Pouya LajevardiandClaude Opus 5
2ea4c0f8ac
Four rulings from Pouya, 2026-08-30, and their sweep. D20 — the review protocol. Per build step the review is `adversarial-reviewer` alone. `claims-auditor` no longer runs per step; it runs ONCE, at cutover, over the whole finished site, as a blocking item near the top of docs/06's checklist. `check:claims` is unchanged and still runs on every build and both deploy paths. The reasoning is recorded in full in AGENTS.md D20, as a calibration and not an erosion: nothing has shipped, so every claims finding so far has been about a page no visitor can reach, and one pass over twenty finished pages catches more than nine passes over drafts because it sees the site as a reader does. The /med-arb/ ADRIC gloss is the proof — no individual claim was false, the defect was adjacency, and adjacency does not exist until the pages sit next to each other. The code reviewer stays per step because what it catches compounds. What this costs is recorded honestly beside it, not summarised away. D17 and D19 amended to match. D19's two-round cap governs the per-step code review only; the single cutover claims pass runs until its findings are resolved, because there is no second pass behind it. Q56 — mediation is NOT scoped commercial. Thirteen shipped strings corrected across five files: page titles, meta descriptions, hero ledes, section ledes, the `Service` node's name and description, and `ProfessionalService`'s. §4's mediation row stays unscoped, and the reason now sits beside both rows so the asymmetry reads as designed: arbitration is scoped commercial because of a LEGAL GATE (Q39 — family arbitration in Ontario requires prescribed training); mediation has no such gate. `adversarial-reviewer` then found three surfaces the sweep had missed, the worst on /practice/ — "These describe the process the parties are choosing between, in commercial matters" scoped mediation with the two words never appearing in the same element, so no proximity grep reached it. Q55 — CLOSED WITHOUT BEING RESOLVED, and the difference is the ruling. The Q.Arb stamp is split: `[verified]` on the status, `[Pouya's stated basis]` on the date. The 2026-08-26 record is marked UNRECONCILED, permanently and on purpose. The date is not published and nothing depends on it. check:claims — FROZEN. Round 2 found five defects in round 1's own fixes to that script, two of which made it worse than before the pattern existed. A pattern is added only after a real breach reaches dist/, never speculatively, and each addition ships with a probe plus a negative fixture. No refactors, no coverage improvements. It is a tripwire, not a program. Two conventions into CLAUDE.md: sweep the VOCABULARY, not only the subject (`git grep 'Q.Arb'` is line-anchored and could not find ten lines entirely about Q.Arb that never name it); and agent definitions load at session start, so an edit to .claude/agents/*.md does not reach the session that made it. Verified: check 0 errors, lint 0, build 0 (12 pages), check:claims 0. Lighthouse not run — tool unavailable until build step 7. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Md3GndFqWPzK78xAoebsg5
28 lines
1.2 KiB
Markdown
28 lines
1.2 KiB
Markdown
---
|
|
description: Run the adversarial review pass on demand — on the working tree, a commit range, or named files.
|
|
argument-hint: [what to review — defaults to uncommitted changes]
|
|
---
|
|
|
|
**ultrathink**
|
|
|
|
Scope: $ARGUMENTS
|
|
|
|
If no scope is given, review the uncommitted working tree (`git status`,
|
|
`git diff`).
|
|
|
|
Invoke **`adversarial-reviewer`** on that scope.
|
|
|
|
**`claims-auditor` is not part of this command — D20, Pouya, 2026-08-30.** The
|
|
claims pass runs **once, at cutover**, over the whole finished site; `AGENTS.md`
|
|
D20 records the reasoning and the measured cost of deferring it. Run it here only
|
|
if Pouya asks for it by name in `$ARGUMENTS` — in which case say in the report
|
|
that it was run out of band, and against a draft rather than the finished site,
|
|
because that is the condition D20 says weakens it.
|
|
|
|
Give it the diff and the relevant specs from `docs/`. **Do not brief it on why
|
|
the code is correct** — that anchors the review and turns it into agreement.
|
|
|
|
Report findings grouped by severity, most severe first. For each: the defect, the
|
|
concrete failure it produces, and the fix. Do not fix anything yet — Pouya
|
|
decides what gets addressed. Then ask what he wants done.
|