spec

spec is a command for Claude Code from alifanov/ai-garage-launch. It costs 25 tokens per session (413 once invoked), scanned A, original, MIT.

A command that collects the basic product brief before coding: the target user, their problem, one feature, its value, possible names, and landing-page copy.

In plain words
What is it for?
Use it during early product planning to create a brief in the project documents and prepare for scaffolding a Next.js application. It requires an identified feature source or a prior validation step.
Why use it?
It makes the team decide who the product is for and what single problem it addresses before building an application.

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 Use it during early product planning to create a brief in the project documents and prepare for scaffolding a Next.js application. It requires an identified feature source or a prior validation step.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/alifanov/ai-garage-launch/spec"><img src="https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 413 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 $0.00025 $0.00413
Opus 5 $0.00013 $0.00206
Sonnet 5 $0.00005 $0.00083
Haiku 4.5 $0.00003 $0.00041

Measured 8d ago against content hash bf0d0a7364ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec 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 8d 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/spec.md · 31 lines

What it actually says

/garage:spec — продуктовый бриф

Перед кодом отвечаем на два вопроса: кто пользователь и что у него болит. И берём у донора ровно одну фичу.

Предусловия

Прочитай docs/STATE.md, docs/02-validation.md, docs/03-channel.md. Нет донора — скажи запустить /garage:validate.

Что сделать

Собери бриф (спрашивай пользователя там, где не хватает данных):

  1. ЦА — конкретный человек, не «все» и не «малый бизнес». Например: фрилансер, теряющий клиентов; SaaS-founder, которому некогда писать тексты.
  2. Боль — за что он готов платить, чтобы проблема исчезла.
  3. Одна фича — та самая, что взяли у донора (из docs/02-validation.md). Всё остальное — потом.
  4. Ценностное предложение — одно предложение: для <ЦА>, который <боль>, продукт делает <результат>.
  5. Название + домен-кандидаты — 3–5 вариантов (проверку доменов сделаем на деплое).
  6. Экран лендинга — заголовок, подзаголовок, CTA.

Артефакт

Запиши бриф в docs/04-product.md (это главный документ — на него опираются все команды сборки). Обнови docs/STATE.md: поле Продукт = название, шаг 4 [x].

➡️ Дальше

/garage:scaffold — создать Next.js приложение с лендингом на основе брифа.

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. 8d ago First seen · 31 lines · 0 tokens per session scan A bf0d0a7364ca

Subscribe to this mod's changes

spec is a command published in the GitHub repository alifanov/ai-garage-launch (2 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 413 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.