web-scrape AGENTS.md

A set of instructions for using the web-scrape package to fetch or extract text from websites, including sites rendered with JavaScript or protected by access checks.

In plain words
What is it for?
Fetching rendered page text, scraping ordinary HTML, running the package as an HTTP service, or using its JavaScript library.
Why use it?
It helps an agent choose the appropriate command and distinguish trustworthy page content from blocks, login pages, robot restrictions, and other failures.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/teslashibe/web-scrape/agents-md
Clone the repo
git clone --depth 1 https://github.com/teslashibe/web-scrape

Made for: Codex, OpenCode.

Per session 592 This file is loaded in full into every session.
When invoked 592 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00592 $0.00592
Opus 5 $0.00296 $0.00296
Sonnet 5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured yesterday against content hash 4b1556b007b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-scrape AGENTS.md 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 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.

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.

AGENTS.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — web-scrape

Guidance for autonomous agents using this package.

Prefer CLI

web-scrape fetch <url> --json
web-scrape scrape <url> --json
web-scrape serve --port 8091
  • Use fetch when you need rendered DOM text (JS sites, soft challenges).
  • Use scrape when HTTP HTML extract is enough (faster, no Chromium).
  • Use serve only when an MCP client must discover tools over HTTP.

Exit codes: 0 ok, 2 structured failure (statusok), 1 hard error.

Library

import { scrape, browserFetchURL } from "web-scrape";

Do not import server.js unless you intend to bind a port.

Status contract

Never treat non-ok bodies as page content. Important statuses:

status meaning
ok trustworthy extract
cloudflare_blocked / turnstile_required CF/Turnstile gate (solve only if CapSolver env is set)
captcha_required reCAPTCHA/hCaptcha (optional same-origin provider; off by default)
robots_disallowed robots.txt denied
blocked / login_required / rate_limited hard gates
challenge_provider_unavailable CapSolver/provider failed
timeout / error transport

Warnings may include turnstile:<code> — codes are secret-free. Never echo env secrets.

CapSolver rules

  • Opt-in: WEB_FETCH_TURNSTILE_PROVIDER=capsolver + WEB_FETCH_TURNSTILE_API_KEY.
  • Sticky proxy required for Cloudflare clearance (WEBSHARE_USERNAME_TEMPLATE={user}-{country}-1).
  • CapSolver proxy encoding is socks5; do not “fix” that to HTTP.
  • Do not send challenge-page html on AntiCloudflareTask — CapSolver returns invalid html.
  • Budget: hard CF clears often need 30–90s; set BROWSER_FETCH_TIMEOUT_MS ≥ 120000 when enabled.

Safety

  • Only public http(s) URLs (SSRF guard).
  • No social-login / cookie jar reuse — every browser context is ephemeral.
  • Do not disable robots checks.
  • Do not log API keys, proxy URLs, or solved tokens.

Read the full file on GitHub · 63 lines

Changes

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.

  1. yesterday First seen · 63 lines · 592 tokens per session scan A 4b1556b007b7

Subscribe to this mod's changes

web-scrape AGENTS.md is an instructions file published in the GitHub repository teslashibe/web-scrape (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 592 tokens to every session, about $0.0030 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 2026-08-31.