~20 minute setup  ·  Mac / Windows / Linux

Turn your laptop into an AI Operating System.

Second-Brain OS wires Claude Code into your files, your calendar, your inbox, and a structured second brain that remembers what you're working on. The tools install themselves. Your job is to show up.

We build harnesses because managing context is the hard part of working with AI. Every prompt to a vanilla chatbot is a cold start. The Second-Brain OS gives Claude persistent memory of you, your tools, your work — so every conversation picks up where the last left off.

§1 · Foundation

What is Second-Brain OS?

You already know what an OS is — macOS, iOS, Windows. The layer between you and your computer where everything lives. You don't think about it because it just works.

Now add AI on top. Agents. Persistent memory. Reasoning that runs while you sleep. The OS doesn't just hold your files — it can see them, connect them, and act on them. It can read your inbox, scan your calendar, draft your reply, remember what you said in a meeting three weeks ago, and tell you what matters this morning.

That's Second-Brain OS — your AI Operating System. It's what this onboarding builds.

You Second-brain harness (CLAUDE.md · memory · skills · hooks) Claude Code (the agent runtime) Tools (CLI · MCP · API) Your data · files · email · calendar · code · meetings
Second-Brain OS sits between you and your data — agent runtime + harness + tools.

The four C's

Build in this order. You can't have Cadence without Connections. You can't have Capabilities without Context.

C1
Context
What the AI knows about you, your team, your voice, your business. Lives in SOUL.md, USER.md, project memory.
C2
Connections
What data it can reach. MCP servers, CLIs (gws, gh, databricks), APIs.
C3
Capabilities
What it can produce — write a briefing, scaffold a project, summarize a meeting. Encoded as skills.
C4
Cadence
When it acts on its own. Skills you invoke. Hooks on file events. Crons on a schedule.

The durable layer

Claude Code today. Codex tomorrow. Something else next year. The tools churn — that's fine.

What survives is the harness: the folder structure, the CLAUDE.md + memory.md discipline, the skills you wrote, the context you accumulated. Port that to whatever agent comes next and you're moved-in within an hour. That's the real asset you're building. The agent runtime is just the host.

The point

You're not learning a tool. You're building a layer of durable, agent-readable context about your work. The tool is replaceable. The layer is not.

How you'll know each pillar is real.

Abstractions are easy. Tests are hard. Here's how to verify your Second-Brain OS actually works after install.

Pillar Test Pass signal Fail signal
Context Ask "who am I?" Reads like a teammate. Reads like a stranger.
Connections Ask "what's on today?" Live answer in seconds. It asks you to paste.
Capabilities Type a 7-word brief. Multi-step artifact returns. It asks for clarification.
Cadence Close laptop. Wait. Output lands without you. Output never arrives.

If a pillar can't be tested, it's not in place. The framework only counts what survives a real prompt.

§2 · Mindset

Before you install anything.

The install is the easy part — 20 minutes of typing. The mindset is the hard part. Get this wrong and you'll abandon the system in week two.

The three M's

Three layers of AI adoption. Most people skip the first two and wonder why the third doesn't stick.

M1
Mindset
The habits below. The default-shift, the function-breakdown, the curiosity rule. This is the work that has to happen between your ears, not on your laptop.
M2
Method
How you decide what's worth automating. Not everything is. Eliminate the work first; then automate what's left; then delegate.
M3
Machine
The technical layer — what this onboarding installs. Useless without the other two.
In that order
Buying the gym membership doesn't make you fit. Installing Second-Brain OS doesn't make you faster. The habits do.

Three habits to install in your head

1. The default-shift habit

Every time you start a task — drafting a doc, replying to a thread, prepping a meeting, scanning a CSV — ask one question first: "Could AI do this for me — even 30% of it?"

30% is the magic number. You're not asking "can AI replace me on this?" You're asking "can it remove the boring part?" Half the time the answer is yes. Most of the time you discover it can do 70%. You just have to ask before you start.

2. The function-breakdown habit

Your job is a tree. The trunk is your role. The branches are the things you do — write briefs, run meetings, analyze data, manage stakeholders. The leaves are the individual atomic tasks under each branch.

Don't try to automate the trunk. You can't. Automate one leaf at a time. Pick the most boring leaf this week. Build a skill or workflow for it. Move on. Six months in, half your leaves are agent-driven and you got there one leaf per week.

3. The curiosity rule

AI is a mentor, not a vending machine. The vending-machine pattern is: type a question, copy the answer, close the tab. The mentor pattern is: type a question, read the answer, ask "why?", ask "what did you skip?", ask "what would you do differently if X?".

You learn ten times faster the mentor way. And you build a working model of why the system does what it does, which is what makes you good at directing it.

The productivity dip is real

When you adopt this system, expect a 20% productivity drop for the first three to five days. You're learning new commands, building new habits, debugging new tools. It feels worse before it feels better.

baseline +50% 0% -20% day 0 5 10 20 30 Don't give up here days since adoption
Three-to-five-day dip, then a fast climb. Most people quit during the dip.

Then it climbs. By day ten you're back to baseline. By day twenty you're 30-50% above. By day sixty you don't remember how you worked the old way.

The trap

Most people quit on day four — right at the bottom — because they were sold "instant productivity gains." It's not instant. It's a J-curve. Plan for the dip. Push through it.

§3 · Architecture

How Second-Brain OS is structured.

The harness is opinionated. The opinions exist because the alternative — a freeform AI workspace with no rules — collapses into chaos within a month.

The operating principles

Six rules. They sit above any individual skill. When you're not sure what to do, return to these.

1. Connect before create
Before scaffolding anything new — a project, a doc, a skill — search first. Run /find <topic> across Projects, Resources, Archive, and memory. The whole point of a second brain is knowing what already exists. Creating duplicates breaks that.
2. Revive before scaffold
If existing work is in 4-Archive/, move it back. Flip its status from done to active. Don't clone a fresh project-v2. Lineage matters.
3. Eliminate before automate
Three M's of efficiency: Eliminate, Automate, Delegate — in that order. Before you build a skill, ask: can this work just stop happening? Can a written rule cover it? Don't automate things that should be discipline.
4. Consolidate before duplicate
When the same content lives in two files, one is the source of truth and the other points at it. Pick one. Drift kills second brains faster than anything else.
5. Reference, don't reproduce
Schema lives in one file. Skills link to it. Configuration tokens live in CLAUDE.md. Copies drift. Single source of truth scales.
6. Capture before commit
When a thought, file, or folder is uncertain — "is this a project or just an idea?" — it goes to 0-Inbox/. Not 1-Projects/. Projects are for things that earned the scaffold. Skipping Inbox creates the unmigrated-folder graveyard the whole system exists to prevent.
Underneath all of it

Boring is beautiful. Predictable beats clever. Push autonomy up only after the lower level is proven.

The two-file rule

Every active project has exactly two meta-files. Not three. Not five.

Research finding from running this for months: more than two meta-files per project = bloat and abandonment within weeks. People stop opening the folder. The project goes cold. The lesson generalizes — keep the meta thin so the work can be heavy.

PARA — the folder model

Five folders. That's the whole organizational schema. Inspired by Tiago Forte's PARA, simplified for an agent-native workflow.

0-Inbox capture 1-Projects active work 2-Coding code repos 3-Resources reference 4-Archive done capture → promote → reference → archive
Five folders. Capture in Inbox; promote to a Project or Resource; archive when done.
Next
See what's inside — architecture, files, memory, hooks
Architecture →