/review-verify

name: review-verify
user-invocable: false
version: 4.10.0
author: "Gabriel Trabanco <1969593+gtrabanco@users.noreply.github.com>"
license: MIT
description: >
  Internal run-it verification review pass of the agentic-workflow review pack —
  composed in-turn by review-change and product-audit; not a menu entry. Runs
  the project's gate and the changed behavior for real — commands, exit codes,
  observed output — instead of assuming; what cannot be executed goes to the
  manual checklist. Findings only; never edits code.

Review Verify (internal)

> **Runner commands** below are `bunx @gtrabanco/agentic-workflow@<pin> …` — read `<pin>` > from [references/RUNNER.md](../runner-contract/references/RUNNER.md). It is stamped at > release and never guessed: a hard-coded version re-opens the per-release sweep the > contract removes, and `latest` is not a legal pin.

Composed by `review-change` / `product-audit` within their conversation — on any agent, follow this file inline as the routed step. **Findings only; never edits, never refactors.**

**Shift from discoverer to auditor of recorded evidence (S5).** The implementer's claim-evidence loop is the primary verification. This review *audits* the recorded evidence: re-runs a sample of the recorded commands instead of re-deriving the whole change. This is the cost-scaling invariant — reviewers dig into code only when evidence is absent or contradicts.

Scope

The caller's diff or path/glob — the shape is the finder contract's (`skills/review-implementation/references/FINDER_CONTRACT.md`, this section's owner). State the scope at the top of the returned table.

Checklist (evaluate EVERY item — none is optional; n/a must be stated)

✓ **Evidence audit.** Sample the unit doc's Evidence rows: re-run ≥ 3 of the recorded commands and compare observed output against what the implementer recorded. Mismatch → finding: "evidence contradicts observation at <file:line>". ✓ **Claim-evidence loop verification.** Check the fold's claim table (if present): every row has `status: ✓`. Any `✗` row means the implementer's turn did not complete its claim-evidence loop. ✓ **Unit-route triage currency.** Re-run `bunx @gtrabanco/agentic-workflow@<pin> unit-route --triage <slug>` and compare the `Steps:` line against the unit doc's Evidence section. Mismatch → stale triage. ✓ **Gate evidence is consumed, not re-run.** Run `bun scripts/gate-receipt.mjs verify`; it answers the receipt's state: `current` + `pass` (exit 0) means the declared closure has not moved — cite its `checks[]` ids and `manifest.digest` as the gate evidence; `missing` (3), `stale` (4) or `invalid` (5) is a finding routed to `bun scripts/gate-receipt.mjs run`, never a prompt to run the gate from this review and never an implicit pass; a current `fail`/`degraded` receipt fails the review with the failing check ids and their fragments ✓ The change's primary claimed behavior was exercised for real (run the CLI/endpoint/function; paste the actual observed output) — *in addition to* the evidence audit, verify at least one behavioral claim not covered by recorded evidence ✓ At least one failure-mode from the SPEC's dev scenarios was reproduced (bad input, missing file, error path) and behaved as specified ✓ New/changed tests actually fail when the implementation is reverted or broken (mutate or stash to prove they assert something — restore after) ✓ No test was skipped/disabled to get green (grep for skip/only/todo markers in the diff) ✓ The build artifact/dev server starts cleanly (no new warnings that indicate breakage) ✓ Anything that can only be confirmed by a human (visual, device, locale, load) is listed explicitly under "Manual" — never silently dropped

Materiality bar

The bar is owned by `skills/review-implementation/references/FINDER_CONTRACT.md` — apply it as written: cite the rule it violates beside the evidence; never pad the table.

Return exactly

`Sev` and `Impact` are the two published closed sets (`BLOCKER | CRITICAL | WARNING | SUGGESTION` and `blocking | docs-only | report-only`); their meanings are owned by `review-implementation` (`CLASSIFY.md` §Severity ladder) — assign a token, never a prose grade.

REVIEW VERIFY — scope: <scope>

| # | Finding | Sev | Impact | Evidence | Suggested fix |
|---|---------|-----|--------|----------|---------------|
| 1 | <what>  | BLOCKER|CRITICAL|WARNING|SUGGESTION | blocking|docs-only|report-only | <file:line> | <smallest action> |

Checklist: <n> evaluated, <n> pass, <n> findings, <n> n/a (<which + why>)
Summary: <1-2 sentences>
Manual (a human must check): <bullet list, or "none">
Decision: PASS | FAIL

FAIL if any `BLOCKER`, `CRITICAL` or `WARNING` finding is open; PASS otherwise. `SUGGESTION` findings never block — they route to the caller's triage step.

Done when

• Every checklist item was evaluated with evidence (file:line or command output)

or explicitly marked n/a with the reason.

• The fixed-format block above is returned — nothing more, nothing less — and

no code was changed.