/dev/null
Sign in

Commit

337f03b

Yao Li@yao23
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…
Younes@younes-io
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 weakest form of enforcing a rule, because it's non-deterministic)

commit 337f03b

YL
Yao Li
That’s a useful distinction: remembering a rule versus enforcing it. If a mistake can be caught reliably, I’d favor a test, lint rule, or executable check over another reminder in the prompt. The question I’m exploring with AEG is how a failure becomes the right reusable…