Guess
Free check
this page, no email
The Setup Audit, for professionals who run Claude
Every morning, Claude has forgotten your business. You re-explain, re-paste, re-type; the work gets done, but nothing compounds. That forgetting has a price. Find out roughly what it is, free, in two minutes.
The free check takes two minutes and needs no email. The full interview is free for the first cohort, by invite; your report appears as soon as you finish it. The pack is $99, refunded within 14 days if it plainly does not fit.
No account access, everRead every line before it runsEstimated, then verified on your machine
Example report
34
out of 100, estimated
Emerging
Illustrative example, not your result. Your own interview produces yours.
The free check
Your rough score, in two minutes
Eight honest questions, scored on the same six-category rubric as the full interview. The number appears right here; no email needed.
0 of 8 answered; unanswered questions score zero, honestly
Estimate
Interview
free, by invite
Verified
Pack
$99
The ladder
Where do you sit?
Five bands, 100 points. The interview places you on this ladder and names what is holding you at your band.
Ad hoc
0-20
Chats from scratch. Nothing persists between sessions; every day starts with re-explaining.
Emerging
21-40
Some saved prompts or notes, no durable system. Value arrives, then evaporates.
Systematic
41-60
An operating manual and project context exist; memory is partial. The week most people believe they are already having.
Compounding
61-80
Memory, rituals and first skills in daily use. Work done once stays done.
Productised
81-100
Workflows encoded, automated where safe, deployable to others. The setup itself is an asset.
Take the band ladder as a one-page reference. Free, prints cleanly to A4, no email needed.
The method
How it works
Three steps, most of it done for you.
1
The interview
About 20 minutes, mostly multiple choice: your role, surfaces, tools, workflows, memory habits and goals. Where the free check guesses from eight answers, the interview estimates from eighteen, and that difference is what makes the result worth acting on.
Free, by invite2
Your results
Your score and report appear as soon as you complete the interview: a band on a 100-point scale across six categories (foundations, memory, skills, integrations, productisation, advanced use), your top three gaps named plainly, and what they cost you day to day. Estimated, and honest about that.
Included3
Your personalised pack
A zip of runbooks assembled for your profile from a tested 28-runbook library, human-reviewed within 48 hours. Your own Claude executes them; its audit runbooks turn the estimate into a measured score, starting with a read-only foundation audit.
$99The rubric
A real standard, not a made-up number
Your score comes from a 100-point rubric across six categories, weighted by what compounds most. Foundations and memory carry the most, because everything else builds on them.
100
points, six categories, weighted. The free check estimates it from eight answers; the interview scores all six properly.
The obvious question
Could you just ask Claude to do this?
Yes. Here is what that gets you, and what it does not.
Ask Claude to audit your own setup and you get a thoughtful one-off answer, framed by whatever you thought to ask, scored against no particular standard, gone when the chat ends. Self-report has a known failure mode: everyone believes their setup is roughly fine. The gap between what people report and what an evidence check finds is the reason audits exist as a discipline.
What you are paying for here is the standard: a published 100-point rubric, runbooks that have already been run and verified on their intended Claude surface, assembly against your actual answers, and a human read before anything ships. None of that needs taking on faith; the artefacts are published:
- A real sample report: the exact format buyers receive, from a real fixture profile.
- One complete runbook: plain markdown with its verify checks, exactly as it ships in a pack.
- The full scoring rubric: every criterion, weight and rule, nothing held back. Score yourself by hand if you like.
If you read those and conclude your own prompt gets you there, that is a fine outcome and we mean it. The free check is still yours.
The diagnosis
Three gaps, named plainly
A scored picture of your setup and the specific things costing you the most, in order. These are illustrative examples; your report names yours.
Example gap 1
Memory & context
13 of 24 points behind
Nothing carries over between sessions, so you re-teach Claude your business every day.
Day to day: roughly 20 to 40 minutes lost re-establishing context on a typical working day.
Example gap 2
Integrations
9 of 12 points behind
The tools that hold your real data are not connected, so Claude works from what you paste in by hand.
Day to day: manual copy-paste between Claude and the tools that actually hold your numbers.
Example gap 3
Skills & reuse
8 of 12 points behind
Workflows are re-typed each time rather than encoded once, so nothing compounds.
Day to day: the same instructions written out again and again, week after week.
Your pack, once you buy it
- Assembled to your profile from the 28-runbook library, never generated fresh
- Written Claude Code first; browser-only? Say so in the interview and we tell you before you pay whether the pack fits
- Every runbook carries a verify check, so you know it worked before moving on
- A scoreboard that tracks your pack progress; the audit runbooks measure your score
- Plain markdown. Your Claude executes it, on your machine, with you in the loop
Tested means each runbook has been run against its intended Claude surface and carries a defined verification check.
Stop paying that tax: request your free interview inviteThe buyer
Built for professionals who run Claude
Not a course, not consulting hours. A diagnosis and the files that fix it.
Freelancers & consultants
Client work runs through Claude but every engagement starts from a blank chat. The pack builds the memory and project structure that makes the second client cheaper than the first.
Agency operators
Deliverables are repeatable in your head and nowhere else. The pack encodes them as skills and runbooks your Claude executes the same way every time.
Small teams
One person is the Claude person and everything lives in their history. The pack turns private habits into files a team can share, review and hand over.
The standard
Honesty is the brand
Estimated, then verified
Your interview score is a band from self-reported answers, not fake precision. The pack’s audit runbooks are read-only checks your own Claude runs locally, turning the estimate into a measured score, category by category.
We never touch your account
There is no OAuth path onto your Claude setup and we do not ask for your login. The interview asks; your own Claude inspects, on your own machine, when you choose to run it.
Every line inspectable
Runbooks are plain markdown. Nothing installs itself and nothing runs unattended; you read it, then your Claude executes it with you in the loop.
A 20-minute self-report earns you an estimate, not a certainty. We say which is which.
Guess
The free check
FREEEstimate
The interview
FREE, BY INVITEVerified
The pack
$99The price
Pricing, plainly
One price. The diagnosis is free; you pay only if you want the fix.
The Setup Interview
Free
For the first cohort, by invite. It runs on real model tokens, so it is invite-only rather than open.
- About 20 minutes, one question at a time
- Mostly multiple choice, skip what you are unsure of
- Your score, band and top three gaps, named plainly
The Upgrade Pack
$99
Human-reviewed before delivery, within 48 hours. Refunded within 14 days if it plainly does not fit.
- Runbooks assembled to your profile from the 28-runbook library
- Audit runbooks that turn your estimate into a measured score
- Plain markdown, verify checks throughout, yours to keep
The questions
Asked before buying
Why is the interview invite-only rather than just open?
It runs on real model tokens and every report gets a human read, so while the first cohort is open we keep it small by invitation rather than gating it with a price. Request an invite with your email; they go out personally, usually within a day. The free check needs no invite and no email.
Do you access my Claude account?
No. There is no mechanism for a third party to inspect your Claude setup remotely, and we do not ask for your login. The interview asks; your own Claude verifies locally when you run the pack's audit runbook.
Why not just ask Claude to audit itself for free?
You can, and the audit prompt would be yours to invent, run and interpret. What you are buying is the rubric (a tested 100-point scoring standard), a library of runbooks that already work, assembly against your actual answers, and a human review before delivery. The rubric, a full sample report and a complete sample runbook are published on this page; read them before paying anything.
What do I need to use the pack?
A Claude plan. The pack is written Claude Code first; that is where the runbooks that touch files and skills earn their keep. If you only use claude.ai in the browser, say so in the interview and we tell you honestly, before you pay, whether the pack is worth it to you yet.
Is my interview data safe?
Your answers form a profile used to score you and assemble your pack. It contains no passwords or keys by design (we never ask for them). Stored securely, deleted on request, and any benchmark use is anonymised.
Is the free check the same as the interview score?
No, and we will not pretend it is. The check is a rough guess from eight self-graded answers, one band of margin either side. The interview estimates properly across all six categories, and the pack's audit runbooks verify the estimate on your machine, category by category. Guess, estimate, verified: in that order.
How is the score calculated?
A 100-point rubric across six categories (foundations, memory, skills, integrations, productisation, advanced use), weighted by what compounds most. From interview answers alone you get a band with a stated margin; running the pack's audit runbooks on your machine verifies it, category by category.
What exactly is in the pack?
Runbooks: step-by-step task files your Claude executes, each with verify checks, assembled for your profile from a tested 28-runbook library, plus a scoreboard page that tracks your pack progress. The audit runbooks, not the ticks, measure your maturity score.
What if I already score high?
Then the report says so, and the pack leans into what is left: usually productisation and the advanced tier. A high scorer gets fewer, harder runbooks rather than padding. If the pack plainly does not fit your interview, tell us within 14 days for a refund or reassembly.
Find out what you are actually running.
About 20 minutes, one question at a time. Free while the first cohort is open.
Request my free interview inviteAlready have an access link? Go straight to the interview.