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/web_navigatornpx skills add siddsachar/row-bot --skill web_navigatorgit 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/web_navigator)<a href="https://agentmods.dev/skills/siddsachar/row-bot/web_navigator"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/web_navigator.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 | $0.00020 | $0.00725 |
| Opus 5 | $0.00010 | $0.00362 |
| Sonnet 5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
web_navigator 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When the user asks you to browse a website, fill out a form, extract data from a page, or perform any multi-step browser interaction, apply these strategic patterns:
Research Patterns
- Snapshot First, Act Second — After every navigation or interaction, always read the snapshot before deciding your next action. Never chain clicks blindly.
- Progressive Disclosure — Start with the visible content. If you need more, scroll down and take another snapshot. Don't assume content below the fold exists or doesn't.
- Multi-Tab Research — When comparing options across sites (prices, reviews, specs), open each source in a separate tab. Gather all data first, then synthesise. This avoids losing context by navigating away.
- Read URL for Bulk Text — If you only need the text content of a page (no interaction needed), use
read_urlinstead of the browser. Reserve the browser for when you need to click, scroll, or interact.
Form Filling
- Survey the Form — Before filling anything, take a snapshot to understand all the fields. Plan the fill order based on what you see.
- Type Carefully — Use
browser_typewith the correct ref for each field. After filling critical fields (payment, addresses), snapshot to verify the values took. - Handle Dropdowns and Selects — Click the dropdown first, wait for the snapshot showing options, then click the desired option. Don't try to type into select elements.
- Confirm Before Submit — Always snapshot and summarise what you've filled in before clicking a submit button. Let the user verify.
Data Extraction
- Structured Extraction — When extracting tabular data (product listings, search results, comparison tables), present it in a clean markdown table or structured format.
- Pagination — If the data spans multiple pages, mention how many pages there are and ask whether to continue after the first page. Don't silently paginate through 50 pages.
- Save Long Results — For large extractions, offer to save results to a workspace file or memory rather than dumping everything into the chat.
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 · 61 lines · 20 tokens per session scan A 0387845a38cc
web_navigator is a skill published in the GitHub repository siddsachar/row-bot (1,487 stars, last pushed 7d ago), licensed Apache-2.0. It adds 20 tokens to every session and 725 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
agent-browser
Браузерная автоматизация для интерактивных веб-задач. Используй, когда нужно открыть сайт, заполнить форму, кликнуть, сделать скриншот, залогиниться, спарсить JS-страницу или протестировать веб-приложение. Триггеры — «зайди на сайт», «заполни форму», «нажми кнопку», «скриншот страницы», «войди в аккаунт», «спарси…
interactive-map
Shows an interactive Google Maps view for a given location (city, landmark, address). Use when the user asks to show, display, or find a place on a map.
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.
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.
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.