Browser4 is an AI-native browser engine that lets autonomous agents and people control real browsers, extract information from web pages, and automate tasks at scale. It combines browser interaction through a Rust CLI and MCP with deterministic selectors, machine-learning clustering, and language-model extraction. The catalogue entries provide skills and instructions for using Browser4.
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 platonai/Browser4 --skill browser4-web-minergit clone --depth 1 https://github.com/platonai/Browser4Wrote 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/platonai/browser4/browser4-web-miner)<a href="https://agentmods.dev/skills/platonai/browser4/browser4-web-miner"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-web-miner/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/platonai/browser4/browser4-web-miner"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-web-miner.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 | $0.00057 | $0.02408 |
| Opus 5.5 | $0.00023 | $0.00963 |
| Sonnet 5.5 | $0.00011 | $0.00482 |
| Haiku 4.5 | $0.00006 | $0.00241 |
Grade A, and why
browser4-web-miner scanned grade A with 1 finding 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 25d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
browser, wget, or a crawler to fetch pages first. How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebMiner — Convert Detail Web Pages into Interactive Views
Quick Start
browser4-cli webminer install # one-time install (Java 17+ auto-detected)
browser4-cli webminer all <html-dir> # full pipeline: encode → cluster → views
WebMiner groups similar web pages together and produces an interactive HTML report with clusters of related pages — plus Excel spreadsheets for further analysis. Give it a folder of downloaded HTML files, and it handles the rest. Everything runs locally; no data leaves your machine.
When to Use
Use WebMiner when you have a folder of downloaded HTML pages and want to cluster them into interactive views and Excel reports — fully local, no LLM tokens. It complements rather than replaces browser4-cli crawl/swarm (which acquire pages): WebMiner analyzes pages you already have. Not for single-page extraction — use htmlsnapshot for that.
How It Works
WebMiner runs a three-stage local pipeline: encode converts each HTML page into a 69-dimension feature vector, cluster groups similar pages with SMILE KMeans (k auto-detected), and views renders an interactive HTML report plus Excel spreadsheets. Everything runs locally on your machine — no data leaves it, and no LLM tokens are consumed.
Patterns
1. Full pipeline on a folder of pages
browser4-cli webminer all <html-dir>
2. Rebuild views from an existing run
browser4-cli webminer views <result-dir>
3. Try it on the sample dataset
browser4-cli webminer run-example
Flags
| Flag | Applies to | Description |
|---|---|---|
--max-files <n> |
webminer all |
Limit the number of HTML files processed (default 40) |
--output <dir> |
webminer all |
Override the output directory |
--resume [<project-id>] |
webminer all |
Resume a previous run |
Errors & Recovery
| Symptom | Cause | Fix |
|---|---|---|
webminer install fails |
No Java 17+ on PATH | Install JDK 17+ or point JAVA_HOME at it |
webminer all finds no pages |
Directory has no .html files |
Check the input directory path and file extensions |
| Pipeline crashes on large corpora | Free tier limit (< 1,000 pages) | Reduce the corpus or use --max-files; see the commercial Spark tier for scale |
| Views land in an unexpected temp dir | The views stage uses the app task-output root | Use webminer views <result-dir> to rebuild beside the result dir |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 25d ago Changed · +16 lines fa4566525410
- 1mo ago Changed · -2 lines 1467776a9176
- 1mo ago First seen · 214 lines · 57 tokens per session scan A ad9245881444
browser4-web-miner is a skill published in the GitHub repository platonai/Browser4 (1,164 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 2,408 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
xlsx
Create, inspect, edit, recalculate, validate, render, and deliver Excel workbooks while preserving formulas, formatting, drawings, links, macros, and metadata.
craft-data-visual
Turn data into a finished visual with ArtCraft apps - GridCraft workbook with a formula-error read-back, chart, VectorCraft/DesignCraft infographic, DeckCraft slide; verified and resumable. Use for "make a chart from this spreadsheet", "build an infographic from these numbers", "put the revenue chart on a slide".
gridcraft
Headless spreadsheets with GridCraft (XLSX/CSV/TSV workbooks, formula evaluation, recalculation, PDF export), provisioned on demand by pi-craft. Use for "build a budget spreadsheet with formulas", "convert this xlsx to csv", "what does this formula evaluate to", "change a cell and recalculate the totals", "export the…
office-documents
Create, edit and convert Word, Excel, PowerPoint and PDF artifacts with format-aware verification. Use when producing docx, xlsx, pptx or PDF files; preserve templates and actual document structure, and render or recalculate before delivery.
Spreadsheets
Create, edit, analyze, and verify standalone spreadsheet files or Google Sheets-ready workbooks, including .xlsx, .xls, .csv, and .tsv. Do not use for live controlling Microsoft Excel app or a live Excel session.
tencent-docs-sheet-generation
A tool for creating a new Excel workbook (.xlsx) from written requirements or reference PDF, Word, or presentation files. It is for starting without an existing spreadsheet file.