agentmods.dev

FounderOS-DEMO: Instructions file for Claude Code

CLAUDE.md

FounderOS-DEMO CLAUDE.md is an instructions file for Claude Code from Bennettxai/FounderOS-DEMO. It costs 2,164 tokens per session, scanned A, original, MIT.

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.

In plain words
What is it for?
Use them when developing, testing, seeding, or changing the architecture of the FounderOS demo.
Why use it?
They give coding agents the project context needed to make changes without bypassing its data layer or breaking its tests and type checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; built for openclaw.

This is Bennettxai/FounderOS-DEMO's own configuration. It tells Claude Code how to work on FounderOS-DEMO itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything FounderOS-DEMO configures →

not rated 796repo +36 14d ago A scan 2,164 tokens original MIT
View source ↗ Bennettxai/FounderOS-DEMO thefounderos.com
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.

agentmods badge for FounderOS-DEMO CLAUDE.md

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.

agentmods 80×15 button for FounderOS-DEMO CLAUDE.md

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 2,164 This file is loaded in full into every session.
When invoked 2,164 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02164 $0.02164
Opus 5 $0.01082 $0.01082
Sonnet 5 $0.00433 $0.00433
Haiku 4.5 $0.00216 $0.00216

Measured 9d ago against content hash 47605deab3a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FOUNDER OS

Personal OS / AI agent command center. Live web recreation of the FounderOS "Conducting AI" board. Runs on port 4100 (command-center owns 4000).

Commands

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

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: larp-first, real-ready

This is the load-bearing design rule. v1 looks alive 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 seeded tables for live sources (Attio, Zernio, OpenClaw, MCP status) is a repo-level change. Keep it that way: new data = new repo method + Zod schema + seed entry + test.

G-Brain — ANSWERED (2026-06-11)

G-Brain = GBrain v0.41 (gbrain CLI on PATH): markdown knowledge in ~/knowledge/brain-store/ + Supabase backend ("Second Brain", free tier — pauses on idle) + ZeroEntropy embeddings (key in ~/.config/knowledge/config.json). The real provider in lib/connectors/gbrain.ts shells out to the CLI (doctor --json --fast, query --no-expand) and falls back to local brain-store grep when the database is unreachable. Default BRAIN_PROVIDER=gbrain; stub exists for tests.

Real connectors & agents (v2)

Alex's directive: real integrations, not larp. Strict black & white theme (UI polish deferred — he'll design it himself once everything is wired).

  • lib/connectors/ — 12 connector groups, all returning honest ConnectorStatus (never fake "connected"): email.ts (4 IMAP slots), slack.ts, payments.ts (Stripe + registry), notion.ts, gbrain.ts, zernio.ts (key from ~/.config/social/.env — LIVE), attio.ts (key reused from ~/.config/mcp.json mcpServers — LIVE), arcads.ts (local .env — LIVE), miro.ts (knowledge/.env.agents — LIVE), wispr.ts (local flow.sqlite readonly — LIVE), obsidian.ts (vault fs; needs macOS Documents permission), local-stack.ts (local service ports
    • tmux + brew binaries).
  • lib/creds.ts — credential resolution: process.env first, then Alex's canonical files at runtime. NEVER copy secret values into this repo.
  • lib/agents/runtime.ts + real.ts — agent registry; every seeded agent row maps 1:1 to a RuntimeAgent with a real run() (enforced by seed tests). Runs persist to agent_runs. POST /api/agents/[id]/run.
  • /integrations is the live Connections board (GET /api/connections).
  • Credentials go in .env.local (gitignored) — see .env.example. NEVER commit keys; never copy keys from ~/knowledge/.env.agents into the repo.

Read the full file on GitHub · 147 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.

  1. 9d 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 (796 stars, last pushed 14d ago), licensed MIT. It adds 2,164 tokens to every session, about $0.0108 per session on Opus 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 agentsai-agentsdashboardfounder-osnextjsopen-sourceoperator-os
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens