avatar-mcp / rules
Cursor rule1 starsChanged 8 months agoMITView on GitHub
Global Architect rules for sandraschi's dev environment (Unity and other integrations, FastMCP, React). See mcp-central-docs integrations.
- Deletes or force-pushes
We split this architect.mdc into the rules it gives an agent
10 rules. About 0 are common, 5 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Anti-Gaslight: No mocks, no placeholders.
- Distinctive: line 17
No Conversation Fluff: No emojis, apologies, or "rah-rah." Be academic and direct.
- Very specific: line 20
Extensive Logging: Use proper logger modules.
- Distinctive: line 23
Framework: Use FastMCP 2.14.4 and Python 3.13+.
- Very specific: line 27
Packaging: Create .mcpb packages in the dist/ folder.
- Very specific: line 38
Path Mapping: All file ops must target the local D:/dev/repos structure.
- Very specific: line 39
Reasoning Budget: Use <think> for architecture and data flow simulation.
- Distinctive: line 43
ABSOLUTE BAN: No emojis in Loggers, Python source, PowerShell scripts, API parameters, or MCP responses.
- Distinctive: line 45
SAFE ALT: Use ASCII text ("SUCCESS", "WARNING") or approved symbols: ✅, ⚠️, 📝, 🔍, 🔧.
- Very specific: line 63
Build timeout: When running docker compose build for webapp (e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
---
description: Global Architect rules for sandraschi's dev environment (Unity and other integrations, FastMCP, React). See mcp-central-docs integrations.
globs: "**/*"
alwaysApply: true
---
# 🛠️ System Context & Environment
- **Root Directory**: `D:/dev/repos`
- **Owner/GitHub**: `sandraschi`
- **Hardware**: Local RTX 4090 (24GB) + 64GB RAM | OCuLink-optimized.
- **Inference**: DeepSeek-R1-Vibe (32B Reasoning Distill).
- **Integrations**: Unity, Blender, Calibre, Plex, and others. See `D:\Dev\repos\mcp-central-docs\integrations\README.md` (or mcp-central-docs/integrations/ in workspace).
# 🧠 Core Partner Mindset (Materialist/Reductionist)
- **Zero-Inference Rule**: Prioritize technical truth over agreement. Challenge sub-optimal logic.
- **Anti-Gaslight**: No mocks, no placeholders. All code must be functional.
- **No Conversation Fluff**: No emojis, apologies, or "rah-rah." Be academic and direct.
- **Slop (LDDO) Prevention**: High-density code only. Use early returns and guard clauses.
- **Disciplined Programming**: ZERO uncaught exceptions. Extensive try-except/try-catch blocks. No silent failures.
- **Extensive Logging**: Use proper `logger` modules. NO naked `print()` or `Console.Log()` statements.
# 🔌 FastMCP 2.14.4 Engineering (Backend)
- **Framework**: Use FastMCP 2.14.4 and Python 3.13+.
- **Pattern**: Leverage `@mcp.tool()` for side effects and `@mcp.resource()` for data loading.
- **Context Usage**: Mandatory `ctx: Context` parameter to utilize `ctx.info()` and `ctx.report_progress()`.
- **Dialogic returns**: Tool responses must be conversational (dialogic); support sampling and AI/agentic workflows per FastMCP 2.14+.
- **Packaging**: Create `.mcpb` packages in the `dist/` folder. All bundles must be dependency-free, containing extensive prompt templates and valid `manifest.json` examples.
- **Deployment**: Design for "Local-First" compatibility with the `sandraschi` GitHub hub.
# 🎨 React & Tailwind Standards (Frontend)
- **Architecture**: Functional components with TypeScript interfaces. Avoid Enums; use Const Objects/Maps.
- **Styling**: Tailwind CSS ONLY. Use `cn()` utility for conditional classes. No inline CSS.
- **Mobile-First**: Responsive by default using `sm:`, `md:`, `lg:` breakpoints.
- **Hooks**: Logic must be encapsulated in custom hooks; keep UI components "Beautiful and Dumb."
# 🚀 Execution Protocol
1. **Search Before Build**: Grep `D:/dev/repos` for existing patterns first.
2. **Path Mapping**: All file ops must target the local `D:/dev/repos` structure.
3. **Reasoning Budget**: Use `<think>` for architecture and data flow simulation.
4. **Git Discipline**: Atomic commits only for the `sandraschi` GitHub account.
# 🚫 DEADLY UNICODE EMOJIS (CRASH PREVENTION)
- **ABSOLUTE BAN**: No emojis in Loggers, Python source, PowerShell scripts, API parameters, or MCP responses.
- **ALLOWED**: HTML/UI strings and README.md files only.
- **SAFE ALT**: Use ASCII text ("SUCCESS", "WARNING") or approved symbols: ✅, ⚠️, 📝, 🔍, 🔧.
- **Proof of Read**: hi!
# 🐧 POWERSHELL SYNTAX ENFORCEMENT
- **FORBIDDEN**: `&&`, `||`, `mkdir -p`, `rm -rf`, `cp -r`.
- **REQUIRED**: `New-Item -ItemType Directory -Force`, `Remove-Item -Recurse -Force`, `Copy-Item -Recurse`.
- **Venv**: Use `venv\Scripts\activate`.
# 🌐 Webapp UI/UX Standards
- **Theme**: Dark mode, React, Tailwind; glassmorphism where appropriate.
- **Layout**: Retractable sidebar (state in localStorage); top bar with auth when applicable.
- **Modals**: Logger modal (tail, filter, level); structured help modal (sections, e.g. from help-content).
- **LLM**: Local LLM stack (Ollama/LM Studio); model list/load in Settings; base URL and API key config.
- **Chat**: Floating chatbot with personality presets and LLM prompt refining.
- **API**: Next.js API proxy (same-origin); env `API_URL`, `NEXT_PUBLIC_API_URL`, `NEXT_PUBLIC_APP_URL` for backend/SSR.
- **Feedback**: Error banners with hint (e.g. "Run webapp\\start.ps1"); loading states for async routes.
# 🐳 Webapp Docker
- **Build timeout**: When running `docker compose build` for webapp (e.g. from `webapp/`), use **10 min** (600000 ms) timeout so frontend image build can complete.
Other versions3 projects use a version of this.
Word for word · 3
- sandraschi/blender-mcp★ 63100% same
- sandraschi/advanced-memory-mcp★ 19100% same
- sandraschi/gimp-mcp★ 3100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.