Evolution

Module 7: Evolution

You’ve built a working system. The question now is: what comes next, and how do you know when to add more?

This module isn’t a how-to guide. It’s a map of what’s possible and a set of principles for deciding when complexity is worth it.

The Complexity Question

Every feature you add to a system has two costs: the time to build it, and the ongoing mental overhead of maintaining it. A system with too many moving parts becomes fragile and exhausting. You spend your energy tending the system instead of using it.

The right time to add something is when you have specific friction that the addition would remove. Not because something looks interesting. Not because you saw someone else’s setup and wanted the same thing. Because you’re hitting a real limit in your current system, regularly, and the fix is clear.

Signs you’re ready for more:

• You’re running the same multi-step workflow every day and it still requires conscious effort
• You’re capturing information that Claude can’t easily find when you need it
• You’re doing work in Claude that you’re repeating across sessions without saving the result

Signs you’re over-engineering:

• You spend more time configuring the system than using it
• You’ve added a new tool but can’t name what friction it removed
• Your CLAUDE.md is five thousand words and you can’t remember what’s in it

The principle: add when friction is real, not when ambition is high.

What’s Possible

Here’s a tour of what an advanced setup looks like — not to teach it, but to show you the direction.

Custom agents — beyond slash commands, Claude Code can run agents that operate semi-autonomously. An agent might watch your inbox, triage items, and route them to the right project folder without you asking. Agents are powerful and require careful design — they’re acting on your behalf with significant autonomy.

Skills — repeatable behaviours encoded as markdown files in your global Claude configuration. A skill might define how Claude should write in your voice, how it should format a meeting summary, or how it should approach a specific kind of analysis. Skills travel across sessions and projects.

MCP servers — the Model Context Protocol lets Claude connect to external services as first-class tools. Want Claude to query your calendar directly, search the web, or interact with your task manager? MCP servers make that possible. There’s a growing ecosystem of open-source MCP servers for common services.

Hooks — Claude Code supports lifecycle hooks that run automatically at certain points. A pre-session hook might update your vault’s context file with today’s date and recent activity. A post-session hook might log what you worked on. Hooks make the system more ambient — doing useful things in the background without you thinking about them.

Your Path Forward

You don’t need any of the above to have a functioning, valuable co-operating system. The foundation you’ve built in these seven modules — vault, AI connection, daily habits, sync, integrations, commands — is a complete system.

The advanced features exist for when you’ve lived with the basics long enough to know exactly what you’d want to change.

Keep using the system. Pay attention to friction. When friction repeats, that’s a signal. When you have a signal, you’ll know what to build next.

The system gets better as you get better at using it. That’s the compound effect this whole course has been building toward.

You’ve completed the course. Your next step is simply to use what you’ve built.

---

This module evolves as your system does.