Borrowing it
Nothing to install: this file belongs to aphrody-code/bxc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aphrody-code/bxc/main/.claude/skills/scraper-recipe/SKILL.mdgit clone --depth 1 https://github.com/aphrody-code/bxcWrote 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/aphrody-code/bxc/scraper-recipe)<a href="https://agentmods.dev/skills/aphrody-code/bxc/scraper-recipe"><img src="https://agentmods.dev/badge/skills/aphrody-code/bxc/scraper-recipe/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/aphrody-code/bxc/scraper-recipe"><img src="https://agentmods.dev/badge/skills/aphrody-code/bxc/scraper-recipe.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00066 | $0.01096 |
| Opus 5.5 | $0.00026 | $0.00438 |
| Sonnet 5.5 | $0.00013 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
scraper-recipe 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bxc scraper recipe
Quand invoquée via /scraper-recipe, cette skill produit un fichier scraper complet à partir des inputs suivants :
- URL ou pattern d'URL (obligatoire)
- Schéma cible (description naturelle, ex : "titre + prix EUR + stock")
- Profil souhaité (optionnel, défaut =
static) - Mode (one-shot dans
examples/<name>.ts, ou sub-package danspackages/<name>/src/)
API réelle (0.4.0)
L'API publique est Browser.newPage() → page.* → page.close(). Il n'existe
pas de Browser.fetch() ni Browser.scrape(). La feature LLM-extract a été
supprimée — l'extraction se fait par sélecteurs CSS (page.$$) ou Markdown
(page.markdown()), puis Zod.parse().
import { Browser } from "@aphrody/bxc"; // singleton
import { googleSearchRich } from "@aphrody/bxc/google"; // si recherche
Surface page utile : goto(url,{timeoutMs}), content() (HTML), markdown()
(GFM, fallback JS si cdylib absente), $(sel)/$$(sel) (handles → .textContent()
/.getAttribute(name)), title(), screenshot(), evaluate(fn) (profils JS),
close().
Workflow
-
Lis le contexte :
src/api/browser.ts—Browser.newPage(opts)+ classePage(API ci-dessus)src/api/browser.ts(PageOptions) — profils valides :static | http | fast | stealth | maxsrc/storage/Dataset.ts— store JSONL interne (Datasetnon exporté du package : import relatif ou JSONL manuel)
-
Décide l'extraction :
- HTML structuré + sélecteurs CSS suffisent →
page.$$()+Zod.parse() - Contenu prose / page entière →
page.markdown()
- HTML structuré + sélecteurs CSS suffisent →
-
Génère le fichier avec ce template :
import { z } from "zod";
import { Browser } from "@aphrody/bxc";
const Schema = z.object({
// ... champs selon la demande utilisateur
title: z.string(),
});
type Item = z.infer<typeof Schema>;
async function scrape(url: string): Promise<Item> {
const page = await Browser.newPage({ profile: "static" }); // static|http|fast|stealth|max
try {
await page.goto(url, { timeoutMs: 30_000 });
const titleEl = await page.$("h1");
const raw = {
title: (await titleEl?.textContent()) ?? "",
// ... autres champs via page.$$/$ ou page.markdown()
};
return Schema.parse(raw);
} finally {
await page.close();
}
}
const urls = [/* ... */];
const out = Bun.file("dataset.jsonl").writer();
try {
for (const url of urls) {
try {
const item = await scrape(url);
out.write(JSON.stringify(item) + "\n");
console.log(`OK ${url}`);
} catch (err) {
console.error(`FAIL ${url}`, err);
}
}
} finally {
await out.end();
await Browser.close();
}
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 · 103 lines · 66 tokens per session scan A dc4b76d3636c
scraper-recipe is a skill published in the GitHub repository aphrody-code/bxc (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,096 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
obscura
Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against deterministic…
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
browser_harness
../../SKILL.md.
agent-browser-cli
A browser-control skill for agent-browser-cli, a command-line tool that operates a real Chrome browser while keeping its existing login state and cookies. It supports page inspection, interaction, screenshots, PDFs, and local files.
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.