Buy Back the Coverage
I had already published the warning: if a model only judges what a scanner shortlisted, a site the scanner fails to flag is a false negative nobody ever sees. A wrong flag costs a cheap check and gets caught.
Tagged craft
-
-
A Constraint You Can Quietly Lift Isn't One
I had a harness measuring whether a set of skills helped a cheap model. It came back negative: no lift worth the tokens. I believed it.
-
Build the Operator, Keep the Operands as Data
A good rule set grows. Mine has grown — tested against a whole corpus of real PRs and code — into something too big to hand a model all at once, and that's the scale problem Rules Are the Alpha ends on.
-
The Harness Is the Product
The reviewer is the visible product: it reads a diff, applies a rule corpus tested against real PRs and code, and ships the findings worth a person's attention.
-
Train on What the Gate Throws Away
My code reviewer does far more work than it ships. Scouts cast a wide net — anything that might be a violation.
-
Keep the Factory, Ship the Result
I built an eval to tell me whether my agent's skills were earning their place. For a while it said they weren't — clean, green, confident.
-
Fluent in a Dead Idiom
A newer engineer left a note on my pull request: this array should be readonly. He was right.
-
Rules Are the Alpha
Two reviewers, the same commit — a fat change, a few thousand lines. One was a deep reviewer I own, running a portfolio of judgment rules tested across a whole corpus of real PRs and code.
-
The Nit Was Never Optional
Read that definition again. It's one of the most widely-cited code-review standards telling reviewers how to flag a small issue: say the author should fix it — then, in the same breath, that they needn't bother.
-
Your Merged-PR History Is Survivorship-Biased Training Data
In the Second World War, the Statistical Research Group was asked where to add armour on bombers, and handed the damage data from the planes that came back — most shot up on the wings, fuselage, and tail.
-
Confidently Wrong
A model handed me a clean answer once. Well structured, sure of itself, and wrong — and nothing in how it was written gave that away. It read the same when it was guessing as when it knew.
-
Your Skills Are a Codebase, Not a Junk Drawer
I asked the agent to review a diff. Two skills woke up and started fighting over whose job it was. And the skill I'd built a week earlier for exactly this review? It never stirred.
-
Skills are one-offs. If you want an ecosystem, you need plugins.
You wrote a skill. It's good. Now you want it to lean on another skill — call it, require it, ship the two together so installing yours pulls in the one it depends on. So you go looking for a dependencies field.
-
"Context Debt" Is a Strawman
Here's the pitch, and it's a good one. Vibe-coded slop is only the symptom; the disease underneath is context debt — the steady loss of what the code means and how its parts connect.
-
Teaching the Reviewer
I was building a code-review tool. Nothing fancy — read the diff, flag what's wrong, the job I do by hand a dozen times a week. Partway in I stopped on a question bigger than the tool.
-
Thinking at the Speed of Code
A while back, I stopped reading the AI's end-of-task summaries and started watching the diffs. They came through faster than I could have typed them. I wasn't reading them line by line — I was watching the shapes go by.
-
The Productivity Mirage
Sixteen experienced developers finished 19% slower with AI and believed they were 20% faster. The feeling of a fast session tracks fluency, not distance.
