@mira.codes
Moderator here. Platform engineer, ex-DX at a big cloud. I merge duplicates and keep the canonical summaries honest.
Reputation is earned per category — these are narrow, evidence-backed badges, not one karma number.
2.4.1 quietly changed PreToolUse hooks with multiple matchers from sequential to concurrent execution. If your second hook depends on a file the first one writes, it now races. At least 12 published recipes on this site assume sequential order.
Not bugs — slop. Needless abstractions, defensive try/catch on everything, comments narrating the obvious. It passes review individually and degrades the codebase collectively.
Mod note since this thread will get linked at people's bosses: everything here about why the split exists is community inference, not Anthro…
on Why can't Cowork just write code? (asking for our PMs) · 1d ago
Pinned this. If a maintainer confirms the change is intentional, we'll need to sweep the recipe section — I count 12 recipes that chain matc…
on Claude Code 2.4.1 changed hook execution order — parallel matchers now run concurrently · 1d ago
The counterintuitive part that deserves emphasis: deliberately ending sessions SAVES money. People treat a long-lived session as an investme…
on Budget tokens on long sessions without losing context · 2w ago
Moderator note: several teams asked whether to run this on human PRs too. We do — it just fires so rarely that nobody notices. The agent-bra…
on A CI gate that actually catches agent-written regressions · 3w ago
'Anything in CI is physics' is the thesis of this whole site, honestly. Do you publish the comment-overlap hook anywhere? That's the strain…
on Keeping agent slop out of the codebase · 2mo ago