db-auth

db-auth is a command for Claude Code from alifanov/ai-garage-launch. It costs 21 tokens per session (393 once invoked), scanned A, original, MIT.

A deployment command for connecting a web app to Neon, a hosted PostgreSQL database, and Clerk, a service for user sign-in and account management.

In plain words
What is it for?
Adding Neon and Clerk to a deployed app, enabling passwordless or Google sign-in, protecting routes, and recording the infrastructure setup.
Why use it?
It documents the database and login setup, including environment variables and protected routes, without committing secret keys.

Command for Claude Code

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

Part of the garage plugin — 4 skills, 12 commands, 2 agents shipped together

Good fit Adding Neon and Clerk to a deployed app, enabling passwordless or Google sign-in, protecting routes, and recording the infrastructure setup.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alifanov/ai-garage-launch/db-auth
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.

Clone the repo
git clone --depth 1 https://github.com/alifanov/ai-garage-launch

Made for: Claude Code.

Or install garage, the plugin that ships this one along with the rest of its 4 skills, 12 commands, 2 agents.

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 db-auth

README.md
[![agentmods](https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/db-auth/github.svg)](https://agentmods.dev/commands/alifanov/ai-garage-launch/db-auth)
Your own site
<a href="https://agentmods.dev/commands/alifanov/ai-garage-launch/db-auth"><img src="https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/db-auth/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 db-auth

Your own site · 80×15
<a href="https://agentmods.dev/commands/alifanov/ai-garage-launch/db-auth"><img src="https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/db-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 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 $0.00021 $0.00393
Opus 5 $0.00010 $0.00197
Sonnet 5 $0.00004 $0.00079
Haiku 4.5 $0.00002 $0.00039

Measured 9d ago against content hash 62414c396a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

db-auth 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 9d 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.

commands/db-auth.md · 28 lines

What it actually says

/garage:db-auth — база и авторизация

Предусловия

Прочитай docs/06-deploy.md (сайт задеплоен). Нет — скажи запустить /garage:deploy.

Что сделать

Опирайся на скилл stack-reference. Работа с секретами — не коммить ключи, клади в env (локально .env.local, в проде — Vercel env vars).

  1. Neon (БД) — создать базу на neon.tech (бесплатный тир), скопировать DATABASE_URL, добавить в Vercel: Settings → Environment Variables. Локально — в .env.local.
  2. Clerk (авторизация) — готовый сервис: UI-компоненты, пользователи и сессии из коробки. Поддерживает Magic Link / OTP и Google OAuth (самый конвертящий вход). Поставить пакет, добавить ключи Clerk в env, обернуть приложение провайдером, закрыть нужные роуты.
  3. Проверить: регистрация/логин работают на боевом URL, пользователь появляется в дашборде Clerk.

Google OAuth требует свой домен (из шага deploy) в настройках OAuth-консоли.

Артефакт

Запиши в docs/07-infra.md: какие env-переменные заведены (имена, БЕЗ значений), способы входа, что защищено авторизацией. Обнови docs/STATE.md: шаг 7 [x].

➡️ Дальше

/garage:analytics — поставить аналитику и разметить воронку visitors → users → buyers.

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. 9d ago First seen · 28 lines · 21 tokens per session scan A 62414c396a6c

Subscribe to this mod's changes

db-auth is a command published in the GitHub repository alifanov/ai-garage-launch (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 393 once invoked, about $0.0001 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.