mfd

mfd is a skill for Claude Code from vmkteam/claude-plugins. It costs 99 tokens per session (2,349 once invoked), scanned A, original, MIT.

A Go code generator that reads XML descriptions of a PostgreSQL schema and creates models, repositories, services, and test helpers. It is used through project Makefile commands.

In plain words
What is it for?
Generating database models, repositories, test factories, and selected RPC or UI code after adding or changing PostgreSQL tables and fields.
Why use it?
It avoids repeatedly writing code that mirrors database tables and their relationships. Regenerating code keeps these parts aligned with the schema description.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vmkteam-developer plugin — 35 skills shipped together

Good fit Generating database models, repositories, test factories, and selected RPC or UI code after adding or changing PostgreSQL tables and fields.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vmkteam/claude-plugins/mfd
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.

Any agent
npx skills add vmkteam/claude-plugins --skill mfd
Clone the repo
git clone --depth 1 https://github.com/vmkteam/claude-plugins

Made for: Claude Code.

Or install vmkteam-developer, the plugin that ships this one along with the rest of its 35 skills.

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 mfd

README.md
[![agentmods](https://agentmods.dev/badge/skills/vmkteam/claude-plugins/mfd/github.svg)](https://agentmods.dev/skills/vmkteam/claude-plugins/mfd)
Your own site
<a href="https://agentmods.dev/skills/vmkteam/claude-plugins/mfd"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/mfd/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 mfd

Your own site · 80×15
<a href="https://agentmods.dev/skills/vmkteam/claude-plugins/mfd"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/mfd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,349 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 $0.00099 $0.02349
Opus 5.5 $0.00040 $0.00940
Sonnet 5.5 $0.00020 $0.00470
Haiku 4.5 $0.00010 $0.00235

Measured 6d ago against content hash fb149aea3132, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mfd 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 6d 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.

plugins/developer/skills/mfd/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MFD Generator

Upstream: https://github.com/vmkteam/mfd-generator

Генерирует Go-код (модели, репозитории, VT-сервисы) из XML-описания схемы PostgreSQL. Запускай через --help бинарника для полного списка флагов.

Makefile-цели (vmkteam-конвенция)

  • XML из БД: make mfd-xml, make mfd-vt-xml, make mfd-xml-lang
  • Go-код: make mfd-model, make mfd-repo NS=<ns>, make mfd-db-test
  • VT/UI: make mfd-vt-rpc NS=<ns>, make mfd-vt-template NS=<ns>
  • Финал: make generate (zenrpc + colgen)

Новая таблица

make mfd-xml && make mfd-model && make mfd-repo NS=<ns> && make mfd-db-test
make mfd-vt-xml && make mfd-vt-rpc NS=<ns> && make generate

mfd-xml на новой таблице спрашивает неймспейс интерактивно. Неинтерактивно — флаг -n (формат ns:t1,t2;ns2:t3; README генератора ошибочно пишет =, с ним флаг молча игнорируется — #73):

mfd-generator xml -c "$CONN" -m docs/model/<project>.mfd -t "t1,t2" -n "session:t1;journal:t2"

Изменение существующей

make mfd-xml && make mfd-model && make mfd-repo NS=<ns> && make mfd-db-test

Сначала примени миграцию к локальной БД (/pgmigrator): mfd-xml читает схему из базы.

Layout

  • docs/model/<project>.mfd — корневой MFD (PackageNames, TableMapping, GoPGVer)
  • docs/model/<namespace>.xml — per-namespace Entities/Attributes/Searches

Неймспейсы — по поддоменам

Таблицы делятся на неймспейсы так же, как домен на поддомены: вход и пользователи, основная работа, журнал, файлы — по 2–8 таблиц (gatesrv: common, user, project, alert). Один неймспейс на 20 таблиц даёт XRepo на сотни методов, и любой менеджер видит всё. Менеджер держит репозитории нужных неймспейсов; ручные методы — в <ns>_ext.go, общее — в common_ext.go.

Команда — с разбиением: -n "auth:users,tokens;work:tasks,sprints", а не -n "<project>:<все таблицы>". Уже свалено в один — разложи <ns>.xml по сущностям, поправь TableMapping в .mfd и перегенерируй make mfd-repo NS=… по каждому неймспейсу.

Read the full file on GitHub · 137 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. 6d ago Changed · +67 lines · +32 tokens per session fb149aea3132
  2. 1mo ago First seen · 70 lines · 67 tokens per session scan A 5220c82ae41f

Subscribe to this mod's changes

mfd is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 6d ago), licensed MIT. It adds 99 tokens to every session and 2,349 once invoked, about $0.0004 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.

Related

Other skills, from other repositories