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/newbot)<a href="https://agentmods.dev/commands/stereosam/stereo-vibe-public/newbot"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/newbot/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/newbot"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/newbot.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 | $0.00974 |
| Opus 5 | $0.00000 | $0.00487 |
| Sonnet 5 | $0.00000 | $0.00195 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade B, and why
newbot scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Токен нового бота — СЕКРЕТ. Он лежит в `/path/to/bots/<assistant-bot>/managed/<username>.token` (chmod 600). В синканутую память (`claude_memory`) НЕ писать. В вывод stdout токен не печатать. How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Создать новый Telegram-бот через work_bot (Bot Management API). Без ручного BotFather.
Аргумент $ARGUMENTS = <Имя бота> | <username> (username ОБЯЗАН кончаться на bot).
Пример: /newbot Stereo Disk Sync | stereo_disk_bot
Если аргумент не передан — спроси имя и username.
Что уже готово (не пересоздавать)
- Менеджер: @stereo_work_bot (id 8628356043),
can_manage_bots=true. Токен в/path/to/bots/<assistant-bot>/.env(TELEGRAM_TOKEN), владелец —OWNER_CHAT_ID. - Движок:
/path/to/bots/<assistant-bot>/tools/newbot.py(делает весь флоу).
Шаги выполнения
- Запусти движок В ФОНЕ (он сам стопает work-bot на время поллинга и потом рестартит):
Запускать черезssh <user>@<your-server> '/path/to/bots/<assistant-bot>/venv/bin/python /path/to/bots/<assistant-bot>/tools/newbot.py --name "<Имя>" --username <username>'run_in_background: true(поллинг до 5 мин). - Сразу скажи пользователю: «В Telegram от @stereo_work_bot пришла ссылка — нажми её и подтверди создание бота». Без его тапа бот не создастся.
- Дождись завершения фонового процесса. Успех = строка
[OK] бот @<username> создан. Токен сохранён -> /path/to/bots/<assistant-bot>/managed/<username>.token. - Если
[FAIL]— смотри причину в выводе:- «ссылку не нажали» → попроси нажать, перезапусти движок.
- «поле не совпало» (RAW managed_bot keys) → структура апдейта отличается; поправь извлечение токена/параметр
getManagedBotTokenв движке по показанным ключам.
Безопасность (КРИТИЧНО)
- Токен нового бота — СЕКРЕТ. Он лежит в
/path/to/bots/<assistant-bot>/managed/<username>.token(chmod 600). В синканутую память (claude_memory) НЕ писать. В вывод stdout токен не печатать. - work-bot во время поллинга недоступен ~до 5 мин (нужен эксклюзивный getUpdates) — это норма, движок его сам поднимает в
finally.
Рецепт под капотом (на случай отладки)
Bot API Bot Management: deep-link https://t.me/newbot/<manager>/<suggested>?name=<name> → владелец подтверждает → прилетает update.managed_bot (ManagedBotUpdated, поля user+bot) + сервисный ManagedBotCreated → токен забирается методом getManagedBotToken (параметр — id нового бота).
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 · 43 lines · 0 tokens per session scan B 41bb24f64ec9
newbot is a command published in the GitHub repository stereosam/stereo-vibe-public (1 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 974 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
planificar-tecnico
Generar blueprint técnico desde una especificación Gherkin.
go-stack.inertia.setup
Instructions to setup the go-stack Inertia.js integration for fullstack Go applications, including boot provider wiring and frontend workflow.
sparc-supabase-admin
🔐 Supabase Admin - You are the Supabase database, authentication, and storage specialist. You design and implement d...
sparc-mcp
♾️ MCP Integration - You are the MCP (Management Control Panel) integration specialist responsible for connecting to a...
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.