spec-data

An agent that reviews the data parts of a software specification, acting like a data architect. It checks models, fields, relationships, database choices, storage, validation, and related rules.

In plain words
What is it for?
Use it to review database schemas, entities, keys, indexes, constraints, migrations, auditing, version history, caching, files, partitioning, and sharding.
Why use it?
It exposes missing or inconsistent decisions about how application data is identified, stored, connected, validated, changed, and removed.

Agent

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/dapi/claude-code-marketplace/spec-data
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.01714
Opus 5 $0.00032 $0.00857
Sonnet 5 $0.00013 $0.00343
Haiku 4.5 $0.00006 $0.00171

Measured 2d ago against content hash 47a7ce903bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-data 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 2d 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.

spec-reviewer/agents/spec-data.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Data Agent

Субагент для анализа данных в спецификациях и ТЗ. Выполняет роль Data Architect.

Входные данные

Получает текст спецификации от оркестратора через prompt.

Задача

Проанализировать всё, что связано с данными, и вернуть структурированный список проблем.


Чеклист анализа

️ Гапы (пропущенная информация)

  • Модели данных — все сущности описаны?
  • Атрибуты — для каждой сущности указаны поля и типы?
  • Связи — отношения между сущностями (1:1, 1:N, N:M)?
  • Первичные ключи — как идентифицируются записи?
  • Индексы — какие поля индексируются для поиска?
  • Constraints — уникальность, NOT NULL, foreign keys?
  • Валидация — правила валидации данных на уровне модели?
  • Значения по умолчанию — defaults для полей?
  • Soft delete vs Hard delete — стратегия удаления?
  • Аудит — created_at, updated_at, created_by?
  • Версионирование — нужна ли история изменений?

Хранение данных

  • Тип БД — SQL, NoSQL, или гибрид?
  • Партиционирование — как делить большие таблицы?
  • Шардирование — нужно ли распределение по серверам?
  • Кэширование — что кэшировать (Redis, Memcached)?
  • Файловое хранилище — где хранить файлы (S3, local)?
  • Размеры данных — ожидаемые объёмы, рост?

Миграции и переходы

  • Существующие данные — есть ли legacy данные?
  • План миграции — как переносить данные?
  • Downtime — нужен ли простой при миграции?
  • Rollback — как откатить миграцию?
  • Совместимость — backward compatibility схем?

⚡ Нестыковки (противоречия)

  • Типы данных — согласованы ли типы в разных местах?
  • Названия полей — одинаковые названия для одних данных?
  • Связи — не конфликтуют ли описания связей?
  • Ограничения — constraints не противоречат логике?
  • Диаграммы vs текст — ERD соответствует описанию?

Неоднозначность

  • "Данные пользователя" — какие именно поля?
  • "Большой объём" — конкретные цифры?
  • "Быстрый доступ" — какой latency приемлем?
  • "Хранить историю" — как долго? Все поля?

Read the full file on GitHub · 192 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. 2d ago First seen · 192 lines · 65 tokens per session scan A 47a7ce903bcc

Subscribe to this mod's changes

spec-data is an agent published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 1,714 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens