Cursor IDE + Arcanea Intelligence OS — Setup Guide
Explains how Cursor IDE reads Arcanea Intelligence OS rules and how to activate Guardian-specific rules in Chat and Composer.
What this file does
Explains how Cursor IDE reads Arcanea Intelligence OS rules and how to activate Guardian-specific rules in Chat and Composer.
When to use it
- Setting up Cursor IDE for an Arcanea-based project
- Learning how to invoke Guardian rules in Cursor Chat
- Understanding rule priority and automatic application in Cursor
- Regenerating rule files after updating Arcanea Intelligence OS
Assumes this stack
Cursor IDE + Arcanea Intelligence OS — Setup Guide
"The antidote to a terrible future is imagining a good one." — Arcanea Core Premise
How Cursor Reads Arcanea Rules
Cursor automatically reads rules in this priority order:
.cursorrules(root-level) — Applied to all AI interactions.cursor/rules/arcanea.mdc— Modular rule withalwaysApply: true.cursor/rules/arcanea-typescript.mdc— TypeScript-specific (activated for .ts/.tsx files).cursor/rules/guardian-*.mdc— Guardian-specific rules (activated on demand)
No manual setup required — Cursor picks these up automatically.
Activating Guardian Rules in Cursor Chat
Reference Guardian rules explicitly in Cursor Chat:
@rules guardian-lyssandria.mdc How should I structure this database schema?
@rules guardian-lyria.mdc Review this component's visual design
@rules guardian-draconia.mdc Optimize this query for performance
Guardian Quick Reference
| Guardian | Rule File | Activate When |
|---|---|---|
| Lyssandria | guardian-lyssandria.mdc | Database, security, architecture |
| Leyla | guardian-leyla.mdc | UX, animations, accessibility |
| Draconia | guardian-draconia.mdc | Performance, CI/CD, optimization |
| Maylinn | guardian-maylinn.mdc | Community features, notifications |
| Alera | guardian-alera.mdc | APIs, docs, error messages |
| Lyria | guardian-lyria.mdc | UI components, design tokens |
| Aiyami | guardian-aiyami.mdc | Strategy, philosophy |
| Elara | guardian-elara.mdc | Refactoring, perspective |
| Ino | guardian-ino.mdc | Integrations, third-party |
| Shinkami | guardian-shinkami.mdc | Orchestration, planning |
Cursor Composer Usage
In Cursor Composer (multi-file edits), Arcanea rules are automatically applied:
- Open Composer (Cmd+I / Ctrl+I)
- Describe the task in Arcanea terms:
- "Lyssandria's domain: add RLS policy for this table"
- "Leyla's principle: add smooth transition to this modal"
- "Alera's voice: rewrite these error messages in Arcanea voice"
- Composer will apply rules from
.cursor/rules/automatically
Inline Suggestions
Cursor's inline suggestions read .cursorrules and will:
- Suggest TypeScript with strict types (no
any) - Use Arcanea design tokens in Tailwind classes
- Generate comments in the Arcanean voice
- Prefer Server Components over Client Components
Updating Rules
Run arcanea install cursor to regenerate all rule files with the latest
Arcanea Intelligence OS content. Your customizations in filesCustomized
(tracked in .arcanea/overlay-manifest.json) are preserved.
Notes
.cursorrulesis read globally — it shapes all Cursor AI interactions- MDC rules in
.cursor/rules/can be referenced explicitly in Chat - Guardian rules are not always-applied — activate them when working in their domain
- Run
arcanea install cursor --level luminorto get the deepest level of Guardian rules
What's inside
1 priority list, 1 quick reference table (10 guardians), 3 usage sections, 1 update command, 4 notes
Change this for your project
- Replace
frankxai/arcaneawith your own repository name - Replace Guardian names like
guardian-lyssandria.mdcwith your own rule files - Replace
arcanea install cursorwith your own install command
Where it goes
Save in docs/ or the repository root. Gives agents and new contributors a map of the codebase.
Worth borrowing
- Using a priority-ordered rule system for AI interactions
- Activating domain-specific rules on demand via @rules in Chat
- Preserving customizations during rule regeneration with an overlay manifest
Related Documents
PCB Design Sources for Industry-Scale Testing
Lists GitHub repos and communities where you can download real PCB designs for testing optimization at scale.
Design Document: BharatSeva AI
Describes a 10-agent AWS system that helps India's informal workers access government schemes via voice-first, serverless architecture.
OpenClaw Enterprise Transformation Plan
Transforms a single-user AI agent into a dual-mode platform supporting both viral open-source and Fortune 500 enterprise deployments through phased security, IAM, audit, multi-tenancy, and Kubernetes features.
Qwen Image and Edit: Open-sourcing and Local GGUF Generations with Lightning
Documents the Qwen-Image and Qwen-Image-Edit models, covering architecture, training, benchmarks, ComfyUI setup, and prompting techniques for local GGUF deployment.