Field notes, written as I ship. Newest first.
39 posts
Quick answer (2026): I ran the same feature through GitHub Spec Kit, Kiro, and a plain plan.md in Claude Code to see which spec-driven setup actually earns its place. Spec Kit wins for writing shared project rules, Kiro wins for killing spec-and-code drift, and a hand-written plan.md wins on setup cost. The plain plan.md is the one I kept.
A three-month field log on the best MCP servers in 2026: the five that earned a permanent slot, the ones I uninstalled, and the context and trust costs no listicle mentions.
I hit Claude Code's weekly limit mid-refactor, then ran the same repo through seven alternatives for two weeks. The three I kept, and the honest catch nobody markets.
My CI step running claude -p hung for the full timeout, waiting on a permission prompt no human would answer. The three flags that fix headless Claude Code, the jobs I kept, and the two I ripped back out.
A month of running Cursor and Claude Code on the same repo. The honest 2026 verdict: it is not either-or, and the real question is not IDE vs CLI.
A field log of Claude Code's built-in /sandbox: what its OS-level cage actually locks down, the setup that bit me, what auto-allow still stops for, the tools that broke, and the one thing it does not protect.
Claude Code checkpoints and /rewind are fast in-session recovery, not version control. A field log on what a checkpoint actually captures, what it silently ignores (bash writes, your own hand-edits), and the two-line git habit that keeps it safe.
A first-person weekend log of cloning and running ai-app-builder-open, an open source AI app builder, on localhost. What worked, the one API key you need, and the honest catch versus local-first Dyad.
The three arrays, the precedence rule nobody explains, the two gotchas that cost me an afternoon, and the exact settings.json allow, ask, and deny block I run now.
Two weeks of pushing real work onto Claude Code subagents. The two I kept, the frontmatter line that actually decides delegation, and the gotcha that cost me an afternoon.
An honest 2026 field log on Claude Code skills: I installed 30 community skills, deleted almost all of them, and kept the three I wrote for my own repo. What a skill is actually good for, and the rule I use to pick skill vs CLAUDE.md vs MCP.
I ran spec-driven development for a month on a live B2B product. An honest 2026 field log: where the spec earned its overhead, where it was pure ceremony, and the six-heading spec that survived.
