Omarchy 4 and Basecamp 5 put the agent boundary at the age of the codebase

An agent working a feature ticket sees the repository, the tests and the prompt. It does not see the decisions that were made once and never written down: which layer may touch the database, which object owns a lifecycle, which duplication was deliberate. Local correctness is checkable, which is why each pull request passes even though nothing checks the union of pull requests. The publisher's framing is right on that point, that an agent can produce functioning code without understanding the years of accumulated decisions that make a large application maintainable ^[14], and Hansson says this is what showed up at 37signals as pull requests that read reasonably one at a time and needed human programmers to clean up ^[8].

Reviewing overall structure is cheap when the structure fits in one head. Hansson says he directed Quattro, inspected its structure and reviewed critical sections while hand-writing none of the shipped code ^[5], and the official release materials describe a unified Quickshell-based shell, dual-boot support and faster installation ^[2], so the agent work covered a shell, not a theme refresh. Copying that division of labour means reproducing the conditions attached to it: one owner holding the whole design, and a repository young enough that this month's choices are not constrained by old ones. Omarchy started in the summer of 2025 ^[1]. Basecamp 5 was not built that way, since designers were implementing features directly alongside programmers ^[7], and the codebase belongs to the company where Hansson built Rails before releasing it in 2004 ^[13].

"All the code shipped" is a provenance claim, and provenance is measured at the commit. It is compatible with a great deal of human work upstream of the commit: specifying the problem, choosing among proposed solutions, judging whether the result is coherent ^[6]. Hansson closes off the loose reading himself, defining vibe coding as asking an agent to build software without examining the implementation, and saying his own workflow still depends on technical judgment ^[11].

The dates need work. The account puts his change of mind at November 24, 2025 ^[10], the Fridman conversation's posting at August 26 ^[4], and the Quattro release at around August 21 ^[16]. Two months of agent-led implementation ending at that release places the work somewhere between late June and August ^[18], which puts the stated conversion after the release it is offered to explain ^[17]. One of those dates is wrong; a five-hour interview will not tell you which.

The softest figure is the one the publisher already flags: tens of thousands of downloads shortly after launch, on Hansson's own count, with no independently measured active-user number ^[12]. Installs say nothing about whether agent-written code survives its second year of changes. As evidence this is one participant's report on two codebases he owns, thinner than a study and more useful than another benchmark table, because it names the variable ^[15].