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/sandraschi/rtorrent-mcp/cursorrulesgit clone --depth 1 https://github.com/sandraschi/rtorrent-mcpWhat 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 | $0.00583 | $0.00583 |
| Opus 5 | $0.00292 | $0.00292 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
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 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.
This is a copy
92% identical to cursorrules — 13 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Central Documentation Rules
Rule #1: Read Central Docs First
BEFORE making any changes or starting work, ALWAYS:
-
Read the Central Documentation README:
- Location:
D:\Dev\repos\mcp-central-docs\README.md - This shows all important documentation "branches" (folder trees)
- Navigate from there to find specific information
- Location:
-
Follow Documentation Branches:
- Central docs are organized by topic (Anthropic ecosystem, Google ecosystem, patterns, projects, etc.)
- Each branch has its own README explaining what's inside
- Use the branch structure to find relevant docs
-
Check for Existing Patterns:
- Look in
docs/patterns/for design patterns - Check
templates/for reusable templates - Review
docs/projects/for similar project examples
- Look in
-
Avoid Duplication:
- Search existing docs before creating new ones
- Update existing docs rather than creating duplicates
- Reference central docs instead of copying content
Documentation Branches (from Central README)
Core Standards
STANDARDS.md- Documentation quality standardsSTRUCTURE.md- Directory layout guideCONTRIBUTING.md- How to contribute
Anthropic Ecosystem (docs/anthropic-ecosystem/)
- MCP Protocol, FastMCP, MCPB, Claude Desktop, Glama
Google Ecosystem (docs/google-ecosystem/)
- Gemini 3, Antigravity IDE, Nano Banana Pro, DeepMind, TPU infrastructure
Patterns (docs/patterns/)
- Design patterns for MCP servers and development
Projects (docs/projects/)
- myai, veogen, mywienerlinien, autohotkey
Monitoring (monitoring/)
- Prometheus/Grafana/Loki stack
Templates (templates/)
- Reusable templates and scripts
Quick Reference
Central Docs Location: D:\Dev\repos\mcp-central-docs\
Start Here: D:\Dev\repos\mcp-central-docs\README.md
When in doubt: Read the central README and navigate from there.
Session Context (rTorrent MCP)
You can manage rTorrent torrents and search anime/TV sources (nyaa.si, Pirate Bay, YTS, Anna's Archive) with Austrian legal checks via the rtorrent-mcp MCP server.
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.
- yesterday First seen · 76 lines · 583 tokens per session scan A 79160e7e9895
cursorrules is a cursor rule published in the GitHub repository sandraschi/rtorrent-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 583 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to cursorrules, differing in 13 lines, and is treated as a copy.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.