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/status)<a href="https://agentmods.dev/commands/alifanov/ai-garage-launch/status"><img src="https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/status/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.
<a href="https://agentmods.dev/commands/alifanov/ai-garage-launch/status"><img src="https://agentmods.dev/badge/commands/alifanov/ai-garage-launch/status.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00387 |
| Opus 5 | $0.00013 | $0.00193 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
status 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.
What it actually says
/garage:status — где мы в пайплайне
Что сделать
- Прочитай
docs/STATE.md. Если его нет — пайплайн ещё не начат, скажи запустить/garage:start. - Пройди по папке
docs/и сверь: для каждого шага проверь, есть ли соответствующий артефакт (docs/01-ideas.md,02-validation.md,03-channel.md,04-product.md,05-build.md,06-deploy.md,07-infra.md,08-analytics.md,09-launch.md,10-metrics.md,11-payments.md). Если файл есть, а галочки в STATE нет (или наоборот) — синхронизируйdocs/STATE.md. - Выведи компактный чек-лист: ✅ сделано / ⬜ осталось, плюс поля Продукт / Донор / Канал.
- В конце — какую команду запускать следующей (первый невыполненный шаг пайплайна).
Формат вывода
Продукт: <…> Донор: <…> Канал: <…>
✅ 1. start идеи → docs/01-ideas.md
✅ 2. validate валидация → docs/02-validation.md
⬜ 3. channel канал трафика
⬜ 4. spec бриф
…
➡️ Следующий шаг: /garage:channel
Ничего не меняй в проекте, кроме синхронизации docs/STATE.md при рассинхроне.
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.
- 9d ago First seen · 29 lines · 25 tokens per session scan A 71439f0a7b3a
status 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 387 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.
status
Show current Heimdall state — project phase, active agents, quality gates, conflicts.
sprint-plan
Starts a new sprint. Rolls over unfinished items from the prior sprint, recommends which ready backlog items to pull in (velocity, epic focus, age), and proposes a sprint goal for confirmation. The sprint-entry gate of the turnstile workflow.
breakdown
Decomposes an epic into user stories, or an oversized story into tasks. Proposes a breakdown for explicit approval, then writes child design docs and backlog entries. Gate 1a-b of the turnstile workflow.
drop
Cancels a ticket. Sets status dropped with a recorded reason, keeping the item visible as history instead of hand-deleting YAML.
park
Stashes the in-progress ticket so urgent unrelated work can start: status parked, a resume note (current state, next step, blockers) written into the item note. /turnstile:pickup offers to un-park it later.