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/aaronontheweb/dotnet-cursor-rules/metagit clone --depth 1 https://github.com/Aaronontheweb/dotnet-cursor-rulesWhat 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 | $0.00000 | $0.00420 |
| Opus 5 | $0.00000 | $0.00210 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
meta 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 2d 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.
What it actually says
Cursor Rules
This document outlines the meta-rules for cursor operations in this repository.
Line Ending & Formatting Rules
-
Line Endings
- Don't modify existing line endings
- Preserve CRLF/LF as found in the original file
-
Whitespace
- Preserve trailing whitespace where it exists
- Maintain existing indentation style (spaces vs tabs)
- Keep line length consistent with existing code
File Handling
-
MDC Files
- Always commit changes to
*.mdcfiles directly - Ensure changes to
*.mdcfiles are synchronized with their implementation - Maintain consistent formatting within MDC files
- Prefer modifying existing files over creating new ones unless explicitly requested
- When adding new content, first check if it fits within an existing rule file
- Always commit changes to
-
File Creation
- Only create new rule files when:
- Explicitly requested by the user
- The content doesn't logically fit in any existing rule file
- Creating a new file would significantly improve organization and clarity
- Document the rationale for creating new files in their README.md
- Only create new rule files when:
Code Style & Structure
-
Formatting
- Preserve existing code formatting patterns
- Maintain consistent naming conventions
- Keep indentation consistent with file style
-
Organization
- Keep file structure consistent
- Don't move files without updating all references
- Maintain existing import/include order
Rule Content
- Examples
- Always include "do" and "don't" examples when showing specific changes to files or syntax
- Include helpful comments that explain why an example is a "do" or a "don't"
Documentation
- README.md
- Each
*.mdcfile is lumped into a folder with aREADME.mdfile explaining what the rule does and when it's used.
- Each
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.
- 2d ago First seen · 59 lines · 420 tokens per session scan A 140b95ad8d4a
meta is a cursor rule published in the GitHub repository Aaronontheweb/dotnet-cursor-rules (134 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 420 tokens. 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
angular
Angular: signals, standalone components, RxJS patterns.
django
Django: models, views, ORM best practices.
java
Modern Java: records, sealed classes, streams, virtual threads.
javascript
Modern JavaScript: ES2023+, async patterns, common traps.
rust
Rust patterns: ownership, Result types, iterators.
accessibility
Accessibility: semantic HTML, ARIA, keyboard navigation, testing.