Adapt CB-WP-0021 and CB-WP-0022 to ground-game's rulings

GR-S01 was ruled 2026-08-04: Surface always, union hidden priorities
1..k, k = 2/3/4. So the deal is 3/4/5 Problems, not 2/3/4; available
points 6/9/12; thresholds 5/7/9 stand; SHARED GROUND is 2-6p as printed.
The question CB-WP-0021 was going to send has been answered, and it was
the deal.

CB-WP-0021 is re-scoped. The import is now LOAD-BEARING rather than
merely correct: the ruled 6/9/12 holds only with Problems.csv values, and
the same deal with the stand-in gives 6/10/15 -- a different game that
happens to also be winnable. Fixing the deal without importing the data
would produce numbers nobody ruled on, so T05 (deal) and T02 (import)
must land together. gd0001 is to be INVERTED, not deleted: it is the
record of why this changed. gr-e01 is rewritten as a non-provisional
import check, per the ruling's own wording, and loses its provisional
owner because ground-game has now ruled.

CB-WP-0022 absorbs ground-game's process ruling, which is stricter than
this pass proposed: arithmetic findings need a runnable reproduction AND
a row-level deal table listing Surface and each hidden priority
separately, never only a sum or a deal depth. That is a direct
consequence of both premises we got wrong. So the reproduction rule gains
a SHAPE requirement, not just an existence one -- a finding that ships a
passing test but describes the wrong quantity is still a bad finding, and
that is what happened twice. T02's review brief is flipped accordingly:
press whether the rule is SUFFICIENT, not whether it is affordable.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

workplans/CB-WP-0022-the-design-instrument.md

@@ -161,7 +161,12 @@ above, and require an attempt at:
   third thing;
 - **that "carries its reproduction" is affordable** — if half the real
   findings cannot be reproduced cheaply, the rule will be quietly dropped
-  and the register becomes a suggestion box anyway;
+  and the register becomes a suggestion box anyway. *(Since this task was
+  written the answer has hardened: two findings reached ground-game on
+  wrong premises, and ground-game has itself ruled that reproductions are
+  required. The reviewer should now press the opposite way — whether the
+  rule is **sufficient**, given both bad premises would have shipped a
+  passing test alongside a wrong description.)*
 - **that a register is needed at all**, rather than one more section in
   `GroundRules.md §Underdetermined`, which already exists and already
   works.
@@ -212,6 +217,26 @@ Candidate measures, to be argued not adopted:
   *read*; that is the number this exists to fix;
 - **findings closed by a ruling** vs **findings still open**, with age.
 
+**ground-game has ruled on what a finding must carry** (GROUND-WP-0004
+T02, 2026-08-04), and it is stricter than this pass proposed. Adopt it:
+
+> 1. Arithmetic findings must ship a **runnable reproduction** *and* a
+>    **row-level deal table** listing Surface and each hidden priority
+>    separately — **never only "sum of file" or "deal depth N"**.
+> 2. ground-game rulings that depend on arithmetic **should cite** that
+>    reproduction id or path, so a later reader can re-run it.
+
+The second half is theirs to keep. The first is ours, and it is a direct
+consequence of both premises we got wrong: *"12 in the file"* was a sum
+without a deal table, and *"offered on a face-down Problem"* was a
+condition named without checking which one actually fired.
+
+**So the reproduction rule gains a shape requirement, not just an
+existence one.** A finding that ships a passing test but describes the
+wrong quantity is still a bad finding — which is exactly what happened
+twice. The spec must say what a reproduction has to *show*, not only that
+one exists.
+
 Also specify the **trial protocol**, which is the part with no precedent
 here: a trial game is a `--record`ed session plus an observation log, so
 *"we played it and X happened"* is replayable rather than remembered. The