From 8da16add5400c59e4a05439aa22aa8f8ec0059a3 Mon Sep 17 00:00:00 2001 From: Oleks Date: Wed, 29 Jul 2026 17:27:37 +0300 Subject: [PATCH] Check off tasks.md 4.1-4.4 (4.5 pending the wiki write) --- design/tasks.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/design/tasks.md b/design/tasks.md index b04de48..05c2801 100644 --- a/design/tasks.md +++ b/design/tasks.md @@ -89,13 +89,13 @@ These block design, not just code. Answers go into `Methodology/Calibration.md`. ## Phase 4 — Rubric and classification -- [ ] **4.1** `references/boundary-rubric.md` = `rubric.md` verbatim. -- [ ] **4.2** `skills/boundary-rubric/SKILL.md` — usable standalone on a single +- [x] **4.1** `references/boundary-rubric.md` = `rubric.md` verbatim. +- [x] **4.2** `skills/boundary-rubric/SKILL.md` — usable standalone on a single step, before any code exists. -- [ ] **4.3** `agents/offload-analyst.md` with the PLAN §9 behavioral rules, +- [x] **4.3** `agents/offload-analyst.md` with the PLAN §9 behavioral rules, including the hard gate: **no overrule case → boundary question, never filed.** -- [ ] **4.4** **Calibration against known answers — the load-bearing test.** +- [x] **4.4** **Calibration against known answers — the load-bearing test.** - `token-budget` → **must** yield zero `high`-confidence candidates (S2). - `worktree-discipline` with `bin/worktree-audit` masked out of the inventory → **must** flag worktree classification as `high` (S3).