agentmods.dev

scrape-cloudflare-site

scrape-cloudflare-site is a skill for Claude Code, Codex from agentforce314/clawcodex. It costs 34 tokens per session (259 once invoked), scanned A, original, MIT.

A web-fetching workflow for pages protected by Cloudflare, a service that can show an anti-bot challenge instead of the page. It uses a reader proxy, saves multiple pages with one script, and handles continuation pages and rate limits.

In plain words
What is it for?
Use it to collect text such as novel chapters from Cloudflare-protected sites and save the results locally for later use.
Why use it?
It avoids wasting requests on direct tools that receive only the challenge page. It also makes multi-page downloads resumable and stops when the proxy reports a blocking condition.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 927repo +3 yesterday A scan 34 tokens original MIT

Good fit Use it to collect text such as novel chapters from Cloudflare-protected sites and save the results locally for later use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentforce314/clawcodex/scrape-cloudflare-site
View source ↗ agentforce314/clawcodex clawcodex.app
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.

Any agent
npx skills add agentforce314/clawcodex --skill scrape-cloudflare-site
Clone the repo
git clone --depth 1 https://github.com/agentforce314/clawcodex

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for scrape-cloudflare-site

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentforce314/clawcodex/scrape-cloudflare-site/github.svg)](https://agentmods.dev/skills/agentforce314/clawcodex/scrape-cloudflare-site)
Your own site
<a href="https://agentmods.dev/skills/agentforce314/clawcodex/scrape-cloudflare-site"><img src="https://agentmods.dev/badge/skills/agentforce314/clawcodex/scrape-cloudflare-site/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.

agentmods 80×15 button for scrape-cloudflare-site

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentforce314/clawcodex/scrape-cloudflare-site"><img src="https://agentmods.dev/badge/skills/agentforce314/clawcodex/scrape-cloudflare-site.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00034 $0.00259
Opus 5.5 $0.00014 $0.00104
Sonnet 5.5 $0.00007 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 16d ago against content hash d500bfd4a47f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scrape-cloudflare-site 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 16d 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.

description: Fetch web pages (e.g. novel chapters) that return a Cloudflare "Just a moment" page to curl or headless Chrome.
docs/examples/skills/scrape-cloudflare-site/SKILL.md · 16 lines

What it actually says

Scraping pages behind Cloudflare

Do NOT try direct curl or headless Chrome first; both get the challenge page and waste turns.

  1. Fetch through the reader proxy: curl -s "https://r.jina.ai/<full original URL>". The real text follows a Markdown Content: marker.
  2. Write ONE Python script that loops over all pages and saves each to disk, rather than one tool call per page. Skip files already saved so reruns resume.
  3. Sleep ~1s between requests. A ~240-byte body or RateLimitTriggeredError means HTTP 429: wait 10-30s and retry.
  4. Multi-page chapters may continue at <name>_2.html; fetch and join them.
  5. After the loop, print count and byte size per file; re-fetch any that are tiny.
  6. If the proxy returns a 403 AbuseAlleviationError saying "blocked until ", STOP. Do not poll or loop; every retry extends the block. Tell the user the time and finish.
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. 16d ago First seen · 16 lines · 34 tokens per session scan A d500bfd4a47f

Subscribe to this mod's changes

scrape-cloudflare-site is a skill published in the GitHub repository agentforce314/clawcodex (927 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 259 once invoked, about $0.0001 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 2026-10-22.

Browser automationClaude CodeLLMPythonagentai-agentclaude
Related

scrape-cloudflare-site compared with skills from other repositories

scrape-cloudflare-site next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
scrape-cloudflare-siteagentforce314/clawcodexSkill927yesterdayMITA34Claude Code, Codex
x402browser-use/browser-useSkill120kyesterdayMITA175Claude Code
browser-usebrowser-use/browser-useSkill120kyesterdayMITA57Claude Code, Codex
remote-browserbrowser-use/browser-useSkill120kyesterdayMITA22Claude Code
playwrightopenai/openai-agents-pythonSkill31ktodayMITA19Claude Code, Codex
cloudbrowser-use/browser-useSkill120kyesterdayMITA177Claude Code
web-exfiltration-detectionTencent/AI-Infra-GuardSkill7.4kyesterdayApache-2.0A61Claude Code