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/stereosam/stereo-vibe-publicWrote 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/stereosam/stereo-vibe-public/fleet)<a href="https://agentmods.dev/commands/stereosam/stereo-vibe-public/fleet"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/fleet/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/stereosam/stereo-vibe-public/fleet"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/fleet.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 | $0.00000 | $0.01815 |
| Opus 5 | $0.00000 | $0.00907 |
| Sonnet 5 | $0.00000 | $0.00363 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
fleet scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Метрика/визиты/цели: токен «Claude Metrika» в `reference_api_integrations.md`, счётчик 109706407, `curl -H "Authorization: OAuth <t>" https://api-metrika.yandex.net/stat/v1/data?ids=109706407&...`. Цели: 566797911 down How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Работа с Fleet Board (дашборд парка). Аргумент: $ARGUMENTS
Fleet Board — карта и как добавлять плитки
Где: <home>\fleet_board\ (домашний ПК , ВНЕ синка YandexDisk).
ПРАВИЛО: читать файл ПОЛНОСТЬЮ перед правкой; делать бэкап *.bak.<ts>_<что>.
Архитектура
- Окно-виджет:
run_widget.py(pywebview/WebView2) грузитwidget.html(GridStack). Запуск:pythonw run_widget.py(Python312, НЕ venv). ИконкаFleet Widget.lnk. Один экземпляр — mutexFleetWidgetSingleton. - Данные (2 сборщика, пишут рядом, виджет читает через инжект
<script>— обход file:// CORS):status_collector.py(30с, автозапускFleetCollector.vbs) →status.json+status.js(window.__STATUS__). Сервисы ПК + ОДИН ssh к VPS (vps_all(): сервисы/диск/аптайм/туннели/ошибки/скачивания disk-sync) + Я.Диск-квота + диск C + корзина.hw_sampler.py(3с,FleetHW.vbs) →hw.js(window.__HW__): CPU/RAM (psutil) + GPU/темпа/VRAM (nvidia-smi) + сеть + VPN.
- Раскладка:
layout.json(позиции). Нет записи для плитки → autoPosition (свободное место); ручной drag → persist в layout.json. - Автозапуск (Startup .vbs): FleetWidget + FleetCollector + FleetHW.
РЕЦЕПТ: добавить плитку «X»
- Данные в
status_collector.py:- VPS-метрика → дописать
echo "KEY $(...)"вcmdвнутриvps_all()(там уже DISK/UP/TUN/ERR/DL*); добавить ветку парсингаelif p[0]=="KEY":→res[...]; вresinit добавить ключ; в финальныйdata={...}добавить"x": v.get("x"). - ПК-метрика → отдельная функция + положить в
data. - Кавычки в ssh-cmd: строки Python одинарные
'...', bash-двойные"..."внутри литералом (в т.ч. вложенные"..."/$(...)в$()— bash ок). СНАЧАЛА протестировать команду живымssh <user>@<your-server> '...', потом вшивать.
- VPS-метрика → дописать
- widget.html — 4 точки:
buildTiles():add('x',w,h);addHideCtx('x');(w,h ×2 внутри add — сетка 12 кол.).draw()(вif(d){...}):if(d.x)set('x',valTile('',big,sub,'Лейбл'));— данные изd.x.valTile(ic,big,sub,lbl)— ic игнор; иконка эмодзи в big/lbl илиicon('name')+....TILE_GROUPS: добавить'x'в группу (для меню ➕).TILE_NAMES:x:'Имя плитки'(подпись).
- layout.json (опц.): позиция, иначе autoPosition + перетащить.
- Применить:
cd <home>\fleet_board && python status_collector.py(обновит status.js данными). Проверить:python -c "import json,io;print(json.load(io.open(r'<home>\fleet_board\status.json',encoding='utf-8')).get('x'))".- Перезапустить виджет (он кэширует widget.html): убить
pythonw run_widget.py+ ВСЕmsedgewebview2(иначе зомби лочат .wvdata), затемStart-Process pythonw run_widget.py -WorkingDirectory <home>\fleet_board.
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.
- 8d ago First seen · 63 lines · 0 tokens per session scan A 1e9f0d004e11
fleet is a command published in the GitHub repository stereosam/stereo-vibe-public (1 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,815 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
maker-setup
Onboard a Code-with-Claude Makers Cardputer — fetch the build-with-claude repo, flash firmware, and install the Claude Buddy apps.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
amp-register
Register your agent with an external AMP provider for cross-provider messaging.
rvcsi-calibrate
Learn a v0 per-subcarrier baseline (mean amplitude) from a .rvcsi capture.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).
gaai-audit
Show workspace audit log with filters and optional JSON export.