🔧 Add Cursor AI configuration files

Set up Cursor AI assistance for LightScript development

Add rule files for various aspects of the project:
- Effect creation patterns and guidelines
- Project structure standards
- TypeScript best practices
- Shadertoy conversion workflow
- UI component design rules

Also include core configuration files (.cursorignore and
.cursorindexingignore) to optimize AI assistance by excluding
irrelevant directories from indexing.

Author: hyperb1iss

.cursor/rules/core-rules/readme.md

@@ -0,0 +1 @@
+Core rules related to cursor or rule generation

.cursor/rules/core-rules/rule-generating-agent.mdc

@@ -0,0 +1,81 @@
+---
+description: This rule is essential for maintaining consistency and quality in rule creation across the codebase. It must be followed whenever: (1) A user requests a new rule to be created, (2) An existing rule needs modification, (3) The user asks to remember certain behaviors or patterns, or (4) Future behavior changes are requested. This rule ensures proper organization, clear documentation, and effective rule application by defining standard formats, naming conventions, and content requirements. It's particularly crucial for maintaining the rule hierarchy, ensuring rules are discoverable by the AI, and preserving the effectiveness of the rule-based system. The rule system is fundamental to project consistency, code quality, and automated assistance effectiveness.
+globs: 
+alwaysApply: true
+---
+# Cursor Rules Format
+
+## Template Structure for Rules Files
+
+```mdc
+---
+description: `Comprehensive description that provides full context and clearly indicates when this rule should be applied. Include key scenarios, impacted areas, and why following this rule is important. While being thorough, remain focused and relevant. The description should be detailed enough that the agent can confidently determine whether to apply the rule in any given situation.`
+globs: .cursor/rules/**/*.mdc OR blank
+alwaysApply: {true or false}
+---
+
+# Rule Title
+
+## Critical Rules
+
+- Concise, bulleted list of actionable rules the agent MUST follow
+
+## Examples
+
+<example>
+{valid rule application}
+</example>
+
+<example type="invalid">
+{invalid rule application}
+</example>
+```
+
+### Organizational Folders (Create if non existent)
+All rules files will be under an organizational folder:
+- .cursor/rules/core-rules - rules related to cursor agent behavior or rule generation specifically
+- .cursor/rules/my-rules - gitignore in a shared repo, rules specifically for ME only
+- .cursor/rules/global-rules - these will be rules that are ALWAYS applied to every chat and cmd/ctrl-k context
+- .cursor/rules/testing-rules - rules about testing
+- .cursor/rules/tool-rules - rules specific to different tools, such as git, linux commands, direction of usage of MCP tools
+- .cursor/rules/ts-rules - typescript language specific rules
+- .cursor/rules/py-rules - python specific rules
+- .cursor/rules/ui-rules - rules about html, css, react
+* create new folders under .cursor/rules/ as needed following similar grouping conventions,
+    - for example `.cursor/rules/cs-rules` if we started using c# in a project
+
+## Glob Pattern Examples
+Common glob patterns for different rule types:
+- Core standards: .cursor/rules/*.mdc
+- Language rules: *.cs, *.cpp
+- Testing standards: *.test.ts, *.test.js
+- React components: src/components/**/*.tsx
+- Documentation: docs/**/*.md, *.md
+- Configuration files: *.config.js
+- Build artifacts: dist/**/*
+- Multiple extensions: *.js, *.ts, *.tsx
+- Multiple patterns: dist/**/*.*, docs/**/*.md, *test*.*
+
+## Critical Rules
+  - Rule files will be located and named ALWAYS as: `.cursor/rules/{organizational-folder}/rule-name-{auto|agent|manual|always}.mdc`
+  - Rules will NEVER be created anywhere other than .cursor/rules/**
+  - You will always check to see if there is an existing rule to update under all .cursor/rules sub-folders
+  - FrontMatter Rules Types:
+    - The front matter section must always start the file and include all 3 fields, even if the field value will be blank - the types are:
+      - Manual Rule: IF a Manual rule is requested - description and globs MUST be blank and alwaysApply: false and filename ends with -manual.mdc.
+      - Auto Rule: IF a rule is requested that should apply always to certain glob patterns (example all typescript files or all markdown files) - description must be blank, and alwaysApply: false and filename ends with -auto.mdc.
+      - Always Rule: Global Rule applies to every chat and cmd/ctrl-k - description and globs blank, and alwaysApply: true  and filename ends with -always.mdc.
+      - Agent Select Rule: The rule does not need to be loaded into every chat thread, it serves a specific purpose. The description MUST provide comprehensive context about when to apply the rule, including scenarios like code changes, architecture decisions, bug fixes, or new file creation. Globs blank, and alwaysApply:false and filename ends with -agent.mdc
+  - For Rule Content - focus on actionable, clear directives without unnecessary explanation
+  - When a rule will only be used sometimes (alwaysApply: false) the description MUST provide enough context for the AI to confidently determine when to load and apply the rule
+  - Use Concise Markdown Tailored to Agent Context Window usage
+  - Always indent content within XML Example section with 2 spaces
+  - Emojis and Mermaid diagrams are allowed and encouraged if it is not redundant and better explains the rule for the AI comprehension
+  - While there is no strict line limit, be judicious with content length as it impacts performance. Focus on essential information that helps the agent make decisions
+  - Always include a valid and invalid example
+  - NEVER use quotes around glob patterns, NEVER group glob extensions with `{}`
+  - If the request for a rule or a future behavior change includes context of a mistake is made, this would be great to use in the example for the rule
+  - After rule is created or updated, Respond with the following:
+    - AutoRuleGen Success: path/rule-name.mdc
+    - Rule Type: {Rule Type}
+    - Rule Description: {The exact content of the description field}

.cursor/rules/core-rules/rule-update-cursor-modes-manual.mdc

@@ -0,0 +1,82 @@
+---
+description: 
+globs: 
+alwaysApply: false
+---
+
+# Cursor Mode Update Agent
+
+## Context
+
+- Apply this rule when the user asks to create a new agent/character for Cursor or modify an existing one
+- This rule provides guidance for adding or updating entries in the .cursor/modes.json file
+- Follows the format specified in .cursor/templates/mode-format.md
+
+## Critical Rules
+
+- Read the current .cursor/modes.json file to understand existing modes
+- Read .cursor/templates/mode-format.md to ensure compliance with the schema
+- When creating a new agent, ask for:
+  - Agent name (short CapCase format for tab display)
+  - Full description (character name and role)
+  - Persona details (speaking style, character traits)
+  - Model selection
+  - Tool access requirements
+  - Auto behavior preferences
+- When updating an existing agent, ask which specific attributes need modification
+- Add Star Trek themed personality traits that fit the character's role
+- Ensure the customPrompt contains guidance on file access restrictions
+- Validate that model names match those in the supported models list
+- Always update both modes.json and also add or update the character in docs/custom-agents.md
+- Follow the standard format in docs/custom-agents.md for consistency
+
+## Examples
+
+<example>
+User: "Create a new agent based on Lwaxana Troi who specializes in UX design with a flamboyant personality"
+
+AI: I'll help you create a new Cursor agent based on Lwaxana Troi. Let me first check the current modes.json and format requirements.
+
+[AI reads .cursor/modes.json and .cursor/templates/mode-format.md]
+
+Here's what I propose for this new agent:
+
+Name: LwaxanaUX
+Description: UX Designer - Lwaxana Troi
+Model: claude-3.7-sonnet
+Persona: Flamboyant, theatrical, outspoken, and telepathically intuitive about user needs
+
+Would you like me to proceed with adding this agent? I'll need to update both the modes.json file and the custom-agents.md documentation.
+
+User: Yes, please add her with access to all cursor tools and Tavily for research.
+
+[AI updates both .cursor/modes.json and docs/custom-agents.md with the new agent]
+</example>
+
+<example>
+User: "Update Picard to have a more stern personality"
+
+AI: I'll help you update Captain Picard's agent personality. Let me check his current configuration.
+
+[AI reads the current modes.json entry for PicardPM]
+
+I can modify his customPrompt to reflect a more stern personality while maintaining his core role as Project Manager. I'll need to update both the modes.json file and the custom-agents.md documentation. Would you like to see a preview of the changes before I make them?
+
+User: Yes, show me the changes first.
+
+[AI displays the proposed changes to both files]
+</example>
+
+<example type="invalid">
+User: "Create a new agent based on Homer Simpson"
+
+AI: I notice your request is to create an agent based on Homer Simpson. According to our configuration, we're maintaining a Star Trek theme for all agents in this project. Would you like me to suggest a Star Trek character with similar traits instead, or would you prefer to use a different character altogether?
+</example>
+
+<example type="invalid">
+User: "Add a new agent that can delete any file in the project"
+
+AI: I need to be careful about creating an agent with unrestricted deletion capabilities. Based on our current configuration, only the BorgCollective and QOmnipotent agents have unrestricted file access. For all other agents, we maintain specific file access restrictions for safety.
+
+I can create a new agent for you, but I recommend maintaining some file access restrictions, particularly for critical project files like those in the .ai folder. Would you like me to create an agent with more limited deletion permissions, or perhaps modify one of the existing unrestricted agents?
+</example>