From review-by-opp
Finalizes review-by-opp code review sessions by verifying no blocking findings remain open, no incomplete resolutions, then emits final verdict and stats summary.
How this skill is triggered — by the user, by Claude, or both
Slash command
/review-by-opp:finalizeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Finalize the review-by-opp session. This is the exit gate.
Finalize the review-by-opp session. This is the exit gate.
Load the ledger:
reviews/current.json/review-by-opp:start first."Run the exit gate check: Check ALL of these conditions:
a. No blocking findings open:
status === "open" and severity is in blockingSeveritiesb. No findings without resolution state:
status === "open" and is blocking: BLOCK.c. No false completion claims:
fixed MUST have a resolution_notefixed finding lacks a note: BLOCK. "Finding {id} is marked fixed but has no resolution note."If blocked:
/review-by-opp:fix to resolve remaining findings."If clear to finalize:
clean - no open findings at allclean_with_accepted_exceptions - only non-blocking findings remain openmax_rounds_reached - max rounds hit (but no blocking findings)final_verdict in the ledgerreviews/current.jsonReport final verdict: Show a summary:
## Final Verdict: {VERDICT}
- Rounds completed: {N}
- Total findings: {N}
- Fixed: {N}
- Won't fix: {N}
- Not reproducible: {N}
- Needs context: {N}
- Duplicate: {N}
- Superseded: {N}
- Still open (non-blocking): {N}
Session is now closed. Tell user: "Session finalized. To start a new session, run /review-by-opp:start."
CRITICAL: This is the stop gate. You MUST NOT bypass it. If blocking findings remain, finalization MUST fail. This is the entire point of review-by-opp.
$ARGUMENTS
npx claudepluginhub akshan-main/review-by-opp --plugin review-by-oppReviews risky/notable assumptions and context gaps from implementor session reports, fixes confident issues, and asks clarifying questions for ambiguous findings.
Runs a multi-agent code review assessing architecture, simplicity, maintainability, correctness, and more. Launches four parallel agents (reviewer, pre-mortem, adversarial, documentation) and triages findings.
Resolves stuck review findings via a structured put-up-or-concede exchange after arbitration. Enforces decided points, accepts concrete evidence to reopen.