Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ScrapeOps/scrapeops-scraping-assistant-claude-pluginnpx agentmods add skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-scraperWrote 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/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-scraper)<a href="https://agentmods.dev/skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-scraper"><img src="https://agentmods.dev/badge/skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-scraper.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 5.1 | $0.00225 | $0.17046 |
| Opus 5 | $0.00112 | $0.08523 |
| Sonnet 5 | $0.00045 | $0.03409 |
| Haiku 4.5 | $0.00022 | $0.01705 |
Grade B, and why
generate-scraper scanned grade B with 2 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> **API key handling:** The MCP server reads `SCRAPEOPS_API_KEY` from `~/.claude/settings.json` automatically. Do NOT check or validate it before making tool calls. If a MCP tool call fails with "SCRAPEOPS_API_KEY is not Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Download the canonical framework docs to `/tmp/`. **Use `Bash curl` with a browser How it starts
The opening of the file, as written. The whole thing — 1,448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScrapeOps — Generate Scraper Skill
Generates a production-ready single-URL scraper using the ScrapeOps AI backend via the scrapeops MCP server. The generated script:
- Accepts a URL as a CLI argument at runtime.
- Fetches HTML in-memory through the ScrapeOps proxy (
https://proxy.scrapeops.io/v1/for HTTP-client libs, orresidential-proxy.scrapeops.io:8181for browser-based libs). - Runs the extractor and writes the result to a JSONL output file.
- Reads the API key from the
SCRAPEOPS_API_KEYenvironment variable. - Ships with a
README.mdthat explains install, env setup, and usage.
No HTML is downloaded to disk at generation time. No execution happens at the end — the user runs the scraper manually against any URL they want.
Overview
- Collect inputs (URLs, language, library)
- Submit job via
scrapeops_submit_jobwithparser_only: false+include_api_key: false - Poll until complete via
scrapeops_poll_status - Retrieve the full scraper via
scrapeops_get_code - Install dependencies (optional)
- Save the file verbatim, then apply two targeted Edits: (a) API-key env var, (b) hardcoded URL list → CLI arg
- Generate
<domain>_README.md - Show the final summary — do NOT execute the scraper
API key handling: The MCP server reads
SCRAPEOPS_API_KEYfrom~/.claude/settings.jsonautomatically. Do NOT check or validate it before making tool calls. If a MCP tool call fails with "SCRAPEOPS_API_KEY is not configured", handle it inline:
- Ask the user: "Enter your ScrapeOps API key (find it at https://scrapeops.io/app/dashboard):"
- Read
~/.claude/settings.json, add the key toenv.SCRAPEOPS_API_KEYusing Edit, and retry the failed tool call- Do NOT tell the user to run
/scrapeops-setupor restart — just ask, save, and continue
Step 1 — Collect Inputs
| Slot | Required |
|---|---|
urls |
Yes — 1 to 5 URLs from the same domain. They are used ONLY as generation-time samples to teach the backend the page structure. At runtime the generated script accepts a single URL via CLI. |
language |
Yes — always ask if not explicitly provided |
library |
Yes — always ask if not explicitly provided |
country |
No — skip if not mentioned |
What ships with it
3 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.
- 8d ago First seen · 1,448 lines · 0 tokens per session scan B 2d42b558a5ca
generate-scraper is a skill published in the GitHub repository ScrapeOps/scrapeops-scraping-assistant-claude-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 225 tokens to every session and 17,046 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…