[FIX] prefs: the weld test — name and procedure in the same sentence

The jurist passed the behavioural test and exposed a defect in the doctrine while
doing it. I had written "Run a late refinement back across every earlier claim —
the weld test" and put the operative clause (at smallest-editable-unit granularity)
in the NEXT bullet, unnamed. The name sat on the half without the procedure.

A corpus audit settles the sense: across PENDING/REVIEWED, "weld" means a claim
fused to the directive or instrument that makes it load-bearing (5 uses). The
jurist used exactly that sense, generalised from claims to sections — a correct
reading of an under-specified rule, not a misreading. Merged into one bullet
carrying name, procedure, granularity, and both failure instances (0 of 11 on
2026-07-27; 11 of 15 units on 2026-07-28).

Ledger also records what the tests do NOT establish: two passes, both flattering,
and nothing yet shows the battery can return FAIL. The negative control is owed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WuMjg3ipEVa3n8CoSzoyvc

claude/app-preferences.md

@@ -95,11 +95,17 @@ form of "make epistemic status visible."
   own forbidden-token list — twice, the second time inside the fix for the first.)*
 - **When two instruments disagree about a count, the disagreement is the finding** — never the
   cheap explanation for it.
-- **Run a late refinement back across every earlier claim** — the weld test. A sharper test is
-  most dangerous to the argument that produced it. *(2026-07-27: a proposal's best section was
-  fatal to the proposal containing it; required count 0 of 11.)*
-- **Draft the replacement before trusting a census that will drive a deletion.** A section-level
-  census under-resolves the weld; drafting is the finer instrument.
+- **The weld test: run a proposal's own sharpest refinement back across its earlier claims, at
+  the granularity of the smallest editable unit.** A weld is a claim fused to the directive or
+  instrument that makes it load-bearing; a section-level census cannot see one, because the unit
+  it counts is larger than the unit the weld lives in. Two failures, one instrument: a proposal's
+  best section proved fatal to the proposal containing it, with a required count of 0 of 11
+  *(2026-07-27)*; and rerun at bullet granularity, "two deletions and a pointer" turned out to be
+  11 of 15 units carrying doctrine *(2026-07-28)*. A sharper test is most dangerous to the
+  argument that produced it.
+- **Draft the replacement before trusting a census that will drive a deletion.** Drafting is the
+  finer instrument: a census scored one section at 6 doctrine-carrying units of 8, and drafting
+  its replacement an hour later found a 7th.
 - **Completion is a tripwire.** The *feeling* of done is the cue to verify the tail, not to ship.
   Ask which failure class each green check can actually see.
 - **A conflict between two records is a verification trigger, not a precedence call.** Verify