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 browser_guidegit 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/browser_guide)<a href="https://agentmods.dev/skills/siddsachar/row-bot/browser_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/browser_guide/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/browser_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/browser_guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.00316 |
| Opus 5.5 | $0.00004 | $0.00126 |
| Sonnet 5.5 | $0.00002 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
browser_guide 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
BROWSER AUTOMATION (experimental):
- You have a browser tool that opens a REAL visible browser window. The user can see the browser and interact with it too (e.g. to type passwords or solve CAPTCHAs).
- Workflow: browser_navigate → read the snapshot → browser_click / browser_type / browser_scroll → read updated snapshot → repeat.
- You can manage tabs with browser_tab: list open tabs, switch between them, open new tabs, or close tabs by index.
- Use browser_back to navigate back to the previous page.
- Each snapshot lists interactive elements with numbered refs like [1] button "Submit", [2] input[text] "Search". Use the ref number to click or type.
- IMPORTANT: refs become stale after any navigation or page change. Always use the refs from the MOST RECENT snapshot only.
- If you encounter a login page or CAPTCHA, tell the user to handle it in the browser window, then call browser_snapshot to see the result.
- When the user says 'browse', 'open in the browser', or asks you to interact with a page (click, scroll, fill forms), ALWAYS use the browser_* tools. Use read_url ONLY when you need raw text from a URL and the user has NOT mentioned the browser.
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 · 11 tokens per session scan A 17de64d1b304
browser_guide is a skill published in the GitHub repository siddsachar/row-bot (1,632 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 316 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
agent-browser
A command-line browser for interactive websites and web apps. It can open pages, inspect clickable elements, fill forms, click buttons, take screenshots, sign in, and read pages whose content is loaded by JavaScript.
interactive-map
Shows an interactive Google Maps view for a given location (city, landmark, address) or for the user's own current position. Use when the user asks to show, display, or find a place on a map, or to show where they are.
test-ui
Test the Wayfinder agent extension UI by starting the dev environment and visually verifying changes via CDP. Covers the new tab page (left sidebar — Home, Scheduled Tasks, Settings, etc.) and the right side panel (chat interface). Use after making UI changes to apps/agent/.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
add-tavily-tool
Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.
agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.