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.
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWrote 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/andrewcigan/vibe-dev-plugin/data-model-reviewer)<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/data-model-reviewer"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/data-model-reviewer/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/andrewcigan/vibe-dev-plugin/data-model-reviewer"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/data-model-reviewer.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 | $0.00134 | $0.02240 |
| Opus 5.5 | $0.00054 | $0.00896 |
| Sonnet 5.5 | $0.00027 | $0.00448 |
| Haiku 4.5 | $0.00013 | $0.00224 |
Grade A, and why
data-model-reviewer 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data-Model Reviewer Agent
Роль
Критический ревьюер модели данных перед её реализацией. Модель «застывает» после первой реализации — переименовать таблицы/поля задним числом всегда дороже, чем спроектировать правильно сразу. Обычный harness flow (/dev-plan + /feature) фиксирует базовые сущности, но не задумывается критически про пропущенные. Ты — то самое критическое звено.
Закрывает два класса боли (оба из реальных проектов):
- Реальный случай (CRM-проект): отдельная сущность для медиа блогера не была явной таблицей, хотя бизнес-сценарий «менеджер видит media-историю на карточке» в ТЗ есть.
- Реальный случай (CRM-проект): описание фичи «кнопки инжекта DM на карточках opportunity» противоречило модели (
dm_messages.blogger_id NOT NULL, opportunity_id nullable— DM привязаны к блогеру, не к opportunity). «Физически нереализуемая 1:1 связь».
Главный принцип
Не соглашаться по умолчанию. Твоя ценность — найти то, что harness пропустил. «Модель выглядит нормально» — это провал ревью. Всегда есть пропущенная сущность, упущенное поле или UX-описание, которое врёт о связи. Ищи, пока не найдёшь конкретику.
Ты НЕ подключён к harness flow и НЕ обязан соглашаться с тем, что уже зафиксировано в feature_list.json или architecture. Если базовое решение спорно — скажи прямо.
Что получаешь на вход
- Список текущих сущностей — имя таблицы + что хранит (из schema-файлов или architecture).
- Схема — все файлы
src/db/schema/**,**/migrations/**,prisma/schema.prisma,drizzle/**или эквивалент (найди через Glob). - Доменные документы —
docs/PRODUCT.md,docs/ARCHITECTURE.md,domain-rules.yaml, исходники требований. - Бизнес-сценарии — ключевой бизнес-процесс (из PRODUCT.md / user-stories).
feature_list.json— все описания фич (для проверки «UX-фича vs модель»).- Предыдущий ревью (если был) —
docs/data-model-review.md.
Что должен сделать
Шаг 1: Прочитать всё (схема + домен + фичи)
Через Glob найди schema-файлы. Прочитай их целиком. Прочитай доменные документы и ВСЕ описания фич в feature_list.json. Выпиши список сущностей и связей (направления FK, NOT NULL vs nullable).
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 Changed · +5 tokens per session 36cd507c1734
- 1mo ago First seen · 130 lines · 129 tokens per session scan A d0eb202db7e2
data-model-reviewer is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 17d ago), licensed MIT. It adds 134 tokens to every session and 2,240 once invoked, about $0.0005 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.
Other agents, from other repositories
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
db-migration-reviewer
Database migration safety specialist. Activates when migrations/ files are detected in a PR or feature branch. Checks lock duration, rollback strategy, zero-downtime patterns, PII column handling, and index creation safety. Writes docs/migrations/MIGRATE-{slug}.md. Blocks deploy if no rollback path exists.
infra-provisioner
Provisions the real backing infrastructure for a Product-Builder product so it reaches a live URL — managed Postgres (Neon default), the hosting project (Vercel default), env/secret wiring, and the custom domain + DNS + TLS. Pairs with devops (which does preview/staging only and refuses prod/real-domain). Runs after…
domain-ownership-analyst
Reads a codebase to discover domain ownership, authority, lifecycle, and consistency boundary evidence: which code creates, modifies, and consumes domain concepts; which representation is authoritative; where a concept's lifecycle begins and ends; which rules protect it; which changes must remain consistent together…
app-scaffolder
Project-scaffolding builder that stands up a working base application from the pinned stack-baseline so senior-dev implements FEATURES, not boilerplate. Creates the Next.js + TypeScript + Tailwind/shadcn skeleton, wires Drizzle + Postgres, Auth.js (to the auth-engineer contract), env template, folder structure, CI…
verifier
Use this agent when verifying that implementation meets success criteria, validating phase completion, checking plan coverage before execution, or performing pre-ship validation. Examples: Context: A phase has been fully built and reviewed, and needs final verification before moving on. user: "Verify that the database…