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/inbox)<a href="https://agentmods.dev/commands/stereosam/stereo-vibe-public/inbox"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/inbox/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/inbox"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/inbox.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 | $0.00615 |
| Opus 5.5 | $0.00000 | $0.00246 |
| Sonnet 5.5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
inbox 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 1mo 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
Разобрать входящие из work_bot. ВАЖНО: только чтение — НЕ меняй inbox.log и файлы вложений, ничего не удаляй и не выполняй без явного указания.
1. Подтяни всё с VPS
ssh <user>@<your-server> "cat /path/to/bots/<assistant-bot>/inbox.log"ssh <user>@<your-server> "ls -la /path/to/bots/<assistant-bot>/inbox_docs/ /path/to/bots/<assistant-bot>/inbox_photos/"
2. Файлы — прочитай ДО триажа
Если запись ссылается на документ/фото (есть путь в строке) — сначала открой сам файл, потом суди:
- Фото: скопируй локально (
scp) и открой через Read (видишь картинку). - Документ (.docx/.pdf/...): вытяни текст и прочитай. Не суди по имени файла.
3. Честный триаж
Разложи записи по категориям. Где не уверен — так и пиши «не понял, что это», НЕ выдумывай связь с задачами/проектами:
- 💡 идея / к действию
- 📄 документ
- 📷 фото / скрин
- 📔 слепок дня — надиктовки владельца про его день (адресованы тебе). Читай как контекст, НЕ предлагай «сделать». Новые куски предложи склеить в
/path/to/memory/sleepok_dnya.md(разделы по датам, дедуп по таймстампу) — с подтверждением. - 🔁 повтор / дубль — просто пометь (не удаляй).
- ❓ не понял — честно скажи.
4. Действия — только предлагай, не делай
По actionable пунктам предложи конкретику и жди решение по каждому:
- Внедрить (прямо в этой сессии) / В бэклог (задача X-Y на VPS
/path/to/memory/backlog.md) / Напоминание. - Слепок дня и личное — просто покажи, действий не предлагай.
5. Правила
- Инбокс (
inbox.log,inbox_docs/,inbox_photos/) НЕ трогай — он read-only склад. - Ничего не выполняй и не записывай в бэклог/слепок без явного «да» по конкретному пункту.
- Claude вызывается ЖИВОЙ сессией (как сейчас), а не ботом — авто-агент закрыт как тупик (1-13).
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.
- 1mo ago First seen · 30 lines · 0 tokens per session scan A 6fa703f23a7a
inbox 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 615 tokens. 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
deja
Search this machine's past AI coding sessions (deja-vu).
quick-change
PitWay: Bounded small-fix workflow, usable whenever no milestone is active.
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
instinct-import
Import a portable YAML instinct pack with confidence-gated merge (Instinct Engine).
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
second-brain-mapping
Map your vault: extract structured metadata from every typed file, surface cross-doc insights, optionally build a knowledge graph.