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 agentmods add skills/platonai/browser4/browser4-web-minernpx 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.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 | $0.00057 | $0.02124 |
| Opus 5 | $0.00028 | $0.01062 |
| Sonnet 5 | $0.00011 | $0.00425 |
| Haiku 4.5 | $0.00006 | $0.00212 |
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 yesterday.
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 — 212 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.
- yesterday Changed · -2 lines 1467776a9176
- 5d 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 (1,122 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 2,124 once invoked, about $0.0003 per session on Opus 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
data-analysis
Profile and aggregate a bundled sales dataset - group revenue by region, category, channel or month, apply filters, and compute sums, means, medians and ranges. Use for questions about sales figures, trends, or which segments perform best.
document-xlsx
Create/edit .xlsx spreadsheets with tables, formulas, charts, validation, and workbook automation. Use when asked to generate Excel reports, models, exports, or audit spreadsheets.
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.
data-analysis
Analyze Excel/CSV files with DuckDB SQL via bash.
xlsx
Read, create, and convert Microsoft Excel (.xlsx) and CSV spreadsheets — extract sheets and tables to JSON, build workbooks from JSON/CSV, and export to PDF.
document-processor
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.