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.
git 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/launch)<a href="https://agentmods.dev/commands/alifanov/ai-garage-launch/launch"><img src="https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/launch.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 | $0.00019 | $0.00410 |
| Opus 5 | $0.00010 | $0.00205 |
| Sonnet 5 | $0.00004 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
launch 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 7d 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:launch — запускаем канал
Цель — первые посетители в аналитике. Один канал, первый реальный шаг.
Предусловия
Прочитай docs/03-channel.md (выбран канал) и docs/08-analytics.md (аналитика стоит). Нет канала — скажи запустить /garage:channel.
Что сделать
По выбранному каналу (скилл traffic-channels) сделай первый шаг:
- Google Ads (бюджет от $50) — создать кампанию: 5–10 длинных запросов с явным намерением купить (не широкие фразы). Можно через скилл
ads-funnel/ Meta Ads MCP для Meta. - Meta Ads — 5–10 коротких видео по 15 сек, первая секунда цепляет.
- Соцсети (есть аудитория) — пост о запуске: что сделал, зачем, ссылка на сайт (X / LinkedIn / Telegram).
- SEO (время, нет бюджета) — первая статья под ключевой запрос; заготовка 10 страниц по формуле «AI для Y» (скиллы
seo-audit,content-strategy).
Обязательно: ссылки с UTM-метками, чтобы канал был виден в аналитике.
Артефакт
Запиши в docs/09-launch.md: канал, что именно запущено (кампания/пост/статья), UTM-ссылки, дата, где смотреть первые данные. Обнови docs/STATE.md: шаг 9 [x].
➡️ Дальше
Дай трафику накопиться, затем /garage:metrics — разбор воронки и юнит-экономики.
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.
- 7d ago First seen · 31 lines · 19 tokens per session scan A 5dedad590fd4
launch is a command published in the GitHub repository alifanov/ai-garage-launch (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 410 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
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
code-review
Multi-model code review — AI models independently review code, then converge on findings.
plan-review
Multi-model plan review — AI models independently plan, then converge on the best approach.
review
Multi-model review — AI models independently review any document or general topic, then converge on findings.
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
autonomy
Set Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto) — how much the agent does before asking. Use with a number, +/- to cycle, or no argument to show current.