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/web-scrapingnpx skills add platonai/Browser4 --skill web-scrapinggit 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/web-scraping)<a href="https://agentmods.dev/skills/platonai/browser4/web-scraping"><img src="https://agentmods.dev/badge/skills/platonai/browser4/web-scraping.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 | $0.00048 | $0.00866 |
| Opus 5 | $0.00024 | $0.00433 |
| Sonnet 5 | $0.00010 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
web-scraping 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Scraping Skill
Description
Extract data from web pages using JavaScript and CSS selectors. This skill uses real browser automation to navigate to pages and extract content using JavaScript execution. It can extract webpage titles using document.title and body text using document.body.textContent, providing actual content from live web pages.
Dependencies
None
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| url | String | Yes | - | The URL of the web page to scrape |
| selector | String | Yes | - | CSS selector to target specific elements |
| attributes | List | No | ["text"] | List of attributes to extract (e.g., "text", "href", "src") |
Return Value
Returns a SkillResult with the following data structure:
{
"url": "string",
"selector": "string",
"attributes": ["string"],
"data": "extracted content"
}
Usage Examples
Basic Text Extraction
val result = registry.execute(
skillId = "web-scraping",
context = context,
params = mapOf(
"url" to "https://example.com",
"selector" to ".content"
)
)
Extract Multiple Attributes
val result = registry.execute(
skillId = "web-scraping",
context = context,
params = mapOf(
"url" to "https://example.com/products",
"selector" to "a.product-link",
"attributes" to listOf("text", "href")
)
)
Tool Call Specification
ToolSpec(
domain = "skill.debug.scraping",
method = "extract",
arguments = [
"url: String",
"selector: String",
"attributes: List<String> = listOf('text')"
],
returnType = "Map<String, Any>",
description = "Extract data from a web page using CSS selectors"
)
Error Handling
The skill returns a failure result in the following cases:
- Missing required parameter
url - Missing required parameter
selector - Invalid URL format (must start with http:// or https://)
What ships with it
4 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.
- 4d ago First seen · 125 lines · 48 tokens per session scan A 4061d16de8b7
web-scraping is a skill published in the GitHub repository platonai/Browser4 (1,120 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 866 once invoked, about $0.0002 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
cdp
Drive Browser Use Desktop's assigned Chromium target via the DevTools Protocol from JavaScript. Run snippets through the bundled browser-harness-js CLI; it auto-spawns a long-lived Bun HTTP server holding a CDP Session, and every call executes against the same persistent connection.
browser_scripts
Visual browser automation script editor & manager for TubeCLI.
Chrome
Browser automation for the user's Chrome browser. Use for browser tasks that require the user's cookies, logged-in sessions, existing tabs, extensions, or remote authenticated sites.
fsb
FSB drives the user's Chrome via the FSB extension and an MCP bridge for live web tasks.
open-browser-use
Platform-neutral guidance for using Open Browser Use, the open-source Chrome automation stack for AI agents. Use when an agent needs to install, verify, troubleshoot, or operate Open Browser Use through its browser extension, native CLI, JavaScript SDK, Python SDK, Go SDK, or Browser Use style JSON-RPC methods; use…
Browser Automation
Manage anti-detect browser profiles, open/close browsers, automate the web.