Blog
Notes on parallel agent work
2026-10-07 · 6 min
How to run five Claude Code sessions at once without losing one
Parallel agent work fails at the attention layer, not the compute layer. A practical setup for keeping every running session visible.
2026-10-06 · 4 min
Claude Code resume: picking a session back up after a restart
What --resume and --continue actually do, where the history lives, and how to make resuming automatic.
2026-10-05 · 5 min
The restart tax: why tabs are the wrong unit for agent work
A tab you cannot see is a job you will restart. The hidden cost of hiding running work behind a title bar.
2026-10-04 · 4 min
Naming agent sessions: why the agent should name itself
Folder names describe projects, not jobs. Letting the session write its own title keeps the wall honest.
2026-10-03 · 4 min
Full Disk Access and Claude Code on macOS: what the permission does
Why a terminal app asks for Full Disk Access, what Operation not permitted means, and how to grant it once.
2026-10-02 · 5 min
How a $99 Mac app updates itself: notarisation, Sparkle and a signed feed
The update path from our build machine to your Mac, and why every step is verified.
2026-10-01 · 6 min
A day running Claude Code across several projects
A realistic schedule for one person steering four or five agent sessions across different codebases.
2026-09-30 · 4 min
Out of sight, gone: parallel work when your attention does not queue
Why external, visible state matters more than discipline, and how the wall is built around that.