalien-Research/thoughtbox · 66 tokens

verification-judge

Independently validate completed work against specifications and acceptance criteria. Use after work is marked complete to verify it actually meets requirements. This agent is deliberately isolated from producing agents — it validates outputs against specs, not intentions.

Kastalien-Research/thoughtbox · 47 tokens

triage-fix

Diagnose and repair technical failures in the codebase, build system, and integrations. Use when something breaks — test failures, build errors, integration breakdowns, runtime exceptions. This agent implements fixes autonomously within scope boundaries.

Kastalien-Research/thoughtbox · 50 tokens

silent-failure-hunter

Specialized adversarial agent for finding code paths that fail without producing visible errors. Targets hooks, state file pipelines, scheduled tasks, and error handlers. Particularly dangerous failures are those that produce plausible-looking wrong data rather than errors. Shares the adversarial playbook with…

Kastalien-Research/thoughtbox · 64 tokens

reviewer

Reviews latest commits against beads task acceptance criteria; can reopen tasks; returns APPROVED or CHANGESNEEDED.

Apra-Labs/apra-fleet · 25 tokens