From e25b93505ea1e53245ae9d79c911dab0bd95fd32 Mon Sep 17 00:00:00 2001 From: garrytan Date: Tue, 3 Nov 2026 16:03:17 +0000 Subject: [PATCH] changelog: /review saves about 3.3 KB (3,298 B), same decimal rounding as /investigate Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- changelog.d/capy-gst-1088-lane-c.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/changelog.d/capy-gst-1088-lane-c.md b/changelog.d/capy-gst-1088-lane-c.md index 75aed8173..4809ec2ab 100644 --- a/changelog.d/capy-gst-1088-lane-c.md +++ b/changelog.d/capy-gst-1088-lane-c.md @@ -1,4 +1,4 @@ -**/investigate loads about 3.4 KB less and /review about 3.2 KB less, and a /review blocker now needs proof (GST-1088 lane C, the candidate).** Opus 5.5 read these skills in full and still skipped their required steps (Run D, gstack-evals#140). The forced full /review caught 67.2% of blocking bugs but raised 2.71 false blockers per PR per pass (gstack-evals#120). This change cuts pieces of the two skills that nothing showed were doing work, and it makes every blocking /review finding prove itself. It merges only after the GST-1089 no-loss replay passes. +**/investigate loads about 3.4 KB less and /review about 3.3 KB less, and a /review blocker now needs proof (GST-1088 lane C, the candidate).** Opus 5.5 read these skills in full and still skipped their required steps (Run D, gstack-evals#140). The forced full /review caught 67.2% of blocking bugs but raised 2.71 false blockers per PR per pass (gstack-evals#120). This change cuts pieces of the two skills that nothing showed were doing work, and it makes every blocking /review finding prove itself. It merges only after the GST-1089 no-loss replay passes. ### Changed - **Cuts, every loadout and every host**: /investigate drops its learnings search, Capture Learnings and the investigation-typed learnings log. /review drops its learnings search, Capture Learnings, the repo-ownership preamble section and the Step 3.4 VERSION queue line. Always-loaded bytes: /investigate 21,242 to 17,838, /review 60,014 to 56,716 (Claude SKILL.md, frontmatter included, against v1.94.24.0). Telemetry (`gstack-skill-end`) stays, because it writes the timeline's `completed` event with the real outcome. No other skill changes on any host.