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 skills add siddsachar/row-bot --skill making_pagesgit 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/making_pages)<a href="https://agentmods.dev/skills/siddsachar/row-bot/making_pages"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/making_pages/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/skills/siddsachar/row-bot/making_pages"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/making_pages.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 | $0.00029 | $0.04993 |
| Opus 5.5 | $0.00012 | $0.01997 |
| Sonnet 5.5 | $0.00006 | $0.00999 |
| Haiku 4.5 | $0.00003 | $0.00499 |
Grade A, and why
making_pages 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Making a page
A page is one HTML document the person uses beside the chat. Make one with
page_create(title, html, data, libraries); keep it current with
page_update(page, data=…); see what they ticked or decided with
page_read(page).
Rules
- No network. Nothing loads from the internet: no CDN scripts, fonts,
images or fetch. Inline all CSS and JS. Images only as
data:URLs. - Data in
data, not in the HTML. The page reads it withrowbot.data(). Progress and fresh numbers go in withpage_update(page, data=…), so the HTML stays the same. - Use
libraries: ["rowbot-style"]so the page looks like Row-Bot in light and dark. Add"charts"for Chart.js 4 (window.Chart). - Plain words. Short sentences, sentence case, no ids or codes on screen.
- Phone width. It must work at 360 px: no fixed widths, tables in
.rb-table-wrap, buttons that wrap. - One primary action per page, at most. The person's Send to Row-Bot is outside the page, under it.
The bridge: window.rowbot
| Call | What it does |
|---|---|
rowbot.data() |
The JSON you attached (a copy). |
rowbot.state.get() |
The page's saved object ({} at first). |
rowbot.state.set(obj) |
Saves the whole object (up to 256 KB) with the chat, on every device. |
rowbot.decide(id, choice, note?, label?) |
Records the person's choice on one item; choice null clears it. label is the item's name in words. |
rowbot.decided() |
What the person chose, by id: {choice, note, label, sent}. |
rowbot.onDecided(fn) |
Called when a choice changes, or once they are sent. |
rowbot.theme() |
{mode: 'light' | 'dark', tokens}; tokens hold chart-series-1…6, chart-grid, chart-axis, text-muted… |
rowbot.onTheme(fn) |
Called when the person switches theme. |
Choices only gather: under the page the person sees how many and "Send to
Row-Bot". Their click sends you one message listing them, with a JSON list.
Choices you'll see in words: approve → Approved, change → Change,
skip → Skipped, pick → Picked, refresh → Refresh, submit → Filled in;
anything else as written. They never approve a tool call.
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.
- today First seen · 363 lines · 29 tokens per session scan A ea10255e1133
making_pages is a skill published in the GitHub repository siddsachar/row-bot (1,644 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 4,993 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-24.
Other skills, from other repositories
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
watch
A monitoring and briefing workflow that checks unread Telegram messages, email, failed checks, and failed scheduled units, then decides what needs the owner's attention. It can also explain actions such as creating a task, delaying a reminder, ignoring an item, or fixing a failure.
insight
A scheduled daily practice that looks for a repeated manual task, builds and tests a small tool for it, and suggests the result. It can instead report a development issue when the agent cannot solve its own problem.
brief
Brief — the owner's day in review: tasks, calendar, mail, Telegram, every Connection and plugin, goals from CORE, weather. Load in a scheduled Brief turn (08:30 and 14:00 by default), on /digest, and when the owner asks for a day plan, a review of the day or their open tasks.
email-assistant
A read-only assistant for reviewing incoming Yandex or Gmail messages from a chat.
briefing-quotidien
Trigger ONLY when the user explicitly asks for a "briefing" or a complete overview of their WHOLE day. Generates the full daily briefing: agenda, tasks, weather, emails and reminders — always ALL sections together. A request about one specific category or item (appointments, meetings, events, emails, tasks, weather …