fix(skill): regenerate skills/okf-consume from the golden bundle it ships a payload for

The hand-filled skill predated `okf skill`, declared no bundle identity,
and was refused by the checker it tells its reader to run, against the
payload shipped beside it:

  NOT conformant: 16 rules over 3 excerpts and 0 withheld entries, 1 findings
    bundle_mismatch: the skill declares no readable bundle identity, ...

It is now the generator's output for
examples/ingest-golden-segmented-okf-v0-2/expected-bundle, the bundle the
payload always came from:

  conformant: 16 rules over 3 excerpts and 0 withheld entries, 0 findings

The payload's bytes do not move. --force and --example-question are both
required: without the question the payload is a different one (spent
2125 -> 1420, delivered 3 -> 2, withheld 0 -> 1) and the byte test fails.
`okf skill` writes the bundle root and the skill path absolute when --out
is not under .claude/skills/, so the checkout prefix is stripped in one
mechanical step that a test holds; the generator is unchanged.

The frontmatter name becomes b-golden-segmented-okf-v0-2-consume. Claude
Code takes a project skill's command from its directory, which stays
okf-consume, and nothing in this repository named the skill by name.
references/README.md is rewritten by hand with the full regeneration
command; living prose in README, CLAUDE.md, the test comment and the
skill.py docstring is corrected, dated journals are left as written.

Report: docs/2026-09-11-k3-runde18-konsumskillen-regenerert.md

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

CLAUDE.md

@@ -721,15 +721,24 @@ and fixtures, never code.
   now fell, not that no fourth exists. Report:
   `docs/2026-09-10-k3-runde15-bundle-mismatch.md`.
   The first instantiated consumption skill is `skills/okf-consume/`; the
-  measurement behind it, including the control that FAILED, is
-  `docs/2026-09-07-okf-konsumskill-maaling.md`. **That skill is the new rule's
-  first REAL find**: hand-filled before `okf skill` existed, it declares no
-  bundle identity a reader can act on, so `okf check` now refuses it against its
+  measurement behind the form, including the control that FAILED, is
+  `docs/2026-09-07-okf-konsumskill-maaling.md`. **That skill was the new rule's
+  first REAL find**: hand-filled for K2 before `okf skill` existed, it declared
+  no bundle identity a reader can act on, so `okf check` refused it against its
   own shipped example payload (rc 1, 1 finding) — **1 of 1** shipped hand-made
-  instantiated skill. Behind it sits a second fact: its prose states K2 numbers
-  while the payload beside it is regenerated from the tracked golden bundle,
-  because K2 cannot ship. What that artefact should BE is an operator question,
-  not a patch. **The ranking is this
+  instantiated skill. **Since 2026-09-11 (K3-18) it is GENERATED** by `okf
+  skill` from `examples/ingest-golden-segmented-okf-v0-2/expected-bundle`, the
+  bundle its payload always came from, with the command in its
+  `references/README.md`: `--force` and `--example-question "Hva sier
+  veiledningen om krav?"` are both required (the payload test asserts bytes for
+  that question), and the checkout prefix is then stripped, because `okf skill`
+  writes the bundle root and the skill path ABSOLUTE when `--out` is not under
+  `.claude/skills/`. The pair is rc 0, 16 rules, 0 findings, and a test holds
+  the shipped bytes to the generator's. Its frontmatter `name` is now
+  `b-golden-segmented-okf-v0-2-consume`: Claude Code takes a project skill's
+  COMMAND from the directory name and uses `name` only as a display label, and
+  nothing here named the skill `okf-consume`. Report:
+  `docs/2026-09-11-k3-runde18-konsumskillen-regenerert.md`. **The ranking is this
   repository's own choice** — the contract binds a payload, not a retrieval
   algorithm (§ 10) — and it has FOUR optional widenings. Three are **off by
   default** and keep the default payload byte-identical; the fourth
@@ -854,10 +863,11 @@ and fixtures, never code.
   was withheld without reading the bundle (§ 2.2 forbids going to look). The
   code is 11 lines; the bytes are the reason it is off. Measured, it grows an
   N500 payload 37.9 % and takes the 629-concept K2 bundle's BOOKKEEPING to
-  122 704 B — past the 120 000-byte limit itself — which would make the
-  breaking point published in the tracked `skills/okf-consume/SKILL.md`
-  ("~75 KB at 629 concepts … at roughly 8 000 concepts") false on the day it
-  shipped.
+  122 704 B — past the 120 000-byte limit itself — which would have made the
+  breaking point then published in the hand-filled K2 copy of
+  `skills/okf-consume/SKILL.md` ("~75 KB at 629 concepts … at roughly 8 000
+  concepts") false on the day it shipped. That copy was replaced by a generated
+  one 2026-09-11; the measurement of the flag stands.
 
 ## Workflow