feat: build step 4 — /mediation/, /arbitration/, /med-arb/; source ADRIC's rules

Three pages, five in the build, zero JavaScript. /arbitration/ carries §4's
paired-disclosure condition on four surfaces and Q39's struck universal appears
in no form. /med-arb/ meets the procedural-fairness objection at the level of
process design and ships deliberately without Pouya's own protocol commitments,
which are Q54.

docs/01 directed the mediation page to name the "ADRIC Model Mediation Rules".
No such document exists — 0 occurrences across all four of ADRIC's rules pages
against 10 for "National Mediation Rules"; "Model" belongs to the Model Dispute
Resolution Clause inside the rules. Caught only because R14 requires the source
before the claim. docs/reference/adric-rules.md + adric-extract/ carry it, with
the digest drift measured rather than assumed: the HTML changes per request, the
text extracts are byte-stable, so the extracts are the artefact.

Four review passes, 21 defects, and the pattern was mine: I wrote the Q54 gate
into the page and then breached it four times, then round 2 found two survivors
of round 1's own fixes and one defect round 1's fix created. Also removed a
<title> naming a practised role §4 does not grant, a habitual presupposing awards
issued, and a claim about what ADRIC's rules permit that my own reference doc
says is unsupported.

Two instrument failures caught before they became conclusions: touch targets
measured over file:// with no CSS loaded (uniform 18px, including on a .btn with
a 44px floor), and a schema.org validator call that parsed nothing and returned
0 warnings for everything. Both re-run with the instrument validated first.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0148NztQskLKKApP5SzAA78e

docs/reference/adric-extract/README.md

@@ -0,0 +1,43 @@
+# The extracted text behind `../adric-rules.md`
+
+**Why this directory exists, and why it matters more here than for ADRIO.**
+Every term count in `../adric-rules.md` — including Finding 1, which corrected a
+rule-set name `docs/01` had directed onto a public page — was run against these
+extracts, not against the raw HTML. R14: a count taken from an artefact nobody
+can reach is unverifiable by construction.
+
+**And unlike the ADRIO fetch, the HTML digests here do not reproduce.** The
+served pages change on every request. `../adric-rules.md` §Provenance records
+the two measured digests and the four causes read out of the diff. **The
+extracts below are byte-stable across those re-fetches** — verified, not
+assumed: a second fetch of the mediation-rules page produced different HTML and
+an identical `.txt`.
+
+So for these pages, **the `.txt` files are the artefact and the digests are only
+a record of what was fetched.**
+
+## Reproducing
+
+```sh
+curl -sSL -o <slug>.html "https://adric.ca/rules-codes/<path>/"
+node ../adrio-extract/extract.mjs <slug>.html > <slug>.txt
+```
+
+The four URLs and their slugs are in the provenance table of
+`../adric-rules.md`.
+
+**`extract.mjs` is not duplicated here.** It is the same unmodified script
+committed at `../adrio-extract/extract.mjs`, and a second copy is a second thing
+to keep true — `CLAUDE.md`'s single-source rule applied to a tool rather than to
+a fact. If you change it, both reference documents' counts have to be re-run.
+
+## The one command that reproduces Finding 1
+
+```sh
+for f in *.txt; do
+  printf '%-40s %s\n' "$f" "$(grep -o -F 'Model Mediation Rules' "$f" | wc -l)"
+done
+```
+
+Expect `0` on all four. `grep -o -F 'National Mediation Rules'` returns 10 on
+`rules-codes__national-mediation-rules.txt`.