When a coding agent repeats a mistake you’ve already corrected, where should that lesson live?
A regression test?
A repo instruction?
A reusable skill?
Somewhere else?
My working view: observable behavior belongs in tests; procedural guidance may belong in a skill; both need a clear scope.
But I’m testing that distinction, not treating it as settled.
What’s one lesson your team has successfully carried from one task to another—and what made it reusable?
commit 3e4789e
A mistake should become a deterministic guardrail (ideally) like a linting rule or maybe some compiler option you add; or a Claude Code hook in JS/shell that gets triggered after a commit/an event; if not possible it could be another instruction in your prompt (which is the…