From 1734f13a2e6445bbd10150fd091c22072606053c Mon Sep 17 00:00:00 2001 From: Paul Bakaus Date: Tue, 14 Jul 2026 19:18:29 -0700 Subject: [PATCH] a26: finishing review runs in a separate agent when the harness supports it (fresh reader, builder thread stays building) Paul's goal 7: post-checks in a separate agent thread; subagent spawn-at-end now, pro-tier remote endpoint later. Co-Authored-By: Claude Fable 5 --- skill/reference/new-work.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/skill/reference/new-work.md b/skill/reference/new-work.md index 9e163ea35..b63e9c2a1 100644 --- a/skill/reference/new-work.md +++ b/skill/reference/new-work.md @@ -55,3 +55,5 @@ Layout: asymmetric compositions and intentional grid breaks are on the table; fl ## Finish like a studio Look at what you built the way a design lead would, with whatever eyes the harness gives you (browser, screenshot tool, or reading the code cold): major sections individually on long pages, mobile and desktop at minimum. Write an honest critique against the brief and the stated direction, patch material defects, and re-inspect; don't invent defects to demonstrate diligence. Then verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done, and neither is a polished page missing something the brief asked for. + +When the harness can run a separate agent, the review above belongs there, not here: hand the reviewer the artifact path, its direction contract, and the detector command, and have it return a short list of material fixes; apply them and finish. A fresh reader catches what the builder's own eyes slide past, and the build thread stays spent on building.