< Build Your Own Lightsaber

I'm going to make a painfully dorky analogy. Vibe coding your own harness tools is like building your own lightsaber.

Three reasons.

(1) Building it teaches you how it works. A Jedi builds their own saber so they understand it. Writing a hook teaches you when it fires, what the model sees, and what it ignores. When your own tool breaks you know why (and can perhaps find a better way).

(2) It's a key accelerant. I put half my day into supporting tools and still target 100 PRs a day. That only works because the tooling pays for itself. It's painful at first (because it's slower), then it pays back, and more with every model release. Treeline is just one example: a menu bar app that drops me straight into the PRs that need attention and keeps score against the hundred.

Treeline, a vibe-coded macOS menu bar app showing a 24-hour chart of open and merged pull requests, merge counts, and a burndown list of PRs with review and CI status.
Treeline, my menu bar tool for quickly jumping into PRs and tracking against my 100-a-day goal.

(3) It's the piece that should be vibe coded. You can really cut loose when the only customer is you, and I've learned more about the potential (and limitations) of vibe coding from building out my own harness than from anything else. As long as they're secure, I don't need to be particular about how they're built, and I'll happily build them in Swift (like Treeline) or whatever else fits. Things are moving fast in this space, and harnesses turn over fast too. More than once I've built something only to find it shipped as a standard feature shortly after. I had a tool that automatically detected comments on a PR and got Claude to respond. It was a standard feature in Claude Desktop three months later. If something better ships, delete yours.

Even when nobody ships your tool as a feature, it goes stale on its own. Every model update shifts what the AI gets wrong, so last quarter's essential hook is this quarter's noise. And tooling can become its own distraction; it's easy to lose an afternoon perfecting something you'll barely use. So build the tool when you hit the same bump twice, use it on the next PR, and delete it as freely as you built it. Did it help today? If not, bin it.

Borrow a saber to get started. But if you live in the harness all day, build your own.

Also read: Vibe Coding Dev Tools, Sharpening the Axe (Branch), Tool Augmented Prompting, and The pace of AI tools.

I write about AI, organizations, and engineering leverage: find out about me and subscribe here.

Discuss and share via the meta page . Filed under AI, Code, and 100PR.