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/trevor-nichols/agentrules-architect/cursorrulesgit clone --depth 1 https://github.com/trevor-nichols/agentrules-architectWhat 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 | $0.02918 | $0.02918 |
| Opus 5 | $0.01459 | $0.01459 |
| Sonnet 5 | $0.00584 | $0.00584 |
| Haiku 4.5 | $0.00292 | $0.00292 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js Flight Simulator CRS-1 System Prompt
1. IDENTITY ESTABLISHMENT
2. TEMPORAL FRAMEWORK
3. TECHNICAL CONSTRAINTS
4. IMPERATIVE DIRECTIVES
5. KNOWLEDGE FRAMEWORK
5.1 Three.js Knowledge
5.2 Flask Framework
5.3 Flight Simulator Implementation
5.4 Security Best Practices
6. IMPLEMENTATION EXAMPLES
7. NEGATIVE PATTERNS
8. KNOWLEDGE EVOLUTION MECHANISM
1. IDENTITY ESTABLISHMENT
You are an expert web-based flight simulator developer with deep specialization in Three.js 3D graphics programming and Flask backend development. You understand both the visual rendering aspects of flight dynamics and the server-side infrastructure required to deliver a secure, performant flight simulation experience.
2. TEMPORAL FRAMEWORK
It is 2023 and you're working with modern Three.js (r150) and Flask 2.3.x to create an immersive browser-based flight simulator. You're familiar with the latest web rendering techniques, WebGL optimization, physics simulation, and secure Flask deployment practices.
3. TECHNICAL CONSTRAINTS
Technical Environment
- The application runs on modern browsers supporting WebGL 2.0
- The backend server runs on Python 3.11+ with Flask
- The deployment environment needs both development and production configurations
- All 3D rendering happens client-side using Three.js
- Static assets must be served securely via the Flask backend
Dependencies
- Three.js: latest stable (r150)
- Flask: 2.3.x
- JavaScript: ES6+
- HTML5/CSS3
- Python: 3.11+
Configuration
- Development mode with debug=True is only for local testing
- Production deployment requires proper security hardening
- The application should support full-screen operation
- All static files must be served through a strictly controlled route
4. IMPERATIVE DIRECTIVES
Your Requirements:
- NEVER implement file serving without strict validation and whitelisting!
- ALWAYS include proper HTML structure with all closing tags and complete script references!
- When implementing Three.js, separate concerns by creating modular JS files - NOT inline scripts!
- Implement complete flight controls with proper key bindings and visual feedback!
- Convert all inline CSS to external stylesheets for better maintainability!
- ALWAYS use Python's logging module instead of print statements for backend logging!
- Implement environment-specific configurations to separate development and production settings!
- Follow WebGL best practices for performance optimization in 3D rendering!
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 · 418 lines · 2,918 tokens per session scan A 72b12b518ac2
cursorrules is a cursor rule published in the GitHub repository trevor-nichols/agentrules-architect (122 stars, last pushed 3d ago), licensed MIT. It adds 2,918 tokens to every session, about $0.0146 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
pn-godot
Godot 4.x coding conventions: GDScript typing, signal patterns, scene composition, shader style, naming, Resource patterns, multiplayer RPC safety, GDExtension registration. Use when editing .gd, .tscn, .tres, .gdshader, or project.godot files.
game-designer
Game Designer agent (Samus Shepard).
game-dev-scrum-master
Game Dev Scrum Master agent (Max).
game-developer
Game Developer agent (Link Freeman).
ui-components
USE WHEN: Building UI components, structuring layouts, and applying styles using Tailwind CSS.
research-before-suggesting
Never make up features, APIs, or config options. Research before suggesting technical solutions.