Welcome Aboard CODITECT!

Welcome Aboard CODITECT!

Your journey to AI-powered productivity starts here. Get from zero to productive in under 10 minutes with copy-paste commands.

CODITECT is a universal work automation platform — not just for software development. With 130+ specialized agents and 750+ workflows across 15 domains, it handles business strategy, market research, competitive intelligence, education, content creation, HR, legal, finance, healthcare, real estate, and virtually any knowledge work.

Prerequisites

Before starting, ensure you have:

• Python 3.10+ - Required for scripts and automation
• Git 2.25+ - For version control and submodule support
• Claude Code CLI - Anthropic's official CLI (npm install -g @anthropic-ai/claude-code)
• Terminal access - macOS Terminal, Linux shell, or Windows PowerShell
• 10 minutes - Time to complete initial setup

Verify your setup:

python3 --version   # Should show 3.10+
git --version       # Should show 2.25+
claude --version    # Should show Claude Code version

Quick Start (Copy-Paste Ready)

0. Environment Setup (First Time Only)

# Create virtual environment
python3 -m venv .venv

# Activate it
source .venv/bin/activate  # macOS/Linux
# .venv Scripts activate # Windows

# Install dependencies
pip install -r requirements.txt

1. Start Guided Onboarding

/onboard

Launches the coditect-onboarding agent - a friendly consultant who will:

• Assess your experience level
• Verify your environment (Git, Python, Claude Code)
• Set up your shell with the AI Command Router
• Create your first project
• Teach you the Task Tool Pattern

Alternative modes:

/onboard --quick          # Skip assessments, use smart defaults
/onboard --resume         # Resume from where you left off
/onboard --status         # Check your onboarding progress

2. Create Your First Project

# Standard project creation
/new-project "Build a REST API for task management"

# Guided mode with mentor support (recommended for new users)
/new-project --guided "Build a REST API for task management"

The --guided flag activates the first-project-companion agent with:

• Session check-ins with progress context
• Milestone celebrations
• Help when you're stuck
• Gradual fade-out as you gain confidence

3. Use the AI Command Router

Add this to your shell config (~/.zshrc or ~/.bashrc):

alias cr='claude "/suggest-agent"'
alias cri='claude --interactive "/suggest-agent"'

Then reload:

source ~/.zshrc  # or source ~/.bashrc

Now describe what you want in plain English:

cr "I want to add user authentication"
# → Suggests: /implement or /security-hardening

cr "analyze my database schema"
# → Suggests: database-architect agent

cr "help me debug this error"
# → Suggests: debugger agent

4. Invoke Your First Agent

The Task Tool Pattern is the verified method for invoking specialized agents:

# Business analysis
Task(
  subagent_type="business-intelligence-analyst",
  prompt="Create Product-Market Fit analysis for my SaaS platform"
)

# Technical architecture
Task(
  subagent_type="cloud-architect",
  prompt="Design scalable infrastructure for my application"
)

# Multi-agent orchestration
Task(
  subagent_type="orchestrator",
  prompt="Coordinate complete feature development from requirements to deployment"
)

Key rules:

1. subagent_type = the agent name (e.g., "orchestrator", "debugger", "Explore")
2. prompt = detailed description of what you need
3. Include specific requirements for best results

5. Save Your Session

Before ending work, preserve your context:

# Export session transcript (readable backup)
/export

# Process and index to searchable database
/cx

# Combined: export + process + index in one step (recommended)
/cxs

Why this matters: /export creates a human-readable session transcript. /cx extracts unique messages and indexes them for search. /cxs does both - always run before ending work.

Learn the Platform with /cxq

The /cxq command searches 74,000+ indexed messages. Use it to discover features, find examples, and learn patterns.

Discover Available Agents

# Find agents for a task type
/cxq "agent for database"
/cxq "agent for security"
/cxq "agent for testing"

# Learn what an agent does
/cxq "orchestrator agent examples"
/cxq "debugger agent how to use"
/cxq "code-reviewer capabilities"

Find Command Examples

# Discover commands
/cxq "git-sync examples"
/cxq "new-project options"
/cxq "organize-production usage"

# Learn command patterns
/cxq "how to deploy"
/cxq "how to create project"
/cxq "how to sync submodules"

Learn Implementation Patterns

# Find code patterns
/cxq --patterns --language python
/cxq --patterns --language typescript
/cxq "authentication implementation"
/cxq "API endpoint pattern"

# Find architectural decisions
/cxq --decisions
/cxq --decisions --decision-type api
/cxq --decisions --decision-type database

Troubleshoot Issues

# Find error solutions
/cxq --errors "TypeError"
/cxq --errors "connection refused"
/cxq "how to fix import error"

# Find prior solutions
/cxq "debugging steps"
/cxq "test failures resolved"

Explore the Framework

# Understand components
/cxq "what is a skill"
/cxq "difference between agent and command"
/cxq "component activation why"

# Find workflows
/cxq "workflow for deployment"
/cxq "workflow for code review"
/cxq "multi-agent workflow"

Session Context

# Recent activity
/cxq --recent 50              # Last 50 messages
/cxq --recent 200             # More context
/cxq --today                  # Today's work

# Recall specific topics
/cxq --recall "authentication"
/cxq --recall "database schema"
/cxq --recall "deployment"

Pro tip: The more you use CODITECT, the richer your searchable knowledge base becomes. Every session adds to the collective memory.

Essential Commands Cheat Sheet

Session Management

/cxs                             # Save and index session context
/session-index --verbose         # Scan all sessions for discovery
/process-jsonl-sessions --batch  # Process large session files

Git Workflows

/git-sync --target all --mode full  # Full repository sync
/git-sync --target all --dry-run    # Preview changes
/git-sync --mode analyze            # Analysis only

Project Organization

/organize-production --mode analyze   # Validate structure
/organize-production --mode validate  # Get readiness score (0-100)
/organize-production --mode plan      # Create migration plan
/organize-production --mode migrate   # Execute migration

Component Management

# Activate a component
python3 scripts/update-component-activation.py activate agent NAME --reason "purpose"

# Check status
python3 scripts/update-component-activation.py status agent NAME

# List activated components
python3 scripts/update-component-activation.py list --activated-only

Testing

# Run test suite
python3 scripts/test-suite.py

# Run specific tests
pytest tests/test_onboarding_system.py -v

# Run with coverage
pytest --cov tests/

Popular Recipes

Recipe 1: Start a New API Project

Task(
  subagent_type="orchestrator",
  prompt="Create a complete project plan for a REST API with user authentication, CRUD operations, and PostgreSQL database"
)

Recipe 2: Debug an Error

Task(
  subagent_type="debugger",
  prompt="Investigate this error: [paste error message]. Check logs, trace the issue, and suggest fixes."
)

Recipe 3: Add Authentication

Task(
  subagent_type="security-specialist",
  prompt="Implement JWT authentication with refresh tokens, password hashing, and role-based access control"
)

Recipe 4: Review Code Quality

Task(
  subagent_type="code-reviewer",
  prompt="Review the changes in [file/directory] for security, performance, and best practices"
)

Recipe 5: Deploy to Production

Task(
  subagent_type="devops-engineer",
  prompt="Create a CI/CD pipeline with GitHub Actions, Docker containerization, and Kubernetes deployment"
)

Recipe 6: Market Analysis (Business)

Task(
  subagent_type="business-intelligence-analyst",
  prompt="Create comprehensive market analysis for [your market] including TAM/SAM/SOM sizing, competitive landscape, and pricing strategy"
)

Recipe 7: Competitive Intelligence (Research)

Task(
  subagent_type="competitive-market-analyst",
  prompt="Research top 5 competitors to [your product]. Analyze pricing, features, target audience, and market positioning. Create comparison matrix."
)

Recipe 8: Course Curriculum (Education)

Task(
  subagent_type="ai-curriculum-specialist",
  prompt="Design a 5-module curriculum for [topic]. Include learning objectives, hands-on exercises, assessments, and estimated completion times."
)

Recipe 9: Investment Readiness (Finance)

Task(
  subagent_type="venture-capital-business-analyst",
  prompt="Prepare Series A readiness assessment for [startup]. Include valuation analysis, unit economics review, and investor pitch recommendations."
)

Recipe 10: Content Strategy (Marketing)

Task(
  subagent_type="content-marketing",
  prompt="Create 90-day content marketing strategy for [product]. Include blog topics, social media calendar, SEO keywords, and distribution channels."
)

See all 30 recipes: CODITECT-COOKBOOK.md

Training Pathways

Quick Path (30 minutes)

1. Complete /onboard guided setup
2. Create first project with /new-project --guided
3. Invoke 3 agents using Task Tool Pattern
4. Read CODITECT-COOKBOOK.md

Standard Path (2-3 hours)

1. Complete Quick Path above
2. Read USER-quick-start.md
3. Practice all recipes from Cookbook
4. Complete 30-minute and 2-hour training paths

Certification Path (4-6 hours)

1. Complete Standard Path above
2. Read USER-TRAINING-PATHWAYS.md
3. Complete all 5 modules with assessments
4. Build sample project end-to-end
5. Pass certification exam (80%+ required)

Onboarding Ecosystem Reference

Agents

Agent	Purpose
coditect-onboarding	Dialog-driven onboarding consultant with 7-phase flow
first-project-companion	Post-onboarding mentor with milestone celebrations

Commands

Command	Purpose
/onboard	Start guided onboarding workflow
/new-project	Create new project (supports --guided mode)

Skills

Skill	Purpose
coditect-onboarding	Reusable onboarding patterns and flows
first-project-companion	Mentorship patterns and confidence calibration

Component Quick Reference

┌─────────────────────────────────────────────────────────────────┐
│                    CODITECT COMPONENT MAP                       │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│   🤖 AGENTS        → Specialized AI experts (130+ types)       │
│   ⚡ SKILLS        → Reusable automation patterns (186 sets)   │
│   💻 COMMANDS      → Slash command shortcuts (141 available)   │
│   📜 SCRIPTS       → Python/shell automation (233 files)       │
│   🔧 TOOLS         → Claude Code built-in capabilities         │
│   🔄 WORKFLOWS     → Multi-step processes (750+ across 15 domains) │
│   📖 COOKBOOK      → Ready-to-use recipes (30 patterns)        │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

The 1-2-3 Summary

CODITECT has THREE levels:

1. TELL IT (Commands) → /new-project, /debug
2. ASK EXPERTS (Agents) → database-architect, debugger
3. LET IT WORK (Skills) → automated patterns

The Task Tool Pattern

Task(
  subagent_type="agent-name",  ← The specialist you want
  prompt="detailed request"    ← What you need done
)

Examples:

Task(
  subagent_type="Explore",
  prompt="Find all test files in this project"
)

Task(
  subagent_type="debugger",
  prompt="Investigate the authentication error in login.py"
)

Task(
  subagent_type="orchestrator",
  prompt="Create a project plan for building a REST API"
)

Getting Help

Documentation

• Complete docs index
• Best practices & troubleshooting
• Component reference

Community

• GitHub Discussions - Ask questions
• GitHub Issues - Report bugs

Support

• Email: support@az1.ai (AZ1.AI customers)
• Commercial support plans available

Troubleshooting

Common Setup Issues

Python version too old:

# macOS: Install via Homebrew
brew install python@3.10

# Linux: Use pyenv or apt
sudo apt install python3.10

Claude Code CLI not found:

# Install via npm
npm install -g @anthropic-ai/claude-code

# Verify installation
claude --version

Virtual environment activation fails:

# Ensure you're in the project directory
cd /path/to/coditect-core

# Remove and recreate venv
rm -rf .venv
python3 -m venv .venv
source .venv/bin/activate

Agent not responding:

1. Check activation: python3 scripts/update-component-activation.py status agent AGENT_NAME
2. Activate if needed: python3 scripts/update-component-activation.py activate agent AGENT_NAME --reason "Purpose"

For more issues, see USER-TROUBLESHOOTING.md.

Next Steps

After completing onboarding, explore these capabilities:

1. Memory System - Never lose context with /cx and /cxq commands

   • Memory Management Guide

2. Multi-Agent Orchestration - Coordinate complex workflows

   • Architecture Overview

3. Complete Training - Master all CODITECT capabilities

   • Training Pathways

4. Workflow Library - 750+ ready-to-use workflows across 15 domains

   • Workflow Library Index
   • Business, Research, Education, Finance, Legal, Healthcare, Real Estate, and more

5. Full Capabilities Guide - See everything CODITECT can do

   • CODITECT Full Capabilities

---

Welcome to CODITECT - where AI-powered productivity becomes effortless.

You've got this!

---

Last Updated: December 22, 2025 Version: 1.0.0 Framework: CODITECT v1.7.2