# 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`.