Day 40

Founder OS — Full System

Day 39 Day 41

The Complete System — 30-Day Claude Code Series

The Founder OS

Five layers. One terminal. Your entire company — organised, connected, and ready for Claude to navigate.

CLAUDE.md

Teaches Claude who you are, every session

What it is

A markdown file that lives in your project root. Claude reads it automatically at the start of every session. It is the single source of truth about you, your business, and how Claude should behave.

What to put in it

Your business context — what you do, who you serve, how you price
Your active client list and their status
Your tech stack and tools
How Claude should behave — be direct, no fluff, ask before committing
What to avoid — no emojis, no over-promising, no vague suggestions

Structure

Who I am — identity, values, communication style
Current projects — clients, products, priorities
How Claude should work with me — rules, preferences, things to avoid

Example

# CLAUDE.md

## Who I Am
Name: Walid Boulanouar
Business: AY Automate — AI automation agency
Role: Founder, builder, systems thinker

## Current Projects
- 13 active clients across EU, US, MENA
- Building Humanoidz venture studio
- Scaling to 20 clients / 80K MRR

## How Claude Should Work With Me
- Be direct. No fluff. No apologies.
- Ask clarifying questions before assuming.
- Never commit to git without asking.

Time to set up

30 minutes for a solid first version. Iterate as your business evolves.

Without it: Claude asks the same questions every session. With it: Claude already knows.

MEMORY.md

Persistent context that builds over time

What it is

A file stored at ~/.claude/projects/.../memory/MEMORY.md. Claude reads it automatically every session and can write to it when you say "remember this." It grows with you.

Four memory types

User memory — who you are, preferences, quirks that Claude learns
Feedback memory — corrections you have made. "Never do X again." "Always format it like Y."
Project memory — ongoing work context. Client statuses, sprint progress, blockers
Reference memory — where to find things. File paths, tool configs, API endpoints

What makes it powerful

No manual copy-pasting between sessions
Corrections stick — tell Claude once, it remembers
Project state carries forward — no re-explaining what happened last week
Reference paths mean Claude finds files without asking you

Without it: Every session starts cold. With it: Claude remembers what you told it last week.

MCP Connections

Gives Claude hands to act in external tools

What it is

Model Context Protocol servers. They are bridges between Claude and external tools. Each MCP exposes specific actions — read, write, search, send — that Claude can call directly from the terminal.

The 24 MCPs

Attio — CRM. Read contacts, deals, pipeline. Update records.
Slack — Comms. Read channels, send messages, search history.
Notion — Docs. Read pages, query databases, create entries.
Unipile — LinkedIn. Send DMs, read profiles, publish posts.
Anysite — Web. Fetch any URL, scrape content, read docs.
GitHub — Code. Read repos, create PRs, manage issues.
n8n — Automation. Trigger workflows, read executions, manage nodes.
Filesystem — Files. Read, write, search across your local system.
Gmail — Email. Read inbox, send replies, search threads.
Google Calendar — Schedule. Read events, create meetings, check availability.
Google Drive — Docs. Read and write files, search by content.
Zapier — 5000+ apps. Trigger any Zapier zap from the terminal.
Linear — Project. Read issues, update status, create tasks.
Supabase — Database. Query tables, insert rows, manage auth.
Resend — Email API. Send transactional emails programmatically.
PostHog — Analytics. Query events, funnels, user sessions.
Stripe — Payments. Read subscriptions, invoices, MRR snapshots.
Twilio — SMS. Send messages, read delivery status.
Airtable — Spreadsheets. Read bases, create records, filter views.
Webflow — CMS. Publish pages, update collections, trigger deploys.
YouTube — Video. Search, get transcripts, analyse metrics.
Canva — Design. Generate and update designs programmatically.
Figma — UI. Read and comment on design files.
Vercel — Deploy. Trigger builds, read logs, manage env vars.

How it works in practice

You say "check the pipeline in Attio for deals closing this week." Claude calls the Attio MCP, reads the data, and returns a summary. No browser, no tab-switching, no copy-pasting.

Without it: Claude can only see what you paste. With it: Claude reads your CRM, Slack, and files directly.

Hooks

Safety rules that run automatically before and after Claude acts

What it is

Shell scripts that trigger on specific Claude actions. They run before a tool is used (PreToolUse), after it completes (PostToolUse), or when the session ends (Stop). Think of them as guardrails.

The 6 hooks

bash-safety.sh — Blocks destructive git commands: force push, reset --hard, branch -D, rm -rf. Prevents accidental data loss.
file-protection.sh — Blocks edits to .env files and credentials. Warns before modifying CLAUDE.md, MEMORY.md, or settings.json.
file-backup.sh — Creates a backup copy before every file edit. Keeps the last 10 versions in ~/.claude/backups/.
search-year.sh — Automatically appends the current year to web searches that are missing a date. Keeps results fresh.
file-logger.sh — Logs every file change to a daily changelog. Full audit trail of what Claude touched.
stop-notify.sh — Plays a sound when Claude finishes working. Walk away and come back when it is done.

How it works in practice

Before Claude runs git push --force, bash-safety blocks it. Before Claude edits a config file, file-protection warns you. After every edit, file-backup saves a copy. The system protects itself.

Without it: Claude can accidentally destroy git history or edit secrets. With it: Protected by default.

Skills

Reusable agents for specific tasks — type to trigger

What it is

Markdown files stored in .claude/skills/ that define a complete Claude workflow. Each skill has a trigger phrase, input requirements, step-by-step instructions, and output format. One command triggers the full workflow.

25+ skills across 6 categories

Sales — /personalized-value-outreach — Research a prospect, score against ICP, draft a value-first DM, send via Unipile
Content — /yt-to-content — Extract a YouTube transcript, generate 3 LinkedIn posts in different formats
Client — /meeting-processor — Process a meeting transcript into action items, client notes, and follow-up tasks
Intelligence — /content-intelligence — Analyse your LinkedIn performance, extract patterns, suggest what to double down on
Technical — /excalidraw-diagram — Generate architecture diagrams from text descriptions
Operations — /sop — Turn any task into a step-by-step Standard Operating Procedure for the team
Design — /nano-banana — Generate on-brand images, LinkedIn covers, infographic assets
Research — /clay-outreach — Token-efficient prospect research pipeline using Unipile + Clay
Deploy — /deploy-to-vercel — Ship any project to Vercel with one command
SEO — /general-blog-post — Plan, research, and draft a full SEO blog article

How it works in practice

A skill reads CLAUDE.md for your voice and business context. It checks MEMORY.md for client history. It calls MCPs to fetch data from Attio or send messages via Unipile. Hooks keep it safe the entire time.

Without it: You describe the task every time. With it: One command triggers the full workflow.

PARA Folder Structure

Your file system — organized for Claude to navigate instantly

Projects

Active work with a deadline

13 active client folders
Each with brief, assets, deliverables, comms log
Claude navigates by client name

Areas

Ongoing responsibilities

Sales pipeline
Content calendar
Finance + MRR tracking
Team + hiring

Resources

Reference material

SOPs and playbooks
Templates and scripts
Research and frameworks
Tool configs

How they work together

Claude reads CLAUDE.md + MEMORY.md — context loaded. It knows who you are, what you are working on, your preferences, and your corrections from past sessions.

Hooks protect the session — safety active. Destructive commands are blocked, sensitive files are guarded, every edit is backed up and logged.

You trigger a skill — Claude uses MCPs to act on your tools. It reads your CRM, drafts a message in your voice, sends it through LinkedIn, and logs the action. One command, full execution.

The result: 90 seconds to retrieve any context. 40 minutes of morning orientation eliminated.

Day 39: Hooks From Zero to Production

Day 41: 12 Agent Primitives — The Leak Decoded