The founder operating system

Know what matters today.

Founder OS turns your goals, cash, pipeline and commitments into one daily decision — stored locally and traceable to its source.

Local Markdown · No automatic sending · Explicit ownership · No hidden actions

founder-os / studio-north state loaded

08:00 / Daily brief

The one thing that matters today

BET: B1 — premium sprintOWNER: founder

  • 01Finish the Acme proposal scope. Do not start the website redesign.
  • 02Your weekly plan already funds a 09:00–11:30 block.
  • 03Northwind's founder-owned follow-up is 3 days overdue.

Thursday / Pipeline review

Every deal gets a next move or leaves

2 ACTIVE1 OVERDUE

  • 01Acme — founder finishes proposal scope today.
  • 02Northwind — requested references were due July 17.
  • 03Delta — dead because procurement required open-ended availability.

16:00 / Weekly review

The week scored by what actually happened

2/3 SHIPPEDPATTERN: DELIVERY DISPLACES PROOF

  • 01The case study did not ship — third consecutive week.
  • 02Do not roll it forward automatically. Make next week's plan smaller.
  • 03Monday commitment: finish the Acme proposal scope by 11:30.
fictional Studio North exampleexplore the workspace →
1decision for today
15minute hard stop
LocalMarkdown state
0automatic sends

The real problem

You do not need more advice.

You need a system that remembers what you decided, spots contradictions, and brings the decision back when it is actually due.

01

Every conversation starts from zero

Strategy, pipeline, and clients live in different notes. AI answers your latest prompt, not the state of your business.

02

Important work ends as a paragraph

The brief sounds smart, but has no owner, date, or next move. A week later, nobody comes back to it.

03

You are the CEO and the bottleneck

You set the priority, chase the sale, calculate the margin, and judge your own plan. That is not a lack of ambition. It is a lack of structure.

What makes it different

Conversations become company memory.

Founder OS does not pretend to be a magic autopilot. It builds continuity: shared state, clear ownership, operating cadence, and hard boundaries.

Memory that outlives the session

Goals, metrics, pipeline, clients, decisions, and drafts live in a local Markdown workspace. Tomorrow starts with business state, not another retelling.

One owner for every decision

The CFO does not rewrite the pipeline, and the Brand Editor does not change strategy. A write-time guard keeps every role in its lane.

A cadence that comes to you

A brief in the morning, pipeline review on Thursday, weekly review on Friday, and financials after month-end. Run it by hand or on a local schedule.

Opinions, not business horoscopes

Every role has principles you may disagree with. A plan gets a verdict, a bet gets a kill condition, and “no time” gets a calendar audit.

A real workspace, with fictional data

Follow one decision through the whole system.

Studio North is a one-person strategy studio. Its example workspace is small enough to inspect, but complete enough to show how a bet becomes a commitment, a calendar block, and the next morning's brief.

Open the daily brief source →

studio-north / reviews / daily / 2026-07-20.md fictional workspace
owner: chief-of-staff/daily-brief2026-07-20

The day starts with one thing

The one thing

q-0720a Finish the Acme proposal scope — serves B1.

Rotting

Northwind reference follow-up — 3 days overdue.

The trade

The website redesign does not start. It serves neither quarterly bet.

owner: chief-of-staffcap: 15live obligations

Work has an ID, owner, and expiry

Doing

q-0720a Finish the Acme proposal scope — bet: B1 — started 2026-07-20.

Queued

  • q-0717b Publish the Northwind migration case study — bet: B2.
  • q-0717c Book two qualified discovery calls — bet: B1.

Dropped

Website redesign — passed over by three weekly reviews and serves no current bet.

owner: strategistquarter: Q32 active bets

B1 · Make the premium sprint the default

Threshold · 30 September

Sign 3 sprints at or above $15,000 without adding custom delivery.

Downside cap

40 founder hours and $2,000 in design support.

Kill condition · 31 August

Fewer than 2 qualified proposals.

owner: focus-coach/week-planweek of 2026-07-20

The calendar funds the bet

Arithmetic

40h available · 24h delivery · 16h free · 9h planned.

The plan uses 56% of free capacity instead of pretending every free hour is deliverable.

Selected funded blocks

DayBlockServes
Mon · 09:00–11:30Finish Acme proposal scopeB1
Tue · 09:00–11:00Interview case-study clientB2
Thu · 10:00–11:00Pipeline reviewB1
owner: pipeline-coachlast review: 2026-07-17coverage: 2.2×

Every deal has evidence and a date

Pipeline · $33,000 live

DealStageNext action
Acme · $18kProposalFinish scope · Jul 20
Northwind · $15kQualifiedReferences · Jul 17 · overdue
Delta · $12kDeadOpen-ended terms broke the offer boundary

What was learned

Delta was lost because the buyer required ongoing availability, not because the price was too high.

owner: cfoclose: 2026-06closed 2026-07-01

The company closes on actuals

June close

Booked$31,000Collected$24,000
Hours112Effective rate$214/h vs $200 target
Receivables$7,000Runway9.7 months

Profitability signal

The fixed-scope sprint is above target. Custom advisory added 14 unbilled hours and fell below it.

owner: chief-of-staffdecided by: founderserves: B1

Raised the sprint floor to $15,000

Context

The fixed-scope sprint cleared the $200/h target. Custom advisory fell below it after 14 unbilled hours.

Rejected

Keep a $10,000 entry sprint and upsell advisory later.

What would change our mind

Fewer than 2 qualified proposals by 31 August, provided at least 8 ICP-matched discovery calls happened.

How to start

A focused path to your first brief.

Install the plugin, run one resumable onboarding flow, and start from a persisted daily decision. It targets a ten-minute median and stops at fifteen minutes rather than expanding into setup theatre.

1

Add Founder OS

Add the marketplace, then install the plugin. No Founder OS account, dashboard, or external database.

/plugin marketplace add msolecki/founder-os
/plugin install founder-os@founder-os
2

Answer four short groups

Business, customer, quarter, and money are routed to their file owners. Unknowns stay unknown. A valid reviews/daily/YYYY-MM-DD.md has all four required headings: ## The one thing, ## Rotting, ## The trade, and ## Triage, with non-empty ## The one thing and ## The trade.

/founder-os-init
3

Turn on the rhythm

Optional cron cadences run on your machine while it is on. Every workflow also works manually without cron.

/setup-cadences

The business in motion

A week with a backbone.

Founder OS does not create more work. It connects the moments when you already need to make a decision.

Weekdays · 08:00

One thing for today

The Chief of Staff reads your goals, metrics, and weekly plan, then names the most important move.

/daily-brief
Monday

Bets enter the calendar

The Focus Coach turns quarterly bets into concrete blocks of work.

/week-plan
Wednesday

Content starts with the ICP

The publishing plan starts with real audience questions, not an empty content slot.

/content-plan
Thursday

Every deal gets a date

The Pipeline Coach forces a next move. Conversations without action leave the pipeline.

/pipeline-review
Friday · 16:00

The week gets a score

Commitments against outcomes. No copying everything into next week by default.

/weekly-review

The complete operating library

A workflow for every decision that keeps returning.

Start with the decision in front of you. Founder OS routes it to the right owner and workflow.

Browse all 49 workflows
49 of 49 workflows
01 Chief of StaffAttention, reviews, decisions, and the live queue. 6 workflows
/daily-briefscheduled

Open the day with the one move that matters most, grounded in current goals, metrics, and this week's plan.

/weekly-reviewscheduled

Score what you committed to against what actually happened, then name the pattern that keeps repeating.

/monthly-review

Read the month back against the company charter and identify drift after the financial close is complete.

/decision-log

Record an irreversible decision, why it was made, and the evidence that would justify reversing it.

/triage

Turn a pile of obligations into one priority, price the cost of the rest, and route each item to an owner.

/queue

Keep live obligations capped, dated, owned, and able to expire instead of becoming an endless wish list.

02 StrategistQuarterly bets, downside, verdicts, and judgment. 4 workflows
/quarterly-planningscheduled

Close the old quarter's bets and commit to at most three new ones, each with a measurable kill condition.

/bet-sizing

Price what a bet costs when it is wrong and cap the downside before it enters company goals.

/kill-or-continue

Force a verdict when the judgment date arrives, using the original threshold and naming sunk cost out loud.

/annual-review

Review twelve months of decisions and score the quality of judgment, not whether luck produced a good outcome.

03 Board MemberPressure-test a plan before it gets expensive. 3 workflows
/red-team

Attack a finished plan as a hostile reader and return a verdict, not a polite list of concerns.

/assumption-audit

List what must be true, remove what already has evidence, and rank the rest by the cost to test.

/premortem

Assume the plan is dead six months from now and tell the failure story while it can still change the plan.

04 Positioning AdvisorWho you serve, what you sell, and what it is worth. 3 workflows
/icp-definition

Narrow the ideal customer until the definition excludes real, nameable people—not just vague adjectives.

/offer-design

Turn bespoke work into a clear buyer outcome with an explicit boundary a prospect can repeat.

/pricing-strategy

Price against the buyer's outcome and real alternative, then put your walk-away floor in writing.

05 Pipeline CoachEvery prospect gets a real next action. 4 workflows
/pipeline-reviewscheduled

Give every deal a next action with a date—or remove it from the pipeline.

/outreach-draft

Draft a first contact or follow-up from the prospect's problem, never from “just checking in.”

/proposal-draft

Draft a qualified proposal with scope, price, exclusions, and an expiry date after capacity is confirmed.

/win-loss-analysis

Reconstruct why a deal ended from the record and the prospect's own words while the evidence is fresh.

06 Delivery LeadCapacity, scope, client risk, and learning after delivery. 4 workflows
/capacity-check

Compute real deliverable hours before saying yes to a client, extra scope, or a start date.

/scope-guard

Rule whether a client request is inside scope by checking it against the proposal and its exclusions.

/client-health

Score payment, scope, tone, and effort before an engagement turns into a crisis or reaches renewal.

/delivery-retro

Compare estimated with actual hours within five days of shipping, before memory rewrites the project.

07 CFORevenue, survival, margin, and rates—not tax advice. 4 workflows
/revenue-reviewscheduled

Close the month on revenue booked, cash collected, and the effective hourly rate actually earned.

/runway-forecast

Calculate months of survival at real burn, discounting pipeline value by the stage of each deal.

/profitability-analysis

Rank clients by effective hourly rate to show exactly where margin is disappearing.

/rate-raise

Decide whether a rate should rise, by how much, and prepare the script when the numbers justify it.

08 Focus CoachTurn bets into time and compare plan with reality. 3 workflows
/week-planscheduled

Turn this quarter's bets into dated blocks before the week fills itself with other people's priorities.

/calendar-auditscheduled

Compare where the week was meant to go with where it actually went, using the calendar as evidence.

/energy-audit

Find the hours when your output is consistently good or poor from the accumulated calendar record.

09 Skills MentorBuild only the capability the strategy now requires. 2 workflows
/skill-gap

Name the capability gap between the offer sold today and the offer current bets require.

/learning-plan

Attach one needed capability to one real project and one deadline that forces practice.

10 Brand EditorAudience evidence, useful content, and your real voice. 4 workflows
/content-planscheduled

Plan what gets published against the ICP and the number of pieces you actually shipped last month.

/voice-capture

Learn your voice from writing you really sent, including the edits you made before sending it.

/content-draft

Draft one planned piece around one useful idea you learned by doing—not to fill an empty slot.

/audience-research

Collect the exact language your ICP uses for the problem before deciding what to publish.

11 Network ManagerWho you know, when to reconnect, and why now. 2 workflows
/relationship-map

Map real relationships by category and days since meaningful contact before reaching for cold outreach.

/follow-up-sweepscheduled

Surface up to five overdue relationships and give each person a real reason to hear from you.

12 Ops EngineerAutomate only what pays back and cut unused tools. 2 workflows
/automation-audit

Use payback arithmetic to decide whether a manual task is worth automating before building anything.

/tool-stack-review

Find software you pay for but do not use and prepare a cancel list before renewals arrive.

13 Portfolio ManagerThe one decision allowed to cross business boundaries. 1 workflow
/portfolio-reviewscheduled

Rank active businesses, split this week's hours and cash, and say plainly what that allocation is starving.

14 System workflowsLoad, protect, diagnose, and schedule the operating system. 7 workflows
/context-load

Load dated charter, goals, and metrics before advice begins, including the active business slug when needed.

/founder-os-doctor

Diagnose workspace rot—missing files, stale metrics, orphan clients, broken bets, and silent cadences—before repairing it.

/founder-os-init

Interview the founder, scaffold the workspace, route every answer to its owner, and produce the first brief.

/guardrails

Enforce the hard refusals: nothing outbound, nothing paid, and professional escalation for regulated advice.

/ingestion-gate

Classify every external claim as fact, validate, or disregard before it enters canonical company state.

/setup-cadences

Schedule nine recurring reviews per business, plus one portfolio review when multiple active businesses make it relevant.

/state-integrity

Resolve every workspace write against the ownership map and hand it to the correct role when needed.

Commands are shown in their short form. The namespaced form is /founder-os:<workflow>. Open the generated command reference →

Your executive team

13 roles. Zero overlap.

Every agent owns exactly one decision nobody else can make. When you do not know where to start, the Chief of Staff routes the question to the right role.

1role = one decision = one owner of state

  1. Chief of StaffWhat deserves your attention now, and who should handle it.
  2. Board MemberWhether a plan survives contact with reality.
  3. StrategistWhat bet to make this quarter — and what to kill.
  4. Positioning AdvisorExactly who you serve and what you sell them.
  5. Pipeline CoachWhat happens next with every prospect.
  6. Delivery LeadWhether you can take the work and whether it is good enough to ship.
  7. CFOWhether the company can afford it and whether the work makes money.
  8. Focus CoachWhat enters the calendar — and what comes out.
  9. Skills MentorWhich capability to build next and why.
  10. Brand EditorWhat to publish, where, and how to keep your voice.
  11. Network ManagerWho to talk to and when to follow up.
  12. Ops EngineerWhat to automate and what to tolerate.
  13. Portfolio ManagerHow to split time and cash across multiple businesses.

Built for a portfolio of one

One founder. Several businesses. No shared mess.

Founder OS repeats the operating system instead of blending your companies together. Every business keeps its own goals, clients, metrics, pipeline, decisions, and cadence.

Run one business? Nothing changes. The multi-business layer appears only when you register a second active business.

Isolate the workEach company keeps a complete workspace, cadence, logs, and history.
Name the companyThe slug, environment, or registry default resolves context before advice begins.
Cross only at portfolio levelOnly the Portfolio Manager compares businesses, and only to allocate scarce time and cash.
Your business state
goals.md pipeline.md metrics.md decisions/ queue.md

One source of truth

Your business does not live in prompts.

It lives in simple files you can open, edit, archive, and version. Every material claim carries a source and date; agents read the same state, but write only inside their own area.

Founder OS only knows what is recorded here. It does not automatically sync your calendar, CRM, inbox, or bank account.

Workspace files stay on your machine. Prompts and context sent through Claude Code or Codex remain governed by that environment's data-handling terms.

  • Decisions remember not only what, but why — and what evidence would reverse them.
  • Drafts stay on disk; the version you actually sent teaches the system your real voice.
  • The queue has a cap, dates, and expiry — it does not grow into another wish list.
  • With multiple companies, each business keeps its own workspace and cadence.

Hard boundaries

AI advises. You decide.

No agent has a browser, shell, or tool that can reach beyond the workspace. That is a deliberate boundary, not a missing feature.

Human in controlalways on

Never sends. Never pays.

The system can prepare a proposal, follow-up, or rate-raise plan. You press the button, sign the document, and own the decision.

  • Messages and postsdraft only
  • Invoices and transfersno access
  • Legal and tax adviceescalate

An honest filter

This is for you — or it isn't.

Founder OS fits if…

  • you run a company of one or a small service business where every decision lands with you,
  • you use Claude Code and want every conversation to build shared business state,
  • you need a rhythm across pipeline, delivery, money, and focus,
  • you run multiple businesses and need to divide resources honestly.

Do not install it if…

  • you want an autonomous bot that sends messages and moves money for you,
  • you refuse to maintain any business state in files,
  • you need a full CRM with a shared dashboard for a large team,
  • you want an assistant that validates every decision without pushing back.

Before you install

What you need. What it costs.

Founder OS is free and MIT-licensed. It runs inside your existing Claude Code environment and adds no account or subscription of its own.

Continue to installation
Runtime

Python 3; PyYAML recommended

Python runs the ownership hook. PyYAML enables its full ownership-map check.

Optional

cron for schedules

Manual workflows need no cron. Scheduled cadences run only while your machine and cron service are on.

Price

$0 · MIT license

Founder OS is free. Your existing Claude Code plan and usage remain separate.

FAQ

Before you install.

Is Founder OS a separate app?

No. It is a Claude Code plugin. The agents, workflows, and rules install inside that environment, while your business state stays in a local Markdown workspace.

Are 13 agents running all the time?

No. They are specialized roles, not 13 autonomous processes running all day. A workflow invokes the relevant role; nine per-business cadences can run on a local schedule, with Portfolio Review as the tenth on multi-business installs.

How long does setup take?

The plugin installs with two commands after adding its marketplace. Onboarding targets a ten-minute median and stops at fifteen minutes. It is complete only when the first valid daily brief is persisted and passes the same validity check.

Do I need to learn all 49 commands?

No. When you do not know what to use, ask the Chief of Staff. Routing is its job — it sends the question to the right agent.

Can it work in my language?

Yes. The technical section headings stay in English, but the workspace content and the agents' work can use your language. The system can also learn your style from real writing samples.

What if I run more than one business?

Each business gets its own workspace and cadences. The Portfolio Manager is the only role that looks across businesses, dividing time and cash without mixing operational state.

Where does Founder OS get its data?

Only from the Markdown workspace and context you provide. It does not automatically sync your calendar, CRM, inbox, or bank account. Workspace files stay on your machine; your Claude Code or Codex environment's data-handling terms still apply to prompts and context sent through it.

How much does it cost?

Founder OS is free and MIT-licensed. It adds no account or subscription. Your existing Claude Code plan and usage are separate.

Does the system really run automatically?

After the optional /setup-cadences, local cron runs nine cadences per business while your machine and cron service are on. Multi-business installs add Portfolio Review as the tenth. There is no cloud scheduler, and every cadence also works by hand.

Start with one decision, not another dashboard

Know what matters tomorrow.

Claude Code3 steps
  1. /plugin marketplace add msolecki/founder-os
  2. /plugin install founder-os@founder-os
  3. /founder-os-init

Then: onboarding runs one continuous, resumable path and ends only after your first valid daily brief is persisted and validated. Read the complete getting-started guide for the data boundary, first five actions, update, repair, and uninstall steps.