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.
npx agentmods add commands/alifanov/ai-garage-launch/deploygit clone --depth 1 https://github.com/alifanov/ai-garage-launchWrote 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/commands/alifanov/ai-garage-launch/deploy)<a href="https://agentmods.dev/commands/alifanov/ai-garage-launch/deploy"><img src="https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/deploy.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00388 |
| Opus 5 | $0.00014 | $0.00194 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
deploy 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.
What it actually says
/garage:deploy — сайт в интернете
Предусловия
Прочитай docs/05-build.md (приложение создано). Нет — скажи запустить /garage:scaffold.
Что сделать
Опирайся на скилл stack-reference. Действия необратимые и внешние — сначала показывай план и спрашивай подтверждение, потом выполняй.
- GitHub — создать репозиторий (
gh repo create),git init, первый коммит, push. GitHub = источник истины и триггер автодеплоя. - Vercel — импортировать репозиторий (vercel.com → New Project → Import), Deploy. Дальше каждый
git pushв main = автодеплой. Сайт наyourapp.vercel.app. - Домен — проверить и купить свой домен (скилл
namecheap: проверка доступности + DNS; либо Cloudflare). Подключить в Vercel: Settings → Domains → Add. Свой домен нужен для доверия, Google OAuth и email-рассылок.
Проверь: сайт открывается по боевому URL, HTTPS активен.
Артефакт
Запиши в docs/06-deploy.md: ссылка на GitHub-репо, боевой URL (vercel + домен), заметки по DNS. Обнови docs/STATE.md: шаг 6 [x].
➡️ Дальше
/garage:db-auth — подключить Neon (БД) и Clerk (авторизацию).
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.
- 6d ago First seen · 28 lines · 28 tokens per session scan A db1900b5df05
deploy is a command published in the GitHub repository alifanov/ai-garage-launch (2 stars, last pushed 28d ago), licensed MIT. It adds 28 tokens to every session and 388 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.
Other commands, from other repositories
msd-build
Build the app using EAS — local build (no cloud queue) or EAS cloud. Tracks output binary path for direct submission.
setup
Set up terraform-ls LSP integration and install all Terraform tools required by the hooks in this project.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
scan
Scan AWS account for cost optimization.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.