Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/arcassystems/founderos/claude-mdgit clone --depth 1 https://github.com/ARCASSystems/FounderOSWrote 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.
[](https://agentmods.dev/instructions/arcassystems/founderos/claude-md)<a href="https://agentmods.dev/instructions/arcassystems/founderos/claude-md"><img src="https://agentmods.dev/badge/instructions/arcassystems/founderos/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.09025 | $0.09025 |
| Opus 5 | $0.04512 | $0.04512 |
| Sonnet 5 | $0.01805 | $0.01805 |
| Haiku 4.5 | $0.00903 | $0.00903 |
Grade A, and why
FounderOS 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder OS - Claude Code Plugin
This is the generic Founder OS plugin. Install it to give Claude Code the context of who you are, how you work, what you are building, and what you need help with. It replaces 20+ productivity SaaS tools with a single structured Claude Code environment.
What This Is
Founder OS is a Claude Code plugin that installs an operating system for one founder: your identity, your roles, your priorities, your cadence, your scars - so the AI you work with stops treating you like an anonymous user and starts working like a chief of staff who has been with you for five years.
It is NOT a framework. It is NOT a multi-tenant AI platform. It is a product you install once and run every day.
Positioning non-negotiables
- The public Founder OS product is single-founder software. ARCAS's enterprise offering has a separate company and per-employee layer. Do not conflate the two, and do not frame the public product as team or collaboration software.
- Founder OS is plain markdown any capable agent can read and drive. Claude Code is the reference runtime we validate against, and where slash commands and hooks run. We do not ship a separate product per agent: no ChatGPT-Projects pack, no per-agent skills pack. The same markdown OS is read by whatever agent the user brings. See "Runtime honesty" below for the per-skill
Runs on:contract. - Keep the product's established hook framing. Do not invent demo-length claims, and do not paste private brand internals into this public repo. Match the wording already used elsewhere in this repo.
Quick Start
Say "set up Founder OS" to personalize this for your situation. If you prefer a slash command, it depends on how you installed: /setup on a ZIP or git-clone install, /founder-os:setup on a plugin install.
The wizard asks you questions about who you are, what you run, what tools you use, and what is slowing you down. From your answers it generates all the operating files in this repo - personalized to you. Takes 15-20 minutes the first time.
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.
- 3d ago First seen · 331 lines · 9,025 tokens per session scan A 1419f70383d9
FounderOS CLAUDE.md is an instructions file published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 20d ago), licensed MIT. It adds 9,025 tokens to every session, about $0.0451 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 2026-08-31.
Other instructions, from other repositories
website2markdown AGENTS.md
Instructions for Digidai/website2markdown, covering md-genedai (website2markdown) and skill routing.
website2markdown CLAUDE.md
Instructions for Digidai/website2markdown, covering md-genedai (website2markdown) and skill routing.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
telegramify-markdown AGENTS.md
Instructions for sudoskys/telegramify-markdown, covering telegramify-markdown agent guide, task routing, quick commands, project rules and architecture map.