Row-Bot is a local-first desktop AI assistant that combines language models with memory and tools for working across files, repositories, workflows, and communication channels. It is intended for people who want an assistant that can run locally while keeping application data on their machine.
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.
npx agentmods add skills/siddsachar/row-bot/meeting_notesnpx skills add siddsachar/row-bot --skill meeting_notesgit clone --depth 1 https://github.com/siddsachar/row-botWrote 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/skills/siddsachar/row-bot/meeting_notes)<a href="https://agentmods.dev/skills/siddsachar/row-bot/meeting_notes"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/meeting_notes.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 | $0.00014 | $0.00451 |
| Opus 5 | $0.00007 | $0.00226 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
meeting_notes 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 5d 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
When the user shares meeting notes, asks you to summarise a meeting, or says they just finished a meeting, follow these steps:
- Parse the Input — Read through the raw notes, transcript, or description the user provides.
- Identify Participants — List everyone mentioned or involved.
- Structure the Minutes — Organise into:
- Meeting Title & Date
- Attendees
- Key Discussion Points — Summarise each topic discussed in 1–2 sentences
- Decisions Made — Bullet list of any decisions reached
- Action Items — For each action item, capture:
- What needs to be done
- Who is responsible
- When it's due (if mentioned)
- Save to Knowledge Graph — Store action items, decisions, and key facts to memory. Save participants as
personentities if they don't already exist — they'll auto-link in the knowledge graph and appear in the wiki, making them searchable across all future meetings. Use descriptive subjects likeTeam Standup Actions — March 28. Link action items to the people responsible. - Schedule Follow-ups — If any follow-up meetings were mentioned, offer to create calendar events.
- Present — Output the structured minutes in a clean, skimmable format.
Keep the language professional but concise. The goal is to turn messy notes into something the user can share with their team.
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.
- 5d ago First seen · 50 lines · 14 tokens per session scan A 31b4be6e8c08
meeting_notes is a skill published in the GitHub repository siddsachar/row-bot (1,487 stars, last pushed 7d ago), licensed Apache-2.0. It adds 14 tokens to every session and 451 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 2026-08-30.
Other skills, from other repositories
telegram-userbot
Подключение и работа с личным Telegram-аккаунтом владельца (userbot, НЕ бот). Используй, когда просят читать личные чаты/переписку/диалоги, искать по своим сообщениям, писать кому-то от своего имени, «зайди в мой телеграм», «подключи мой телеграм», «прочитай личку», «ответь в личке», «перешли сообщение», а также при…
notes-summary
회의록·미팅 노트·회의 기록을 읽고 정리한다. 사용자가 회의록 정리, 회의 내용 정리, 회의 기록 정리를 요청하면 사용한다.
design-team-meeting-structure
Use when a team's meetings feel like the wrong type of conversation for the decisions being made, when meetings are too frequent or too infrequent, or when team members feel their time is wasted — to design the right meeting types, cadences, and facilitation practices for how the team actually works.
email-assistant
Разбор входящей почты (Яндекс, Gmail) из чата: список писем, чтение по uid, классификация и структурированный отчёт. Триггер — «какие письма», «разбери почту», «что нового на почте».
scheduler
Планирование регулярных задач по расписанию. Триггер — «напоминай мне каждый день», «проверяй почту по будням в 9 утра», «каждый час делай сводку», «запланируй задачу».
mail-digest
Description: Сводка по почте: вызывает emaillist, запускает stats.py для детерминированного подсчёта, интерпретирует результат.