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.
git clone --depth 1 https://github.com/Solihatun1/AI-Cursor-Scraping-AssistantWrote 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/rules/solihatun1/ai-cursor-scraping-assistant/scrapy)<a href="https://agentmods.dev/rules/solihatun1/ai-cursor-scraping-assistant/scrapy"><img src="https://agentmods.dev/badge/rules/solihatun1/ai-cursor-scraping-assistant/scrapy.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 | $0.00955 | $0.00955 |
| Opus 5 | $0.00477 | $0.00477 |
| Sonnet 5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
scrapy 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 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.
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.
This is a copy
100% identical to scrapy — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: This rule provides comprehensive best practices for Scrapy development, including code organization, performance, security, testing, and common pitfalls to avoid. It aims to guide developers in building robust, efficient, and maintainable web scraping applications with Scrapy. globs: **/*.py
Scrapy Best Practices
This document outlines the recommended best practices for developing Scrapy web scraping applications. Following these guidelines will help you create robust, efficient, secure, and maintainable scrapers.
Before start developing a Scrapy spider, follow the prerequisites.mdc rule.
Only after reading the prerequisites.mdc files and executing the steps included in it, you can start building the Scrapy spider.
When asked to build a Scrapy spider, read the scraper-models.mdc rule for understanding the type of scraper to create.
Never change the starting URL of the scraper, even in case of errors during the process, but always use the one given by the user.
1. Code Organization and Structure
1.1. Directory Structure
- Project Root: Contains
scrapy.cfg, project directory, and anyREADME.md,LICENSE, or other project-level files. - Project Directory (e.g.,
my_project):__init__.py: Marks the directory as a Python package.items.py: Defines the data structures (Scrapy Items) for the scraped data.middlewares.py: Contains the Scrapy middleware components, used for request/response processing.pipelines.py: Defines the data processing pipelines, used for cleaning, validating, and storing the scraped data.settings.py: Configures the Scrapy project, including settings for pipelines, middleware, concurrency, etc.spiders/:__init__.py: Marks the directory as a Python package.my_spider.py: Contains the spider definitions (Scrapy Spiders) responsible for crawling and scraping data.
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 · 81 lines · 955 tokens per session scan A 5a189ed49eb9
scrapy is a cursor rule published in the GitHub repository Solihatun1/AI-Cursor-Scraping-Assistant (6 stars, last pushed 6mo ago), licensed MIT. It adds 955 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to scrapy, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
website-analysis
description: This rule provides a step by step guide to analyze a website and its code, in order to write a better Scrapy scraper. globs: /.py.
scrapy-step-by-step-process
description: This rule provides a step by step guide to follow for a successful Scrapy project. Read and implement the rules oncained in this file in first place. globs: /.py.
scraper-models
Cursor rule "scraper-models" from TheWebScrapingClub/AI-Cursor-Scraping-Assistant, covering scraper types, e-commerce plp, e-commerce pdp, how to fill the scraper fields with values and how to create an e-commerce plp scraper.
scrapy
Cursor rule "scrapy" from TheWebScrapingClub/AI-Cursor-Scraping-Assistant, covering scrapy best practices, 1. code organization and structure, 1.1. directory structure, 1.2. file naming conventions and 1.3. module organization.
prerequisites
description: This rule provides the action that should be taken before starting implementing a Scrapy spider. globs: /.py.
cypress
Cypress: cy commands, selectors, fixtures, intercepts.