Twenty-six weeks of work, measured. Output peaked in mid-July and has roughly halved since, which sounds like a slowdown and is not one. The number that fell is the wrong number, and the thing that actually changed is visible in a different chart.
It tracks the model in use. The Co-Authored-By trailers run Opus 4.6 through
4.7, 4.8 and 5, and both peak weeks — 437 and 414 — sit squarely in the 4.8 era. It
tracks how the work was chunked: weft’s 256-commit week was a
fleet of workers each landing one CSS section against an oracle, while the 88 commits of the
week after contain a bare-metal SSH login that took days to earn. And it inverts during
integration — the broadest week in the whole record, touching 23 repositories, is also one
of the quietest by count.
Split by where the commits landed, though, it says something real.
| # | week ending | modus | other | total | repos |
|---|---|---|---|---|---|
| 1 | 2025-03-15 | 1 | 0 | 1 | 1 |
| 2 | 2026-02-28 | 4 | 0 | 4 | 1 |
| 3 | 2026-03-07 | 3 | 0 | 3 | 1 |
| 4 | 2026-03-14 | 3 | 0 | 3 | 1 |
| 5 | 2026-04-11 | 50 | 0 | 50 | 1 |
| 6 | 2026-04-18 | 107 | 0 | 107 | 1 |
| 7 | 2026-04-25 | 82 | 0 | 82 | 1 |
| 8 | 2026-05-02 | 159 | 0 | 159 | 1 |
| 9 | 2026-05-09 | 62 | 0 | 62 | 1 |
| 10 | 2026-05-16 | 111 | 0 | 111 | 1 |
| 11 | 2026-05-23 | 87 | 0 | 87 | 1 |
| 12 | 2026-05-30 | 111 | 0 | 111 | 1 |
| 13 | 2026-06-06 | 173 | 0 | 173 | 1 |
| 14 | 2026-06-13 | 113 | 0 | 113 | 1 |
| 15 | 2026-06-20 | 186 | 41 | 227 | 3 |
| 16 | 2026-06-27 | 72 | 52 | 124 | 4 |
| 17 | 2026-07-04 | 66 | 371 | 437 | 14 |
| 18 | 2026-07-11 | 61 | 172 | 233 | 17 |
| 19 | 2026-07-18 | 43 | 248 | 291 | 27 |
| 20 | 2026-07-25 | 16 | 398 | 414 | 29 |
| 21 | 2026-08-01 | 104 | 190 | 294 | 34 |
| 22 | 2026-08-08 | 112 | 106 | 218 | 38 |
| 23 | 2026-08-15 | 180 | 93 | 273 | 38 |
| 24 | 2026-08-22 | 37 | 99 | 136 | 42 |
| 25 | 2026-08-29 | 41 | 47 | 88 | 42 |
| 26 | 2026-09-05 | 0 | 110 | 110 | 42 |
Weeks 1–14 are one repository. A language being built, with nothing to reuse because nothing else exists yet. Fifty to a hundred and seventy commits a week, all of it modus: a garbage collector, a calling convention, a numeric tower, an object system, and a test harness that had to be rebuilt after it was caught losing 17,587 tests without saying so.
Weeks 15–22 are the explosion. The workspace goes from one repository to thirty-eight. Ten appear in a single week, twice. This is where the eye-catching numbers live, and where the compounding starts: each new thing is written on top of things written days earlier.
Weeks 23–26 are integration. Zero new repositories in three of the four. Forty-two exist and the work is making them behave as one machine — which is where kiln, glass-sdl and operandi-gui came from. Fewer commits, more repositories touched per commit, bigger consequences. It reads as a slowdown on the chart and is the opposite.
If commits are a bad unit, elapsed time to a verifiable capability is a good one — especially here, where almost every library is graded against somebody else’s implementation, so “working” has a date attached rather than an opinion.
These are not the durations of finished software — folio kept going for another day on JBIG2, fax decoding and CJK character maps. They are the durations of the gap between nothing and a thing that passes somebody else’s test, which is the interval where a project either has momentum or does not.
The acceleration is not typing speed. It is that by July there was a substrate. Repositories born before 15 July depend on a mean of 1.47 other workspace libraries; those born after, 2.04. The tails carry more than the mean: weft draws on nine of them, glass on eight, cairn and loom on five each.
The clearest single case is a chain nobody planned in advance.
pagetree was written in June as a crash-safe B-tree for a Bitcoin
node’s UTXO set. In July cabinet became a filesystem on top of
it, and cairn — a from-scratch git — learned to keep an
entire repository inside a cabinet. The first link in that chain took nine hours: pagetree's
first commit landed at 23:39 on a Sunday and the Bitcoin node was storing its UTXO set in it by
08:46 the next morning. Which is what lets a git implementation run on a machine
with no filesystem, and why kiln can clone thirty-three repositories
into a container image that contains no git binary at all.
Look at the copper band in the first chart again. It does not bend. modus takes 37 to 186 commits every week from April to now, through the explosion, through the integration phase, at a rate essentially independent of everything happening above it.
That is the honest limit on all of this. Breadth work got roughly an order of magnitude from oracles, fleets and a growing substrate. Depth work — a collector, a calling convention, a tag scheme, a symbol table — got about one. You cannot fan eight workers at a garbage collector, because the bug is never in eight places; it is in the interaction between two, and finding it is serial no matter how many hands are available.
The best evidence is how long wrong beliefs survived:
The shallow mistakes were caught by tooling in days. The deep one needed somebody to load real software and watch what broke, and no amount of parallelism shortens that.
Forty-one repositories compound. One does not, and it is the one underneath all of them. That is not a criticism of how the work is being done — it is the shape of the problem. But it means the useful question for the next twenty-six weeks is not “how many commits”; it is whether the floor can be made to compound too. Every build check, every oracle, every census before a deletion is an attempt at exactly that: turning a thing somebody has to remember into a thing the machine refuses to let you get wrong.