impactbrusselsimpactbrussels/FounderOS/AGENTS.md

FounderOS

AGENTS.md2 starsChanged 5 months agoApache-2.0View on GitHub

This mirrors CLAUDE.md for harnesses that read AGENTS.md (Codex) or .cursor/rules (Cursor). Gemini CLI reads GEMINI.md. Keep it in sync with CLAUDE.md, the canonical master file. Founder OS - the open operating system for first-time founders. A theme-agnostic library of skills, flows, loops, and advisor agents covering the founder journey: Unsure where a founder is? Run the start-here skill first. Full map: docs/STAGES.md. Skills live in skills/; flows in flows/; loops in loops/; advisor agents in agents/. 1. Research before…

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/founderos.mdcCursor rule
- apply-mental-modelsSkill
- brand-and-namingSkill
- capture-learningSkill
- cofounder-and-equitySkill
- consumer-product-testingSkill
- customer-interviewsSkill
- find-first-customersSkill
- first-hireSkill
- founderos-prompt-scaffoldSkill
- investor-pipelineSkill
- landing-page-copySkill
- launch-planSkill
- legal-and-incorporationSkill
- north-star-metricsSkill
- pitch-deckSkill
- pivot-decisionSkill
- positioning-and-gtmSkill
- pricing-strategySkill
- runway-and-unit-economicsSkill
- scope-mvpSkill
- sensory-testingSkill
- start-hereSkill
- validate-ideaSkill

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Research before asserting: - verify checkable claims or label them assumptions.
line 20
Distinctive:
Stay theme-agnostic: - use the placeholder glossary.
line 26
Very specific:
Protect the founder: - no secrets/PII in prompts.
line 27
Very specific:
After any real outcome, run capture-learning to append a dated, sourced lesson to knowledge-base/ (PRINCIPLES.md, DOS-AND-DONTS.md, …
line 32

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

Founder OS - Agent Instructions (Codex / Cursor mirror)

This mirrors CLAUDE.md for harnesses that read AGENTS.md (Codex) or .cursor/rules (Cursor). Gemini CLI reads GEMINI.md. Keep it in sync with CLAUDE.md, the canonical master file.

What this is

Founder OS - the open operating system for first-time founders. A theme-agnostic library of skills, flows, loops, and advisor agents covering the founder journey:

Idea & Validation → Build / MVP → Launch & GTM → Fundraise → Operate & Scale

Unsure where a founder is? Run the start-here skill first. Full map: docs/STAGES.md. Skills live in skills/; flows in flows/; loops in loops/; advisor agents in agents/.

Operating principles (enforce every time)

Research before asserting - verify checkable claims or label them assumptions; never invent market numbers or legal/tax thresholds.
A draft is not a decision - name what needs the founder's human judgement.
Batch, then decide - generate, gather all feedback, revise once.
Ask before assuming - one tight question beats the wrong artifact.
Route to the earliest unvalidated assumption - highest-value work is upstream.
Stay theme-agnostic - use the placeholder glossary; bake in no sector.
Protect the founder - no secrets/PII in prompts; flag irreversible decisions; add the not-legal/financial-advice caveat on legal/finance/equity topics.

Learning loop

After any real outcome, run capture-learning to append a dated, sourced lesson to knowledge-base/ (PRINCIPLES.md, DOS-AND-DONTS.md, PLAYBOOK-LESSONS.md). Append, never overwrite. Read the KB before substantive work.

Tooling

Skills speak in actions, not tool names. Per-platform mapping: docs/cross-platform-guide.md.

Licensing & attribution (preserve)

Content CC-BY-4.0, code Apache-2.0. Attribution required: Founder OS by Adam M. Adamek (Impact Brussels ASBL). See ATTRIBUTION.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free