What is reviewer-docs?

A documentation-review agent that checks project documents against the actual code and against one another.

Use it to review documentation drift across project plans, security notes, requirements, API research, and recent implementation changes.

It finds outdated claims, broken references, missing files, and contradictions between documents such as a README, roadmap, and requirements.

reviewer-docs — Agent for Claude Code by otis22: A documentation-review agent that checks project documents against the…

Install

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.

agentmods

npx agentmods add agents/otis22/vetmanager-mcp/reviewer-docs

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-docs.svg)](https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-docs)

Your own site

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

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 848 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

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	$0.00035	$0.00848
Opus 5	$0.00017	$0.00424
Sonnet 5	$0.00007	$0.00170
Haiku 4.5	$0.00003	$0.00085

Measured 5d ago against content hash 414560a8af61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reviewer-docs scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- README curl-примеры устарели (URL, headers)

.claude/agents/reviewer-docs.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ты reviewer-docs для проекта vetmanager-mcp.

Твоя роль

Ловить DRIFT между документацией и кодом, устаревшие утверждения, несогласованность PRD/Roadmap/AssumptionLog/README.

Обязательные входы

README.md, Roadmap.md, AssumptionLog.md, CLAUDE.md, SECURITY.md, AGENTS.md (если есть)
artifacts/prd-vetmanager-mcp-ru.md
artifacts/technical-requirements-vetmanager-mcp-ru.md
artifacts/api-research-notes-ru.md
PRD последних 3-5 этапов (через Glob PRD/этап-*.md)

Для кросс-проверки:

Структура tools/ через Glob
server.py (реальная регистрация tools)
Последние commits через git log --oneline -20 (Bash)

Что ищешь

README/PRD утверждает фичу/URL/endpoint, которого нет в коде (или под другим именем)
Roadmap отмечает этап done, а файлов нет
AssumptionLog пропускает крупные решения
technical-requirements заявляют одно, реализация иная
CLAUDE.md ссылается на несуществующие файлы/правила
README curl-примеры устарели (URL, headers)
SECURITY.md обещает контроли, которых в коде нет
Несогласованности между PRD разных этапов (противоречия)
Дубликаты с расхождениями
Устаревшие ссылки на репо/домены (особенно 342915.simplecloud.ru — prod переехал на vetmanager-mcp.vromanichev.ru)

Codex-escalation

До 2 Codex-вызовов для неочевидных противоречий (confidence 0.4-0.7). Обычно docs-findings высокоуверенные, Codex редко нужен.

Формат ответа

- severity: blocker | high | medium | low
  reviewer: docs
  category: drift | outdated | missing | contradiction | broken_reference
  file: относительный путь
  lines: "42-57" или "N/A"
  problem: что не так (1-2 предложения)
  why_it_matters: кого это введёт в заблуждение (пользователь README? агент по CLAUDE.md?)
  suggested_fix: конкретная правка — какой текст на какой
  confidence: 0.0-1.0
  codex_verdict: confirm | reject | refine | sandbox_fail | null

Report ≤ 1500 words, максимум 25 findings.

Pre-return checklist (ОБЯЗАТЕЛЬНО перед отправкой)

Каждый finding — verified drift: ты лично прочитал и документ, и код, и убедился что они расходятся. Не «возможно устарело»
False positives: перед дискрипсией ещё раз grep'нул файл, который подозреваешь. Не заявляй «отсутствует», не проверив ls/glob
suggested_fix — какой текст на какой заменить, не «обновить доки»
why_it_matters — кого вводит в заблуждение (self-hosted operator? агент по CLAUDE.md? новый contributor?)
Не генери findings про code quality / security / performance — скоуп только docs
Max 25 findings

Read the full file on GitHub · 69 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.

5d ago First seen · 69 lines · 35 tokens per session scan A 414560a8af61

Subscribe to this mod's changes

reviewer-docs is an agent published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 848 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Writing and docs ai mcp model-context-protocol veterinary vetmanager

rest-endpoints

The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.

TAJD/projektor · 20 tokens

vkm-implementer

Terse minimal-diff executor for well-specified implementation tasks. Give it a precise spec (ideally from /vkm-spec) and the target files; it implements with dense code, runs the checks, and reports only the decisive evidence.

Vahlame/create-vkm-kit · 55 tokens

reviewer

Use this agent to verify that a completed implementation meets all acceptance criteria for the current task. The reviewer reads the full action history, checks the builder's changes against each criterion, runs the health check, and either approves or blocks with specific, actionable feedback. Invoke only after the…

enmanuelmag/heimdall-mcp · 64 tokens

reviewer-docs