FounderOS / notion-package
CLAUDE.md7 starsChanged 19 days agoMITView on GitHub
In this repository100 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- add-handsSkill
- add-mouthSkill
- add-voiceSkill
- approval-gatesSkill
- auditSkill
- backupSkill
- blind-spot-reviewSkill
- bottleneck-diagnosticSkill
- brain-logSkill
- brain-passSkill
- brain-snapshotSkill
- brand-interviewSkill
- brand-voice-interviewSkill
- business-context-loaderSkill
- campaign-from-themeSkill
- capture-sweepSkill
- catch-upSkill
- client-updateSkill
- connectSkill
- content-repurposerSkill
- content-startSkill
- context-persistenceSkill
- cross-linkSkill
- data-securitySkill
- decision-frameworkSkill
- decisions-startSkill
- delivery-startSkill
- email-drafterSkill
- employee-reviewSkill
- finance-importSkill
- forcing-questionsSkill
- founder-coachingSkill
- founder-next-moveSkill
- founder-os-setupSkill
- founder-reviewSkill
- founder-scope-challengeSkill
- github-opsSkill
- handoff-protocolSkill
- hireSkill
- historySkill
- housekeepingSkill
- ingestSkill
- knowledge-captureSkill
- legal-complianceSkill
- linkedin-brand-directionSkill
- linkedin-network-scanSkill
- linkedin-postSkill
- linkedin-power-auditSkill
- linkedin-startSkill
- linkedin-warm-revivalSkill
- lintSkill
- list-prunerSkill
- log-archiveSkill
- log-replySkill
- meeting-prepSkill
- memory-passSkill
- menuSkill
- The first 60 shown.
The file
We split this CLAUDE.md into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Not a workflow engine. Not a webhook server.
- Distinctive: line 35
Before adding any new file, read this CLAUDE.md and confirm scope fit.
- Distinctive: line 36
After every session that modifies notion-package/, append a dated entry to the "Session log" section at the bottom of this file with: date, …
- Distinctive: line 37
If you are a new Claude session picking up this project cold, read this file first, then scan the most recent session log entries at the …
- Distinctive: line 38
Never add banned words or ARCAS leakage.
- Distinctive: line 39
If scope creep appears (someone asks to add workflows, webhooks, crons), refuse.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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.
Files
Founder OS - Notion Package (Plan B sub-project CLAUDE.md)
What this is
Public-facing Notion Package that non-technical founders can duplicate and start using the same day. Zero terminal required. Runs on a Claude subscription plus a free Notion account.
What this is NOT
Not a workflow engine. Not a webhook server. Not a cloud service. Not the local Claude Code plugin. The local plugin lives in the public FounderOS repo root.
Who this is for
A non-developer founder. Uses Claude and voice input (Wispr Flow or similar). Already lives in Notion or willing to. Runs the business alone or with one or two people. Day is chopped into thirty-minute pieces. Has tried productivity templates that quietly stopped getting used by week three.
The two drivers (positioning)
Claude thinks. Wispr Flow speaks. Founder OS is the markdown layer in between that evolves with the user.
File tree (target)
notion-package/ CLAUDE.md <- you are here README.md <- public-facing intro to the package pages/ <- Notion-page-ready markdown sources 00-landing.md 01-quickstart.md 05-current-limits.md system-prompts/ founder-os-project-prompt.md <- Claude Project system prompt that runs the routing loop against Notion via the connector databases/ schema.md <- Notion DB schemas (Profiles, Decisions, Priorities, Clients, Brain Log, Flags) announce/ README.md <- launch and sharing notes test/ sample-transcript.md <- canned test transcript for first-run demo expected-routes.md <- expected output for the sample
Self-update protocol
This project must be able to evolve itself over time. Pattern:
- Before adding any new file, read this CLAUDE.md and confirm scope fit.
- After every session that modifies notion-package/, append a dated entry to the "Session log" section at the bottom of this file with: date, what changed, why, commit SHA.
- If you are a new Claude session picking up this project cold, read this file first, then scan the most recent session log entries at the bottom of this file before changing anything.
- Never add banned words or ARCAS leakage. Run pre-commit guard before suggesting writes.
- If scope creep appears (someone asks to add workflows, webhooks, crons), refuse. Point at "What this is NOT" above. Direct them to the terminal version.
Voice and style rules for this sub-project
- Plain English. Non-native English speakers are the primary audience.
- Calm founder authority. No hype. No emojis. No em dashes. No banned words.
- "The team" not "my team" when referring to founders using the package.
- Frame benefits as consequences of behavior, not aspirations.
Session log
(appended by future sessions)
- 2026-04-22: Scaffold created. No pages, prompts, databases, or announce copy yet. Commit SHA: (set at commit time).
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
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.

