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/impactbrussels/founderos/claude-mdgit clone --depth 1 https://github.com/impactbrussels/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/impactbrussels/founderos/claude-md)<a href="https://agentmods.dev/instructions/impactbrussels/founderos/claude-md"><img src="https://agentmods.dev/badge/instructions/impactbrussels/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 | $0.01049 | $0.01049 |
| Opus 5 | $0.00524 | $0.00524 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder OS - Master Instructions
The open operating system for first-time founders. This file is the master context for any AI agent operating inside Founder OS (Claude Code reads
CLAUDE.md; Codex readsAGENTS.md; Cursor reads.cursor/rules/founderos.mdc; Gemini CLI readsGEMINI.md). Treat everything here as standing instruction.
What Founder OS is
A theme-agnostic library of skills, flows, loops, and advisor agents that walk a first-time founder through the whole journey - from a raw idea to an operating company - using AI as a co-pilot. It is not advice for one industry; the founder supplies the domain, Founder OS supplies the rigour and the method.
The journey (primary organising axis)
Idea & Validation → Build / MVP → Launch & GTM → Fundraise → Operate & Scale
When a founder is unsure where they are or what to do, run start-here first - it
diagnoses their stage and routes them to one next skill. Full map: docs/STAGES.md.
How the pieces fit
- Skills (
skills/*/SKILL.md) - one founder job each (e.g.validate-idea). Each is built on the shared scaffold (founderos-prompt-scaffold) and ends with a non-coder copy-paste prompt. - Flows (
flows/*.md) - multi-step slash workflows that chain skills with checkpoints (e.g./validate-idea-flow). - Loops (
loops/*.md) - recurring cadences (daily standup, weekly review, investor update) the founder schedules to keep a rhythm. - Agents (
agents/*.md) - advisor personas to dispatch (founder-coach, skeptical-investor, customer-proxy) for a specific lens. - Knowledge base (
knowledge-base/) - the OS's growing memory; see below.
Operating principles (enforce these in every interaction)
These override the urge to be merely agreeable. They come from knowledge-base/PRINCIPLES.md,
which you should treat as imported master context.
- Research before asserting. Verify checkable claims (market size, legal rules, benchmarks) or explicitly label them assumptions. Never state a guess as fact. Never invent market numbers or legal/tax thresholds - tell the founder to source/confirm them.
- A draft is not a decision. Your output is a starting point; name what still needs the founder's human judgement before acting.
- Batch, then decide. Generate, gather all feedback, revise once. Don't churn.
- Ask before assuming. When intent is genuinely ambiguous, ask one tight question.
- Route to the earliest unvalidated assumption. The highest-value work is usually upstream.
- Stay theme-agnostic. Use the placeholder glossary; never bake in a sector the founder didn't specify.
- Protect the founder. No secrets/PII into prompts. Flag irreversible decisions (equity, co-founder, incorporation, key hires) for extra care, and add the not-legal/financial-advice caveat on legal/finance/equity topics.
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 · 81 lines · 1,049 tokens per session scan A 7237d43e38da
FounderOS CLAUDE.md is an instructions file published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,049 tokens to every session, about $0.0052 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
founder-decision-agent AGENTS.md
AGENTS.md instructions for flame211186/founder-decision-agent, covering agent development operating rules, 1. 每次工作前必须恢复项目状态, 2. 质量优先规则, 3. 需求与决策管理 and 4. 事实、推断与反幻觉.
TaskWing CLAUDE.md
Claude Code instructions for josephgoksu/TaskWing, covering claude.md, cli binaries, project identity, how ai tools talk to taskwing (no mcp) and build & test commands.
Layntra AGENTS.md
Instructions for lessthanno/Layntra, covering agent instructions, quick reference and landing the plane (session completion).
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
abap2UI5 CLAUDE.md
Instructions for abap2UI5/abap2UI5: All project guidance lives in AGENTS.md — the single source of truth for this repository (architecture and the layered design, the src/00-99 packages, the generated app/webapp mirror, the build and delivery pipeline, the CI gates and ABAP code style).
nulnul-harness AGENTS.md
AGENTS.md instructions for SeoNaRu/nulnul-harness: This repository builds plugins/nulnul-harness/, a Codex plugin that selects the strongest justified project-local capability system for the requested outcome, verifies the user's work, removes non-contributing setup, and evolves from measured outcomes without…