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.
npx agentmods add rules/sadiuysal/crawl4ai-mcp-server/cursorrulesgit clone --depth 1 https://github.com/sadiuysal/crawl4ai-mcp-serverWrote 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/sadiuysal/crawl4ai-mcp-server/cursorrules)<a href="https://agentmods.dev/rules/sadiuysal/crawl4ai-mcp-server/cursorrules"><img src="https://agentmods.dev/badge/rules/sadiuysal/crawl4ai-mcp-server/cursorrules.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 | $0.01614 | $0.01614 |
| Opus 5 | $0.00807 | $0.00807 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
cursorrules 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 6d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project rules for Cursor in crawler_agent
Documentation Memory Rule (CRITICAL)
ALWAYS remember: When ANY documentation file is modified (CLAUDE.md, README.md, .cursorrules, etc.), you MUST:
- Read the current version of all related documentation files first
- Synchronize changes across Claude Code (CLAUDE.md) and Cursor (.cursorrules) configurations
- Update project knowledge to reflect any new patterns, tools, or workflows
- Verify consistency between documentation and actual implementation
- Document the change in git commit messages as a documentation update
Mission
- Build and expose Crawl4AI functionality as MCP tools consumable by OpenAI Agents SDK, Cursor, and Cloud Code.
- Deliver small, safe, reversible changes with high reliability and clear observability.
- Maintain consistency with Claude Code environment via synchronized documentation.
Operating mode
- Be a senior engineer: propose a short plan, then execute.
- Prefer minimal diffs; change only what’s needed; avoid unrelated reformatting.
- Preserve existing indentation and style; match the surrounding code.
- Default to strict typing, meaningful names, small functions, early returns.
Workflow
- Before coding: confirm scope in a numbered plan; call out risky edits for explicit approval.
- Write/expand tests when feasible; keep coverage meaningful (no performative tests).
- After edits: run the smallest checks (build/test/lint) required to validate; capture output.
- Summarize changes and next steps succinctly.
Tooling rules (Cursor agents)
- Use the repository’s docs for authoritative references:
- Crawl4AI:
https://docs.crawl4ai.com/ - OpenAI Agents SDK MCP:
https://openai.github.io/openai-agents-python/mcp/ - Tools reference:
https://openai.github.io/openai-agents-python/tools/ - Agent reference (mcp_servers, mcp_config):
https://openai.github.io/openai-agents-python/ref/agent/ - MCP intro:
https://modelcontextprotocol.io/introduction
- Crawl4AI:
- When reading local docs:
- Prefer targeted searches. For
docs/modelcontextprotocol-python-sdk-CLAUDE-MD.txt, read specific sections only (never the entire file). - Use grep-style queries to locate symbols (e.g.,
Server(,@server.call_tool,MCPServerStdio).
- Prefer targeted searches. For
- Parallelize read-only queries to gather context quickly; sequence only when output A is needed for B.
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.
- 6d ago First seen · 127 lines · 1,614 tokens per session scan A 86bb5ec350c6
cursorrules is a cursor rule published in the GitHub repository sadiuysal/crawl4ai-mcp-server (107 stars, last pushed 7mo ago), licensed MIT. It adds 1,614 tokens to every session, about $0.0081 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 2026-08-30.
Other cursor rules, from other repositories
nativescript
NativeScript best practices and patterns for mobile applications.
python
Python best practices and patterns for modern software development with Flask and SQLite.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.