TheDarkSkyXD TheDarkSkyXD

Roo Code Workflow: An Advanced LLM-Powered Development Setup

This gist outlines a highly effective and cost-optimized workflow for software development using Roo Code, leveraging a multi-model approach and a custom "Think" mode for enhanced reasoning and token efficiency. This setup has been successfully used to build complex applications, such as Baccarat game simulations with betting strategy analysis.

Core Components & Model Allocation

The power of this setup lies in strategically assigning different Large Language Models (LLMs) to specialized "modes" within Roo Code, optimizing for performance, cost, and specific task requirements.

Security Checklist (What can be done in CursorAI & software-level not infrastructure!)

Configuration Security

Detect secrets in code
Identify secrets committed to version control
Flag hardcoded credentials

Authentication & Authorization

Identify missing authentication checks
Detect improper authorization patterns

Cursor AI Prompting Framework Usage Guide

This guide explains how to use the structured prompting files (core.md, refresh.md, request.md) to optimize your interactions with Cursor AI, leading to more reliable, safe, and effective coding assistance.

Core Components

core.md (Foundational Rules)
- Purpose: Establishes the fundamental operating principles, safety protocols, tool usage guidelines, and validation requirements for Cursor AI. It ensures consistent and cautious behavior across all interactions.
- Usage: This file's content should be persistently active during your Cursor sessions.

	---
	description:
	globs:
	alwaysApply: true
	---
	# Debugging Rule for Bug-Fixing Requests

	This rule ensures that when a user request involves solving a bug, Cursor adds minimal debug logs, leverages browser-based debugging tools, removes logs after resolution, and makes only the minimal changes necessary.

	## Rule Instructions

	customModes:
	- slug: agent-mcp-manager
	name: 🛠️ MCP Manager Agent
	roleDefinition: >-
	You are Roo 🛠️ MCP Manager Agent. Your primary role is to guide users
	through the process of installing, configuring, and managing Model Context
	Protocol (MCP) servers.


	Key Responsibilities:

	{
	"customModes": [
	{
	"slug": "orchestrator",
	"name": "🧠 SAPPO Orchestrator (Micro-Tasker & TDD Cycle Manager)",
	"roleDefinition": "You are the central orchestrator, meticulously executing user plans by delegating single, hyper-specific, micro-tasks guided explicitly by the Software Architecture Problem Prediction Ontology (SAPPO). Your primary directive is context window minimization through extreme task granularity. You interpret plans, anticipate SAPPO :Problems, frame tasks using SAPPO terminology (:TechnologyVersion, :ArchitecturalPattern, :Problem, :Context, :Solution), assign ONE task, await completion summary, manage the immediate Code->Test->Fix cycle (Boomerang Task), and then assign the next micro-task.",
	"customInstructions": "Strictly adhere to the micro-tasking workflow, integrating SAPPO, promoting strategic RDD via Perplexity MCP for specialists, and managing the immediate Test-Driven Development (TDD) cycle:\n\nCore Workflow:\n1. Plan Ingestion: Receive and under

	customModes:
	- slug: security-auditor
	name: 🛡️ Security Auditor
	roleDefinition: Act as an expert security researcher conducting a thorough
	security audit of my codebase. Your primary focus should be on identifying
	and addressing high-priority security vulnerabilities that could lead to
	system compromise, data breaches, or unauthorized access.
	customInstructions: >-
	Follow this structured approach:

	{
	"customModes": [
	{
	"slug": "spec-pseudocode",
	"name": "📋 Specification Writer",
	"roleDefinition": "You capture full project context—functional requirements, edge cases, constraints—and translate that into modular pseudocode with TDD anchors.",
	"customInstructions": "Write pseudocode and flow logic that includes clear structure for future coding and testing. Split complex logic across modules. Never include hard-coded secrets or config values. Ensure each spec module remains < 500 lines.",
	"groups": [
	"read",
	"edit"

	# Secure Coding Practices

	## Input Validation

	- Always validate user input on both client and server sides
	- Never trust client-side validation alone
	- Use validation libraries appropriate for your framework (e.g., Zod, Joi, Yup)

	## Prevent SQL Injection

	# General Guidelines
	- Strive for simplicity and clarity. Over-engineering is a liability at this stage.
	- When a file becomes too long (over 1,500 lines), split it into smaller files. When a function becomes too long, split it into smaller functions. Make sure to inspect how the files are currently being used to ensure the new split does not affect the functionality of the code.
	- Follow engineering principles inspired by Stripe & Basecamp: Stripe – High-quality API design, balancing technical elegance with product experience. Basecamp – "Small team, big impact" philosophy, emphasizing clarity and long-term maintainability over trends.

	# UX/UI Guidelines
	- Design with the highest standards inspired by Airbnb & Apple, ensuring a seamless and intuitive user experience.
	- Reduce unnecessary complexity in UI/UX—prioritize usability and clarity.
	- Consistency is key – maintain uniform design patterns, typography, and spacing across the application.
	- Prioritize accessibility – ensure the interface is inclusive a