Set up Claude Code, configure your project brain, and understand the framework that powers everything you will build in this course.
In this module
An AI Creator OS is a personal operating system for creative work, powered by AI agents, automation workflows, and structured knowledge. It handles the repetitive parts of building -- content production, research, distribution, scheduling -- so you can focus on craft.
Large enterprises invest heavily in AI Centers of Excellence -- dedicated teams with strategy, governance, technology, and ethics frameworks. The same 6-pillar architecture that powers enterprise AI adoption can be applied to individual creators at roughly 1/5000th of the cost.
That is the core insight behind this course. You do not need a team of 50. You need a well-configured system and the discipline to use it.
Claude Code is a terminal-based AI assistant from Anthropic. It reads your project files, understands your codebase, and executes multi-step tasks with real tools -- file editing, git operations, API calls, and more. It is the foundation of everything in this course.
Unlike ChatGPT or Cursor, Claude Code operates directly in your terminal with full filesystem access. It reads your entire project context on every interaction via CLAUDE.md files. It supports custom skills, slash commands, hooks, and MCP tool connections. This means your AI assistant gets smarter the more you configure it -- and it remembers your preferences across sessions.
You need Node.js 18+ installed. Then run a single command:
npm install -g @anthropic-ai/claude-codeNavigate to any project directory and type claude in your terminal. Claude Code will scan your directory, read any CLAUDE.md files it finds, and start an interactive session.
cd ~/my-project
claudeOn first run, you will authenticate with your Anthropic API key. After that, Claude Code loads automatically with your project context.
The single most important file in any Claude Code project is CLAUDE.md. Claude reads this file at the start of every session. It contains your project configuration, brand voice, file structure, coding standards, and any rules you want Claude to follow. Think of it as persistent memory that shapes every interaction.
Create a file called CLAUDE.md in your project root. This is the template to start with -- customize each section for your own work.
# Project Configuration
## Who I Am
- Name: [Your name]
- Role: [Your primary role — creator, developer, founder, etc.]
- Brand: [Your brand name or handle]
- Voice: [2-3 adjectives — e.g. "precise, confident, practical"]
## Brand Voice
- Lead with results, not philosophy
- Use precise technical language
- Show, don't tell — let the work speak
## Key Files
- content/blog/ — All blog posts (MDX)
- lib/ — Utilities and shared logic
- components/ — React components
- data/ — JSON data files
## Standards
- TypeScript strict mode
- Tailwind CSS for styling
- Next.js App Router conventions
- Mobile-first responsive designGive Claude your identity context. This shapes how it writes copy, structures content, and represents your brand. Be specific about your role and voice.
Define the rules for how Claude communicates on your behalf. These guidelines apply to every piece of content it generates -- blog posts, emails, documentation, code comments.
Map the critical directories and files in your project. Claude uses this to navigate your codebase efficiently, especially in large projects with hundreds of files.
Set technical constraints. What framework, what language features, what design patterns. Claude follows these rules when writing or modifying code.
Claude Code loads CLAUDE.md files hierarchically. A root CLAUDE.md applies to the entire project. You can also place CLAUDE.md files in subdirectories -- they add context for that specific area. For example, components/CLAUDE.md can define component-specific rules that only activate when Claude works in that directory.
ACOS stands for Agentic Creator OS. It is the framework that structures your entire AI creator workflow into a coherent system. ACOS applies the same 6-pillar architecture used by enterprise AI Centers of Excellence, adapted for individual creators.
Define what you want AI to do for you. Goals, priorities, and constraints.
Quality checks, review processes, and guardrails for AI output.
Your skills as an AI operator. Prompt craft, tool mastery, agent design.
The stack: Claude Code, n8n, MCP servers, Vercel, databases.
Content libraries, knowledge bases, brand assets, and training data.
Transparency, attribution, bias awareness, and responsible use.
Each pillar translates directly into actions you take every day:
The ACOS framework is open source. You can explore the full architecture, contribute, or fork it for your own use.
github.com/frankxai/agentic-creator-osYou now have the foundation: Claude Code installed, your first CLAUDE.md configured, and an understanding of the ACOS framework. Module 2 goes deeper into the skill system -- how to install, create, and manage hundreds of specialized AI skills.
Learn how to install skills from GitHub repositories, create custom skills for your specific workflows, set up auto-activation with skill-rules.json, and build a library of 500+ specialized AI capabilities.
Coming SoonJoin the course waitlist for early access to new modules, bonus content, and implementation resources.