What is FounderOS-DEMO CLAUDE.md?

Project instructions for FounderOS, a web-based personal command center for AI agents. They describe its commands, software stack, database structure, and rule that pages read data through shared repository code.

Use them when developing, testing, seeding, or changing the architecture of the FounderOS demo.

They give coding agents the project context needed to make changes without bypassing its data layer or breaking its tests and type checks.

How Bennettxai/FounderOS-DEMO configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Bennettxai/FounderOS-DEMO. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Bennettxai/FounderOS-DEMO/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Bennettxai/FounderOS-DEMO

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bennettxai/founderos-demo/claude-md/github.svg)](https://agentmods.dev/instructions/bennettxai/founderos-demo/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bennettxai/founderos-demo/claude-md"><img src="https://agentmods.dev/badge/instructions/bennettxai/founderos-demo/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bennettxai/founderos-demo/claude-md"><img src="https://agentmods.dev/badge/instructions/bennettxai/founderos-demo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,138 This file is loaded in full into every session.

When invoked 2,138 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02138	$0.02138
Opus 5.5	$0.00855	$0.00855
Sonnet 5.5	$0.00428	$0.00428
Haiku 4.5	$0.00214	$0.00214

Measured 1mo ago against content hash 3d0d59dc07ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

FounderOS-DEMO CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FOUNDER OS

Founder OS is a personal operating system for a one-person business: a web command center that runs a company as a set of AI-assisted departments. This file is the contributor guide for anyone (human or agent) working in the repo.

Runs on port 4100.

Commands

npm install
npm run dev        # dev server → http://localhost:4100
npm test           # vitest suite (must stay green)
npm run typecheck  # tsc --noEmit
npm run seed       # re-seed data/founder-os.db (idempotent)
npm run build && npm start

Node 22 is the supported runtime.

Stack

Next.js 14 App Router (server components) + TypeScript + Tailwind + better-sqlite3 (data/founder-os.db, WAL, auto-seeded on first touch) + Zod + Vitest.

Architecture: demo-first, real-ready

This is the load-bearing design rule. The app looks alive out of the box because of rich seeded data, but every page and API route reads through the repository layer. Never query SQLite directly from a page or route:

lib/data.ts — getDb() app singleton; seeds on first touch
lib/db.ts — openDb() + repos (departments, agents, metrics, tools, …)
lib/seed.ts — all seeded content lives here
lib/schemas.ts — Zod schemas validate every row on the way OUT of the DB

Swapping a seeded table for a live source is a repo-level change. Keep it that way: new data = new repo method + Zod schema + seed entry + test.

Connectors and agents

lib/connectors/ — one module per integration group (email over IMAP, chat, payments, CRM, knowledge, social, calendar, local services). Every connector returns an honest ConnectorStatus and never reports a fake "connected". With no credentials configured they degrade to a clearly-labelled disconnected state rather than failing the page.
lib/creds.ts — credential resolution. Reads process.env first. Never commit a secret value or paste a key into the repo.
lib/agents/runtime.ts + real.ts — the agent registry. Every seeded agent row maps 1:1 to a RuntimeAgent with a real run() (enforced by the seed tests). Runs persist to agent_runs via POST /api/agents/[id]/run.
/integrations is the live connections board (GET /api/connections).
Credentials go in .env.local (gitignored). See .env.example.

Read the full file on GitHub · 148 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · -23 tokens per session 3d0d59dc07ba
1mo ago Changed · +1 lines · -3 tokens per session ea7c92eb833f
2mo ago First seen · 147 lines · 2,164 tokens per session scan A 47605deab3a3

Subscribe to this mod's changes

FounderOS-DEMO CLAUDE.md is an instructions file published in the GitHub repository Bennettxai/FounderOS-DEMO (996 stars, last pushed 1mo ago), licensed MIT. It adds 2,138 tokens to every session, about $0.0086 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents ai-agents dashboard founder-os nextjs open-source operator-os

FounderOS-DEMO CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
FounderOS-DEMO CLAUDE.mdBennettxai/FounderOS-DEMO	Instructions file	996	1mo ago	MIT	A	2,138	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

FounderOS-DEMO: Instructions file for Claude Code