Review Verify (internal)
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 bun scripts/unit-route.mjs --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.