From 3bc79274a9a97b9f9f3a6292920ae2b3af856fc2 Mon Sep 17 00:00:00 2001 From: Marius Ciepluch <11855163+norandom@users.noreply.github.com> Date: Wed, 30 Sep 2026 18:23:09 +0200 Subject: [PATCH] bench(independent): protocol v3 budget and shadow-rule choices confirmed by the maintainer Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo --- benchmarks/independent/protocol-v3.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/benchmarks/independent/protocol-v3.md b/benchmarks/independent/protocol-v3.md index d476a26..c1fcb50 100644 --- a/benchmarks/independent/protocol-v3.md +++ b/benchmarks/independent/protocol-v3.md @@ -165,3 +165,9 @@ stability, spend. Shadow quick rules are reported separately as exploratory. (`tests/test_independent_population.py`). - No result of a case whose licence is marked "verify" is published until the licence is checked. Kirby is not OSI-licensed: its results are unpublishable without the licensor's permission. + +## Maintainer confirmation (2026-09-30, before any scan) + +The maintainer confirmed the two choices made while drafting: the model-spend ceiling of $60 in total and $6 per +case (a case stopped by its cap counts as not detected), and shadow quick rules reported as exploratory only, +outside every gate. No v3 repository had been scanned when this was confirmed.