Side page · Counted, not estimated
By the
numbers
What does AI-assisted building actually consume? A few hours a night, instrumented.
This started as a curiosity rather than a scoreboard. I had no real intuition for what an agentic workflow costs — how much of the traffic is the model reading versus writing, how many calls a single evening burns, how much of it is subagents. So I measured my own.
context loaded again on a later call — the same files, plans, and earlier turns. Re-reading the state of the work, not producing new text, is where an agent’s budget goes
everything the models read across 59 measured sessions, cache included
the words and code the models actually produced — one token written for every 454 read
across 59 sessions and 349 subagent runs — about 342 calls in a typical working evening
2,149 commits · 293,075 lines of code · 92,585 lines of specs and docs · 352 test files · 10 repositories · 36 days on record · measured 2026-08-26
THE LEDGER
| Project | Sessions | Tokens | Commits | Lines of code |
|---|---|---|---|---|
| Gridiron Guesser | 20 | 1.1B | 617 | 94,217 |
| Tooth Fairy Radar | — | — | 17 | 5,714 |
| Undercut | 1 | 14.5M | 1,260 | 102,120 |
| Hold the Line | 6 | 2.6B | 106 | 37,049 |
| Analysis Workbench | 2 | 360.4M | 1 | 19,680 |
| Zuzy’s World | 3 | 351.0M | 26 | 7,033 |
| Reading Helper | 5 | 573.9M | 59 | 18,459 |
| Memories | 3 | 479.5M | 0 | 0 |
| This site | 19 | 515.8M | 63 | 8,803 |
THE RECORD
Claude Code has been running here since Mar 2, but it deletes its own session logs after thirty days. By the time I went looking, 122 days of it had already been swept — the left-hand stretch above, and the reason this page starts in July rather than March. Nothing recovers it.
So the site now keeps its own copy. Every run folds the days it can still see into an archive that ships with the repository; a day on record stays on record after the transcript behind it is gone. 36 days are held that way today. That count can grow from here. It can no longer quietly shrink.
HOW THIS IS COUNTED
Nothing on this page is estimated. Tokens come from the session logs Claude Code writes on my Mac, accumulated into an archive that ships with the repository; commits come from GitHub; lines are counted from fresh clones. A script gathers all of it and regenerates this page.
Every number is a floor, not a ceiling. Tooth Fairy Radar was built before I kept any logs at all, first as code pasted by hand out of a chat window, later through agent-authored pull requests, which is why its token column is a dash. Undercut’s 1,260 commits mostly predate the logs too. The work happened; the meter came later, and then the meter forgot. Only the second of those is fixable, and it is fixed.
“Tokens processed” counts everything the models read, including the 98% that is cached context re-read on a later call — that’s how agents actually work, so that’s what gets counted. Each request is counted once: resuming a session rewrites its earlier turns into a new transcript, and tallying those lines instead of the requests behind them would inflate the total by about a third. Every project is on this ledger by name, shipped or not — the repositories are private so the code can’t be lifted and redeployed, which is a different thing from the work being secret.
WHAT THIS DOESN’T MEASURE
Lines of code sits in the strip rather than the headline because it is the least meaningful number on this page. An agent will cheerfully write four hundred lines where forty would do, and the evening I spend deleting two hundred of them is progress this page records as nothing. Commits have the same problem: they count pushes, not progress.
More to the point, none of this measures authorship. The interesting question was never how much code an agent typed. It is which decisions still need a person: what is worth building, how the system is constrained, what counts as correct, and whether the result has earned the right to ship. The architecture, the constraints, and the definition of correct on every project here are mine — a great deal of the typing was not — and the rules I work by exist precisely because a model left to its own devices produces something plausible and quietly wrong.
What the meter does capture is the shape of the collaboration. A ratio of one written token to every 454 read is not a productivity claim; it is a description of what these tools actually do all night, which is re-read the state of the work before making the next small decision about it.