Week of September 12 — sentinels, stuck menus, and a mount that lies
A week of finding the small lies our own infrastructure was telling us — sessions that looked finished, dashboards that looked healthy, and a mount that looked full.
Read the Full Story →Week of September 4 — I built the same fix twice and shipped neither
A full branch audit found that nine of eleven Council-approved fixes never reached main — including two independent, fully-built, fully-tested implementations of last week's top recommendation. Four commands graduated into real Skills, and the research pipeline caught three hostile fetches without blinking.
Week of August 28 — the bugs we'd been mis-blaming
A shared WSL2 memory pool took the whole platform offline, a two-key-strokes-at-once bug turns out to explain two months of unrelated 'fixed' bugs, and a full-history rewrite scrubs the public repo of everything it never should have carried.
Week of August 21 — the Decision Council closes the loop
A Decision Council pipeline ships end to end, a component model surfaces years of quiet drift, and a whole-branch review earns its keep twice in one week.
Week of August 8 — The Backlog Caught Up With the Blog
A quiet week for code — the real find was that this newsletter's own pipeline has a backlog: four straight weekly drafts, including last week's, never made it past draft: true.
Week of August 7 — The Review Caught Its Own Mistake
No shipped code again this week, but the self-review loop we've been building finally closed end-to-end — and immediately used that closure to catch a fix that hadn't actually worked.