mdan-method 2.6.3

package/README.md

@@ -0,0 +1,233 @@
+# MDAN — Multi-Agent Development Agentic Network
+
+![MDAN](https://i.imgur.com/YwfB0Gx.jpeg)
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+[![Wizards](https://img.shields.io/badge/wizards-25-purple)]()
+[![Agents](https://img.shields.io/badge/agents-29-blue)]()
+[![Packs](https://img.shields.io/badge/packs-3-orange)]()
+
+**MDAN** est un framework de développement piloté par l'IA avec des agents spécialisés, des wizards interactifs step-by-step, un système de mémoire persistante, et un protocole de débat structuré.
+
+**100% gratuit et open source.** 🇲🇦
+
+🇫🇷 [Spécification française](./MDAN.fr.md)
+
+---
+
+## MDAN vs MDAN — Ce qui nous différencie
+
+| Fonctionnalité | MDAN V0 | MDAN |
+|---|---|---|
+| Wizards step-by-step | ✅ | ✅ Même qualité + améliorations |
+| **Mémoire persistante** | ❌ | ✅ MDAN-STATE cross-wizard et cross-session |
+| **Debate Protocol** | Party Mode (informel) | ✅ Protocole formel en 5 rounds avec scoring |
+| **Scale-Adaptive** | Mentionné | ✅ Implémenté — auto-détecte solo/team/enterprise |
+| **Quality Gates adaptatifs** | Statiques | ✅ S'ajustent au scale du projet |
+| **CrewAI** (agents Python réels) | ❌ | ✅ Orchestration multi-agents exécutable |
+| **Universal Envelope** | ❌ | ✅ Format inter-agents standardisé |
+| **Bilingue FR/EN** | English only | ✅ Natif |
+| **Personnalités marocaines** | Noms génériques | ✅ Khalil, Reda, Jihane, Haytame... |
+| Cross-wizard context | ❌ Wizards isolés | ✅ Contexte partagé via MDAN-STATE |
+| Auto-debate on conflict | ❌ | ✅ Déclenché automatiquement |
+
+---
+
+## 🚀 Quick Start
+
+```bash
+# Installation
+npx mdan-ai install
+
+# Ou manuellement
+git clone https://github.com/khalilbenaz/MDAN.git
+cd MDAN && npm install
+```
+
+Puis dans votre IDE (Claude Code, Cursor, Windsurf...) :
+
+```
+/mdan-help        → Que faire ensuite ?
+/discover         → Créer un product brief
+/prd              → Créer un PRD
+/architect        → Concevoir l'architecture
+/dev              → Implémenter une story
+/party            → Multi-agents collaboration
+/debate           → Débat structuré
+/status           → État du projet
+/resume           → Reprendre la session
+```
+
+---
+
+## 📋 Les 25 Wizards
+
+### Phase 1 — Discover
+| Wizard | Commande | Steps | Description |
+|--------|---------|-------|-------------|
+| Product Brief | `/discover` | 6 | Brief produit collaboratif |
+| Research (Market) | `/research market` | 6 | Recherche marché |
+| Research (Technical) | `/research tech` | 6 | Recherche technique |
+| Research (Domain) | `/research domain` | 6 | Recherche domaine |
+
+### Phase 2 — Plan
+| Wizard | Commande | Steps | Description |
+|--------|---------|-------|-------------|
+| Create PRD | `/prd` | 12 | Product Requirements Document complet |
+| Edit PRD | `/prd edit` | 4 | Modifier un PRD existant |
+| Validate PRD | `/prd validate` | 13 | Validation en profondeur |
+| UX Design | `/ux` | 14 | Design UX complet |
+
+### Phase 3 — Architect
+| Wizard | Commande | Steps | Description |
+|--------|---------|-------|-------------|
+| Architecture | `/architect` | 8 | Architecture technique + debate |
+| Epics & Stories | `/epics` | 4 | Découpage en epics et stories |
+| Readiness Check | `/ready` | 6 | Vérifier si prêt pour l'implémentation |
+
+### Phase 4 — Build
+| Wizard | Commande | Steps | Description |
+|--------|---------|-------|-------------|
+| Sprint Planning | `/sprint` | — | Planifier un sprint |
+| Dev Story | `/dev` | — | Implémenter une story |
+| Code Review | `/review` | — | Review structurée |
+| Sprint Status | `/sprint status` | — | État du sprint |
+| Retrospective | `/retro` | — | Rétrospective |
+
+### Phase 5 — Ship
+| Wizard | Commande | Steps | Description |
+|--------|---------|-------|-------------|
+| Deploy | `/deploy` | — | Préparer le déploiement |
+| Document Project | `/docs` | — | Documentation complète |
+| E2E Tests | `/e2e` | — | Générer tests end-to-end |
+
+### Quick Flows
+| Wizard | Commande | Steps | Description |
+|--------|---------|-------|-------------|
+| Quick Dev | `/quick` | 6 | Dev rapide sans planification lourde |
+| Quick Spec | `/spec` | 4 | Spec technique rapide |
+
+### Special
+| Wizard | Commande | Description |
+|--------|---------|-------------|
+| Brainstorming | `/brainstorm` | 12+ techniques de brainstorming |
+| Party Mode | `/party` | Multi-agents dans une session |
+| Debate | `/debate` | Débat structuré en 5 rounds |
+| Retrospective | `/retro` | Rétrospective de sprint |
+
+---
+
+## 🤖 Les 29 Agents
+
+### Équipe principale (MMM)
+| Agent | Nom 🇲🇦 | Rôle |
+|-------|---------|------|
+| PM | Khalil | Product Manager — vision, PRD |
+| Analyst | Amina | Business Analyst — research, brief |
+| Architect | Reda | Architecture système, tech stack |
+| Dev | Haytame | Développement, implémentation |
+| QA | Fatima | Tests, qualité |
+| UX Designer | Jihane | Design UX/UI |
+| Tech Writer | Youssef | Documentation technique |
+| Scrum Master | Nadia | Gestion agile, sprints |
+| Solo Dev | — | Mode rapide tout-en-un |
+
+### Builders (MMB)
+| Agent Builder | Module Builder | Workflow Builder |
+
+### Creative Suite (CIS)
+| Brainstorming Coach | Creative Solver | Design Thinking | Innovation Strategist | Storyteller | Presentation Master |
+
+### Packs spécialisés
+| 💰 **FinTech** | Financial Analyst · Compliance Officer · Risk Manager |
+| ☁️ **DevOps/Azure** | Azure Specialist · CI/CD Architect · DevOps Engineer |
+| 🗄️ **DB Optimization** | Query Optimizer · Indexing Specialist · Performance Analyst |
+
+---
+
+## 🧠 Système de Mémoire (exclusif MDAN)
+
+```
+.mdan/
+├── config/config.yaml          ← Configuration projet
+└── state/MDAN-STATE.json       ← État persistant
+
+Le contexte survit entre :
+✅ Les wizards (le PRD a accès au brief)
+✅ Les sessions (reprise automatique)
+✅ Les agents (décisions partagées)
+```
+
+---
+
+## ⚔️ Debate Protocol (exclusif MDAN)
+
+Quand une décision critique arrive (choix de stack, pattern, priorisation) :
+
+```
+Round 1: Ouverture     → Chaque agent présente sa position
+Round 2: Challenge     → Chaque agent attaque la position adverse
+Round 3: Données       → Preuves concrètes (benchmarks, patterns, risques)
+Round 4: Synthèse      → Position finale intégrant les objections
+Round 5: Scoring       → Score automatique + décision utilisateur
+→ Résultat enregistré dans MDAN-STATE
+```
+
+---
+
+## 📁 Architecture
+
+```
+MDAN/
+├── .mdan/                      # Config + État
+│   ├── config/config.yaml
+│   └── state/MDAN-STATE.json
+├── src/
+│   ├── core/                   # Moteur : master agent, tasks
+│   ├── wizards/                # 25 wizards step-by-step
+│   │   ├── 01-discover/
+│   │   ├── 02-plan/
+│   │   ├── 03-architect/
+│   │   ├── 04-build/
+│   │   ├── 05-ship/
+│   │   ├── quick/
+│   │   └── special/
+│   ├── agents/                 # Définitions YAML des agents
+│   ├── packs/                  # FinTech, DevOps-Azure, DB
+│   ├── memory/                 # Système de mémoire
+│   ├── protocols/              # Debate, Envelope
+│   └── phases/                 # 13 phases (5 manual + 8 auto)
+├── integrations/crewai/        # Agents Python exécutables
+├── prompts/                    # Prompts YAML versionnés
+├── tools/cli/                  # CLI Node.js
+├── docs/                       # Documentation Diataxis
+├── tests/                      # Tests JS + Python
+└── website/                    # Site Astro
+```
+
+---
+
+## 📖 Documentation
+
+| Doc | Contenu |
+|-----|---------|
+| [Getting Started](./docs/tutorials/getting-started.md) | Premier projet |
+| [Installation](./INSTALL.md) | Guide installation |
+| [Usage](./USAGE.md) | Utilisation quotidienne |
+| [Agents](./AGENTS_LIST.md) | Catalogue agents |
+| [Architecture](./ARCHITECTURE.md) | Architecture technique |
+| [MDAN Spec FR](./MDAN.fr.md) | Spécification française |
+| [Contributing](./CONTRIBUTING.md) | Contribution |
+
+---
+
+## 📄 Licence
+
+MIT
+
+---
+
+<p align="center">
+  <strong>25 wizards · 29 agents · 3 packs · Mémoire persistante · Debate Protocol</strong><br>
+  Construit avec 🇲🇦 par <a href="https://github.com/khalilbenaz">@khalilbenaz</a>
+</p>

package/SECURITY.md

@@ -0,0 +1,85 @@
+# Security Policy
+
+## Supported Versions
+
+We release security patches for the following versions:
+
+| Version | Supported          |
+| ------- | ------------------ |
+| Latest  | :white_check_mark: |
+| < Latest | :x:               |
+
+We recommend always using the latest version of MDAN Method to ensure you have the most recent security updates.
+
+## Reporting a Vulnerability
+
+We take security vulnerabilities seriously. If you discover a security issue, please report it responsibly.
+
+### How to Report
+
+**Do NOT report security vulnerabilities through public GitHub issues.**
+
+Instead, please report them via one of these methods:
+
+1. **GitHub Security Advisories** (Preferred): Use [GitHub's private vulnerability reporting](https://github.com/mdan-code-org/MDAN/security/advisories/new) to submit a confidential report.
+
+2. **Discord**: Contact a maintainer directly via DM on our [Discord server](https://discord.gg/gk8jAdXWmj).
+
+### What to Include
+
+Please include as much of the following information as possible:
+
+- Type of vulnerability (e.g., prompt injection, path traversal, etc.)
+- Full paths of source file(s) related to the vulnerability
+- Step-by-step instructions to reproduce the issue
+- Proof-of-concept or exploit code (if available)
+- Impact assessment of the vulnerability
+
+### Response Timeline
+
+- **Initial Response**: Within 48 hours of receiving your report
+- **Status Update**: Within 7 days with our assessment
+- **Resolution Target**: Critical issues within 30 days; other issues within 90 days
+
+### What to Expect
+
+1. We will acknowledge receipt of your report
+2. We will investigate and validate the vulnerability
+3. We will work on a fix and coordinate disclosure timing with you
+4. We will credit you in the security advisory (unless you prefer to remain anonymous)
+
+## Security Scope
+
+### In Scope
+
+- Vulnerabilities in MDAN Method core framework code
+- Security issues in agent definitions or workflows that could lead to unintended behavior
+- Path traversal or file system access issues
+- Prompt injection vulnerabilities that bypass intended agent behavior
+- Supply chain vulnerabilities in dependencies
+
+### Out of Scope
+
+- Security issues in user-created custom agents or modules
+- Vulnerabilities in third-party AI providers (Claude, GPT, etc.)
+- Issues that require physical access to a user's machine
+- Social engineering attacks
+- Denial of service attacks that don't exploit a specific vulnerability
+
+## Security Best Practices for Users
+
+When using MDAN Method:
+
+1. **Review Agent Outputs**: Always review AI-generated code before executing it
+2. **Limit File Access**: Configure your AI IDE to limit file system access where possible
+3. **Keep Updated**: Regularly update to the latest version
+4. **Validate Dependencies**: Review any dependencies added by generated code
+5. **Environment Isolation**: Consider running AI-assisted development in isolated environments
+
+## Acknowledgments
+
+We appreciate the security research community's efforts in helping keep MDAN Method secure. Contributors who report valid security issues will be acknowledged in our security advisories.
+
+---
+
+Thank you for helping keep MDAN Method and our community safe.

package/USAGE.md

@@ -0,0 +1,368 @@
+# MDAN Usage Guide
+
+This guide will help you use MDAN effectively in your development workflow.
+
+## 🚀 Quick Start
+
+### Using MDAN with an AI IDE
+
+MDAN is designed to work seamlessly with AI IDEs like Claude Code and Cursor.
+
+1. **Open your project** in your AI IDE
+2. **Select an agent** from the agent selector
+3. **Provide your task** to the agent
+4. **Review the results** and iterate as needed
+
+### Example: Using the Financial Analyst Agent
+
+```
+You: I need to analyze the financial performance of our SaaS product over the last quarter.
+
+Agent (Financial Analyst): I'll help you analyze the financial performance. Please provide:
+1. Revenue data for the last quarter
+2. Customer acquisition costs
+3. Churn rates
+4. Any other relevant metrics
+
+[Agent processes the data and provides analysis]
+```
+
+## 🤖 Using Agents
+
+### Agent Selection
+
+MDAN provides 23 specialized agents across 4 core modules and 3 specialized packs:
+
+#### Core Module (1 agent)
+- **MDAN Master** - Orchestrates all MDAN agents and workflows
+
+#### MMM Module (9 agents)
+- **Analyst (Mary)** - Research and analysis
+- **Architect (Winston)** - System architecture and design
+- **Dev (Amelia)** - Development and implementation
+- **PM (John)** - Project management
+- **QA (Quinn)** - Quality assurance and testing
+- **Quick Flow Solo Dev (Barry)** - Rapid development
+- **Scrum Master (Bob)** - Agile facilitation
+- **Tech Writer (Paige)** - Technical documentation
+- **UX Designer (Sally)** - User experience design
+
+#### MMB Module (3 agents)
+- **Agent Builder (Bond)** - Create custom agents
+- **Module Builder (Morgan)** - Create custom modules
+- **Workflow Builder (Wendy)** - Create custom workflows
+
+#### CIS Module (6 agents)
+- **Brainstorming Coach (Carson)** - Facilitate brainstorming sessions
+- **Creative Problem Solver (Dr. Quinn)** - Solve complex problems creatively
+- **Design Thinking Coach (Maya)** - Guide design thinking processes
+- **Innovation Strategist (Victor)** - Develop innovation strategies
+- **Presentation Master (Caravaggio)** - Create compelling presentations
+- **Storyteller (Sophia)** - Craft engaging narratives
+
+#### TEA Module (1 agent)
+- **TEA (Murat)** - Test Engineering & Architecture
+
+#### FinTech Pack (3 agents)
+- **Financial Analyst** - Financial modeling and analysis
+- **Compliance Officer** - Regulatory compliance
+- **Risk Manager** - Risk assessment and management
+
+#### DevOps/Azure Pack (3 agents)
+- **DevOps Engineer** - CI/CD and infrastructure
+- **Azure Specialist** - Azure cloud services
+- **CI/CD Architect** - Pipeline design and automation
+
+#### DB Optimization Pack (3 agents)
+- **DB Performance Analyst** - Database performance analysis
+- **Query Optimizer** - Query optimization
+- **Indexing Specialist** - Index design and tuning
+
+See [AGENTS_LIST.md](./AGENTS_LIST.md) for detailed descriptions of each agent.
+
+### Agent Interaction Patterns
+
+#### 1. Sequential Workflow
+
+Use multiple agents in sequence to complete complex tasks:
+
+```
+1. Analyst (Mary) - Research the problem
+2. Architect (Winston) - Design the solution
+3. Dev (Amelia) - Implement the solution
+4. QA (Quinn) - Test the solution
+5. Tech Writer (Paige) - Document the solution
+```
+
+#### 2. Parallel Collaboration
+
+Use multiple agents simultaneously to work on different aspects:
+
+```
+1. UX Designer (Sally) - Design the UI
+2. Dev (Amelia) - Implement the backend
+3. QA (Quinn) - Write tests
+```
+
+#### 3. Specialized Pack Usage
+
+Use specialized pack agents for domain-specific tasks:
+
+```
+FinTech Pack:
+1. Financial Analyst - Analyze financial data
+2. Compliance Officer - Ensure regulatory compliance
+3. Risk Manager - Assess and mitigate risks
+```
+
+## 🎯 Common Use Cases
+
+### Use Case 1: Building a New Feature
+
+```
+1. PM (John) - Define requirements and user stories
+2. Analyst (Mary) - Research similar features and best practices
+3. Architect (Winston) - Design the architecture
+4. UX Designer (Sally) - Design the user interface
+5. Dev (Amelia) - Implement the feature
+6. QA (Quinn) - Write and execute tests
+7. Tech Writer (Paige) - Document the feature
+```
+
+### Use Case 2: Database Optimization
+
+```
+1. DB Performance Analyst - Analyze database performance
+2. Query Optimizer - Optimize slow queries
+3. Indexing Specialist - Design optimal indexes
+4. Dev (Amelia) - Implement optimizations
+5. QA (Quinn) - Verify improvements
+```
+
+### Use Case 3: Cloud Migration to Azure
+
+```
+1. Azure Specialist - Assess current infrastructure
+2. DevOps Engineer - Plan migration strategy
+3. CI/CD Architect - Design deployment pipelines
+4. Dev (Amelia) - Implement migration
+5. QA (Quinn) - Test migrated system
+```
+
+### Use Case 4: Innovation Workshop
+
+```
+1. Brainstorming Coach (Carson) - Facilitate brainstorming
+2. Creative Problem Solver (Dr. Quinn) - Generate creative solutions
+3. Design Thinking Coach (Maya) - Apply design thinking
+4. Innovation Strategist (Victor) - Develop strategy
+5. Presentation Master (Caravaggio) - Create presentation
+```
+
+## 🛠️ Advanced Usage
+
+### Custom Agent Creation
+
+Use the Agent Builder to create custom agents:
+
+```
+You: I need an agent specialized in React Native development.
+
+Agent (Agent Builder): I'll help you create a React Native specialist agent.
+Please provide:
+1. Agent name and title
+2. Key capabilities
+3. Communication style
+4. Specific knowledge areas
+
+[Agent creates the custom agent]
+```
+
+### Custom Workflow Creation
+
+Use the Workflow Builder to create custom workflows:
+
+```
+You: I need a workflow for code review.
+
+Agent (Workflow Builder): I'll help you create a code review workflow.
+Please provide:
+1. Workflow steps
+2. Agents involved in each step
+3. Success criteria
+4. Output format
+
+[Agent creates the custom workflow]
+```
+
+### Integration with MCP Tools
+
+MDAN agents can use MCP tools for enhanced capabilities:
+
+- **Filesystem** - Read and write files
+- **Brave Search** - Search the web
+- **Git** - Perform Git operations
+- **GitHub** - Interact with GitHub
+
+Example:
+```
+You: Search for best practices for React hooks and create a summary document.
+
+Agent (Analyst): I'll search for best practices and create a summary.
+[Uses Brave Search MCP tool]
+[Uses Filesystem MCP tool to create document]
+```
+
+## 📊 Monitoring and Observability
+
+### Agent Activity Logs
+
+MDAN logs all agent activities for monitoring and debugging:
+
+```bash
+# View agent logs
+tail -f logs/mdan.log
+
+# Filter by agent
+grep "Financial Analyst" logs/mdan.log
+
+# Filter by date
+grep "2026-02-28" logs/mdan.log
+```
+
+### Performance Metrics
+
+Track agent performance metrics:
+
+```bash
+# View performance metrics
+npm run metrics
+
+# Export metrics to CSV
+npm run metrics:export
+```
+
+## 🧪 Testing
+
+### Running Tests
+
+```bash
+# Run all tests
+npm test
+
+# Run scenario tests
+npm run test:scenarios
+
+# Run evaluations
+npm run test:evaluations
+
+# Run tests for a specific module
+npm test -- --module mmm
+```
+
+### Writing Tests
+
+Create scenario tests for custom agents:
+
+```python
+from scenario import Scenario, expect
+
+scenario = Scenario("Custom Agent - Test Description")
+
+@scenario.test
+async def test_custom_agent():
+    """Test custom agent functionality."""
+    agent = CustomAgent()
+    request = CustomRequest(field1="value1")
+    result = await agent.process(request)
+    expect(result).to_have_key("expected_key")
+```
+
+## 🎓 Best Practices
+
+### 1. Choose the Right Agent
+
+- Use **Analyst** for research and analysis
+- Use **Architect** for system design
+- Use **Dev** for implementation
+- Use **QA** for testing
+- Use **PM** for project management
+- Use specialized pack agents for domain-specific tasks
+
+### 2. Provide Clear Context
+
+Give agents clear, specific context:
+- ✅ "Analyze the performance of our PostgreSQL database with 1M records"
+- ❌ "Analyze the database"
+
+### 3. Iterate and Refine
+
+Work iteratively with agents:
+1. Provide initial request
+2. Review results
+3. Provide feedback
+4. Refine and iterate
+
+### 4. Use Workflows for Complex Tasks
+
+For complex tasks, use multiple agents in a workflow:
+- Define clear steps
+- Assign appropriate agents to each step
+- Review outputs at each step
+
+### 5. Document Your Work
+
+Use the Tech Writer agent to document:
+- Architecture decisions
+- Implementation details
+- Testing procedures
+- Deployment guides
+
+## 🔧 Configuration
+
+### Agent Configuration
+
+Configure agent behavior in `.env`:
+
+```env
+# Agent Configuration
+MDAN_LOG_LEVEL=info
+MDAN_MAX_CONCURRENT_AGENTS=5
+MDAN_DEFAULT_TIMEOUT=300
+MDAN_ENABLE_CACHING=true
+```
+
+### MCP Tool Configuration
+
+Configure MCP tools in `.mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "filesystem": {
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/project"]
+    }
+  }
+}
+```
+
+## 📚 Additional Resources
+
+- [Installation Guide](./INSTALL.md)
+- [Agent List](./AGENTS_LIST.md)
+- [Architecture Documentation](./ARCHITECTURE.md)
+- [Contribution Guide](./CONTRIBUTING.md)
+- [AGENTS.md](./AGENTS.md) - Agent development guidelines
+
+## 🤝 Getting Help
+
+- Check the [Documentation](./README.md)
+- Search [GitHub Issues](https://github.com/khalilbenaz/MDANV2/issues)
+- Visit the [Repository](https://github.com/khalilbenaz/MDANV2)
+- Check the [npm Package](https://www.npmjs.com/package/mdan)
+
+---
+
+**Last Updated:** 28 February 2026
+**Version:** 1.0.0

package/app/__init__.py

@@ -0,0 +1,5 @@
+"""
+MDAN Application Package
+"""
+
+__all__ = []