Preview · what your reports look like

The AI tells you what it thinks of you, and what it has learnt about you: where you spike, what drives you, the patterns you fall into, and how you actually work. Here is what that looks like, shown for John, a sample profile.

Stays on your machine. The full coding report is for your eyes only — it never leaves your computer.

192 interactive sessions · 99 graded so far

Optional: share this full code analysis as feedback for Polymath (will greatly help us make this better!). Private — nothing gets a public link.Work on two machines? Sync each to your account and they combine, overlap counted once.

How you stack up

your numbers, with the gap to the top performers

How hard you push6/11
you peak at ~6,852 words of pure direction in a single day — the very top sustain ~5,000 every day, week after week; the wildest single days on record push ~10,000
Hours you put in
~7.5h of active building on a typical work day — engaged builders average ~3h, and sustaining 7h+ day after day, week after week, is top-1% territory
Your AI parallelism8/11
you already run parallel at the frontier — 63h of your hours with 2+ agents live vs 108h solo; the Claude Code lead keeps 10–15 going at once, and you work the same way
Focus quality when you work6/11
~28% of your work day is true deep flow (~2h) — the very best hold ~50% of theirs in one unbroken block; yours fragments across parallel sessions, so the gain is directing your attention at one thread for longer

A snapshot of your work

Apr

May

Jun

Jul

Project 132 days · 135.3h

Project 28 days · 6.5h

Project 33 days · 10.4h

Project 42 days · 5.3h

Project 51 day · 0.1h

←Hover any day in the grid to see exactly what you worked on that day.

Intensity and Focus

Daily rhythm

active time by hour of day · 62 working days, 261.5h active

12a6a12p6p11p

Work window 10am–11pm. Afternoon worker — 61% of active time is noon–6pm. Peaks around 5pm, second push at 6pm.

Intensity by week · over 49 days of solid coding stretches (~7.0 wk)

Date range · oldest left, recent right

Start→ End

Hours / week, including breaks

your working day with meals and breaks; overnight and 4h+ absences excluded

40.7h

Break hours / week

daytime gaps of 30 min to 4h inside your workday; meals, errands, drift

11.6h

Output

6/10

words per day — a proxy for focus & hard work · your days in orange (your avg = orange dashed line) · grey dashed = the top 0.1% average and the wildest single days on record · hover a dot for detail

How the average is calculated — we only count your sustained coding days: days you were at it across a 4h+ span from first keystroke to last (43 of your 57 coding days). Days you didn’t code — or just did one quick thing and then stopped — are left out, so a light day never drags the number down.

You have already hit 6,880 words in a day, so your 3,956 average runs at 57% of your own proven ceiling; the 43 substantial days out of 57 say the habit is there and the median day is what is short.

Flow state, day by day

in flow vs supervising, half-hour by half-hour · last 14 daysaxis→

14.8hin flow across 14 days · 1.1h/day — rapid exchange only, supervision excluded

in flow (driving many agents at once)nudging (supervising running threads)away (no typing, inside your workday)

00:00

03:00

06:00

09:00

12:00

15:00

18:00

21:00

07/04

07/05

07/06

07/07

07/08

07/09

07/10

07/11

07/12

07/13

07/14

07/15

07/16

07/17

You should be in flow state much longer.

You are at 1.1h a day, longest recent run 1.4h.

Flow state per day · you

15%of your working time locked in hard (solid blocks only; meals and long absences don’t count against you)

the best

~50%

the best spend ~half the workday in true deep flow; ~4h/day is the human ceiling

Longest recent flow run · you

1.4hunbroken rapid exchange

the best

~4h

sustain focus for hours, not minutes — the average worker breaks at ~40 min

Flow finds you in: Authoring rubrics and report copy you can judge by eye · Net-new UI you can watch working the same sitting

It never ignites in: Slow-verifiable engine tuning with no quick ground truth · Infra, distribution and media work

The patterns that end it

4× — Uninterpretable output, you cannot tell what it means or if it worked
22× — Threads drained with nothing queued
2× — Bounced or churned design decision
2× — Manual ops interruption

A gift

Built from your own logs. Paste it into Claude and it starts responding in ways that keep you in flow state longer:

Paste this into Claude Code and it sets everything up

Lead with the verdict: what changed, did it work, how you verified it, in one line before anything else
The single next decision or a reviewable chunk, never a menu
Any threads still running, so I re-enter without asking
When a result is hard to judge from text, render it as a small HTML view, chart, or before/after
Restate my spec in one line before a build pass

Shows you every change for approval before writing anything.

▸ see the prompt

Paste this into Claude Code. When it runs, your replies will lead with the verdict, hard-to-judge results will arrive as a rendered view, slow runs get handled off to the side, and every reply ends with the next task staged.

You are setting up flow-protection tooling for John from his measured coding logs. Make only the changes below. Show every edit to an existing file as a diff and wait for approval; new files need one batch approval; write nothing before he says go.

His measured findings, for your context: his longest runs start between 11:00 and 16:00 (8 of 9); his flow dies when he cannot tell what output means or whether it worked (4 of his longest runs ended that way); he asked the agent to just do terminal and console work itself 69 times across 32 days; his parallel threads drain to nothing with no next task staged 22 times, most often near 18:00; he asked to SEE results rendered 14 times.

1. CLAUDE.md: append the Flow rules block below to his user-global ~/.claude/CLAUDE.md, creating the file if missing, never overwriting existing content:

## Flow rules, derived from 59 days of my own session logs, 2026-07-10
(My flow profile) My longest runs start 11:00 to 16:00; my flow dies when I cannot tell if the output worked (4 of my longest runs); my threads drain to nothing near 18:00 (22 collapses).
(What you should do) Own all terminal, console and status-check work end to end, never hand me steps (asked 69 times); state your call and proceed, one blocking question at most; keep a next task staged; schedule slow runs away from 11:00 to 16:00.
(In every response) Lead with the verdict (what changed, did it work, how verified); render hard-to-judge results as a small HTML view or chart (asked 14 times); restate my spec in one line before a build; plain language, no em dashes.
(At the end of every response) One line for what changed and how it was verified; the single next decision or a reviewable chunk, never a menu; any threads still running.

2. Create these skills, one file each under ~/.claude/skills:
- ops-runner: owns every terminal, console, credential and status check end to end and reports a single verdict line; never hands him steps.
- run-watcher: schedules slow pipeline and distribution builds outside 11:00 to 16:00, watches them, and reports one line (what ran, did it pass, how verified).
- queue-keeper: keeps at least one next task staged during parallel work so a finishing agent hands off instead of stranding him, and nudges once when the set is about to drain.

3. Verify each skill is invocable and report what was created in one line each.

▸ show details — how this is calculated

You count as in flow when you are driving two or more agent sessions at once while actually composing. Concretely: in any rolling 15-minute stretch, you touched two or more sessions and spent over 2 of those 15 minutes producing words — typing at ~40 words a minute or dictating at ~130, measured from your real messages (pastes and machine text excluded). This is evaluated every 3 minutes, and brief lulls under 6 minutes inside a run do not break it. Each half-hour block is shaded by how much of it was flow: solid means more than half, the lighter shade means partial (hover for the exact share). Working in a single session, or watching agents run without typing, counts as nudging — real work, not flow.

Where your day leaks

real coding weekdays only (29 days, 2h+ of work) — weekends are yours and are never counted here

2.1hof your average 7.6h working day goes to breaks

When the break minutes happen · avg minutes away per hour

7:0011:0015:0019:00

Your breaks peak 13:00–14:00 and 16:00–17:00 and 18:00–19:00, but they are not one lunch: the leak runs steadily from late morning to evening.

You step away

2.0x

per day, 30 min or longer

Your 5 tightest days

0.3h

of breaks — you can do this

Your median day

1.9h

of breaks — where you live now

Your last 7 days

33.9h worked · 9.3h away — for every hour you worked, you were gone 17 minutes.

Sat 07-11 · 1.3h work · clean — no breaks over 30 min

Sun 07-12 · 4.5h work · 0.7h away — 13:12–13:51

Mon 07-13 · 7.1h work · 4.0h away — 12:42–14:30, 17:24–18:15, 19:36–20:54

Tue 07-14 · 4.2h work · 2.3h away — 15:09–16:21, 18:12–19:18

Wed 07-15 · 9.3h work · 1.9h away — 17:54–18:42, 19:48–20:51

Thu 07-16 · 4.1h work · clean — no breaks over 30 min

Fri 07-17 · 3.5h work · 0.6h away — 11:24–12:00

Where the time went

Tight days are big days. Your biggest (9.3h Wed) was also your lowest-break (1.9h away).

90 minutes a day is yours: meals, rest, a walk. Past that is drift — 5h a week, 0.8 working days your tightest days prove you can reclaim.

What you worked on, day by day

cell depth = how much of you it got · last 30 days

Jun 18

Jul 03

days · flow

Coding

Feature 4

9d · 44%

Feature 10

5d · 77%

Feature 11

5d · 44%

Feature 15

4d · 66%

Feature 19

3d · 41%

Feature 26

2d · 48%

Feature 27

2d · 25%

Infra

Feature 1

13d · 50%

Feature 9

6d · 22%

Feature 17

4d · 49%

Feature 21

3d · 22%

Feature 22

2d · 85%

Engine

Feature 2

8d · 25%

Feature 5

8d · 68%

Feature 14

4d · 40%

Feature 18

3d · 21%

Feature 24

2d · 31%

Feature 25

2d · 47%

Report

Feature 7

6d · 64%

Feature 13

4d · 67%

Feature 3

2d · 46%

Feature 23

2d · 0%

Onboarding

Feature 8

6d · 51%

Feature 16

4d · 80%

Growth

Feature 6

3d · 22%

Feature 12

1d · 47%

Three questions

Feature 4 spread across 9 scattered days — what kept it from one or two dedicated sittings?
Across the window the product analyzes a person, yet the closest thing to an outside user was a friend asking about the report on 07-09. Did a real external user actually try it this window, or is that still ahead?
A steady share of the period went to tooling that measures the work rather than the product itself — is that the plan, or did it creep?

Another gift, to keep you accountable

Your KPIs from the previous day every morning, and reminders.

Your daily accountability partner

Paste into Claude Code — it installs it as a skill and a daily loop.

Catches your late starts, since you first touch the keyboard around 11 most days, and asks for the one thing before noon.
Shows you each morning what yesterday actually produced: how long you were in flow, what you touched, and whether anyone outside saw it.
Flags when you have polished the same thing for days with no one new seeing it.
Reminds you at night to write tomorrow's first task, since walking straight into a hot thread is what starts your best days.
Nudges you to queue the next thread before your agents finish, because your parallel set keeps draining to nothing around dinnertime.

▸ the full instruction (what you're installing)

---
name: accountability
description: Daily coding accountability partner built from John's own session telemetry.
---

You are John's accountability partner. Speak like a sharp friend: few words, one nudge a day, accurate and kind. Read .data/coding/focus.json fresh each time to compute today's and yesterday's facts. Never recite numbers he already knows.

Morning, first message of the day, two beats:
1. Recap yesterday in 2-3 lines from focus.json: how long he was in flow, which features he touched, whether anything reached outside eyes.
2. He first touches the keyboard around 11 most days. If it is later than that, say so plainly, then ask: 'What is the ONE thing today?'

Evening:
- Have him write tomorrow's first task before closing. Returning straight to a hot thread is what starts his best days.

Resolution echo (use at most once a day):
- If the day ran silent on slow runs or ended on 'did it work', quote his own rule back once: lead with the verdict, and render anything hard to judge.
- His threads drain to nothing around dinnertime (22 times over the window). If he is juggling in the afternoon, remind him once to queue the next task before the agents finish.

Schedule: run the morning beat at first activity, the evening beat at his stop time, and on demand via /accountability. Invent nothing; if focus.json is missing a fact, say so.

Parallelism

— how many agents you drive at once→

Your peak

×6

07-08

the best

×12

Your average

×1.5

while anything runs

the best

×6

How much time at each level

×60.2h

×51.3h

×43.8h

×314.5h

×243.8h

×1107.8h

How you use AI

What you’re doing with AI

Skills & tools you actually use

You drive up to ×6 agents at once — genuinely good, and you can push it a little further.
You explicitly reach for migrate-desktop-account-sessions — very good.
▸ details
Twice asked explicitly by name ('that skill', 'that claude skill') to pull chats and scheduled tasks from an old Claude account into the current one, once for the whole backlog and once for just the 3 latest sessions. Both runs completed cleanly and were verified (56 chats migrated with tasks merged, then 3 more sessions), with no complaints from the user afterward.
You explicitly reach for dataviz — very good.
▸ details
Explicitly asked for an HTML dashboard breaking down 5-hour usage-limit consumption per pipeline stage, then iterated hard on it: drop dollar figures, show percent of the limit, scale to the whole run not a single day, and factor in an Opus-to-Sonnet cost comparison. The user corrected the chart's framing five separate times ('bro we literally ran into a 5 hour usage limit at night how can it be less than 100%') before landing on a version that matched what they actually meant, showing real engagement rather than one-shot satisfaction.
You explicitly reach for whatwasidoing — very good.
▸ details
Used as a sub-step to reconstruct specific past dates (light/off coding days, days with the biggest excluded/away hours) as part of a larger self-analysis effort, matching the exact 'what was I doing on X' recall job the user's own CLAUDE.md designates this skill for. Fed directly into the broader pattern-analysis work the user was steering turn by turn; no pushback recorded on the date reconstructions themselves.
You explicitly reach for deep-research — very good.
▸ details
Explicitly asked to 'run hella web searches' and find state-of-the-art research on qualitatively scoring intelligence-like constructs, to use as the basis for redesigning a scoring rubric together. The fan-out returned strong technical results (112 agents, 29 sources, 24 of 25 claims surviving adversarial verification), but the user then had to ask the model to drop jargon ('What the hell is a gestalt? Be easy with your language'), showing the deliverable needed translation before it was usable to them.
You explicitly reach for update-config — very good.
▸ details
Directly asked for a persistent 'whenever I run Claude Code, keep caffeinate on' automation, which is exactly the hooks-based always-on behavior this skill exists to configure. Shipped and verified three ways including in production, with no follow-up complaints — a clean single-shot success.
You drive Chrome / browser automation by explicitly asking — very good.
▸ details
Explicitly directed at least twice by name ('using Chrome to submit the form', 'Use chrome automation', 'you already can use using the Chrome MCP, whatever, Operate that') to drive Google OAuth verification setup, startup-credit application forms, and AWS console provisioning for an EC2 instance.
You drive Computer use (native desktop control) by explicitly asking — very good.
▸ details
Used alongside Chrome-based control for concrete infrastructure tasks, most clearly when the user told the model to operate a signed-in AWS console tab directly to provision an EC2 box and upload local data to it.

What you’re not doing — and why it’d help

Invest in your CLAUDE.mdcontext

The gap — You re-teach Claude the same anti-fluff, no-jargon, 'feel seen' copy rubric by hand almost every session.

Why it helps you — Tell Claude once, 'add that to your CLAUDE.md,' and the correction sticks for every future session instead of being re-typed. Your recurring rule — no cringe copy, no jargon, no em-dashes, every claim tied to a real example — belongs there, not repeated by hand each time.