Menú
Learn about review-by-opp - what it does, how to use it, and available commands
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Run Codex as an independent reviewer against the current diff or changed files. Parses findings into the ledger. Use after making code changes.
Finalize the review session. Only succeeds if all blocking findings are resolved. Emits final verdict.
Address Codex review findings from the ledger. Shows open findings and guides resolution. Each finding must get an explicit resolution state.
Resume an existing review-by-opp session. Use when returning to a previous review session.
Start a guarded implementation + review session. Use when beginning work that should be reviewed by Codex before completion. Initializes the review ledger and configures the stop gate.
Show current review ledger status including round count, open findings, blocking items, agent configuration, and whether the session can be finalized.
| name | review-by-opp:help |
| description | Learn about review-by-opp - what it does, how to use it, and available commands |
You are answering questions about the review-by-opp Claude Code plugin.
A Claude Code plugin that pairs Claude (builder) with OpenAI Codex CLI (independent auditor). It keeps a strict issue ledger so Claude cannot claim "all fixed" until every Codex review finding is actually closed.
AI coding agents (Claude, Codex, etc.) have a problem: they mark their own homework. When Claude says "all issues fixed", there's no independent verification. You're trusting the builder to also be the auditor.
review-by-opp fixes this by enforcing separation of concerns:
This creates an adversarial review loop where two different AI models hold each other accountable, with a mechanical gate that can't be talked past.
npx @openai/codex login)reviews/current.json| Command | What it does |
|---|---|
/review-by-opp:start | Initialize a new review session. Checks git, Codex, and config. |
/review-by-opp:review | Run Codex audit on your code. Parses findings into the ledger. |
/review-by-opp:fix | Address findings one by one. Each fix requires an explicit resolution. |
/review-by-opp:status | Show session status - open findings, rounds, agent config. |
/review-by-opp:resume | Resume an existing session from reviews/current.json. |
/review-by-opp:finalize | Run exit gate. Blocks if findings remain. Emits final verdict. |
/review-by-opp:help | This help page. |
/start - initialize session/review - Codex audits your code, findings appear in the ledger/fix - Claude fixes issues, marks each with a resolution state/review - re-audit to verify fixes (repeat until clean)/finalize - exit gate checks all findings are resolvedCreate .review-by-opp.json in your project root:
{
"reviewLedger": {
"maxRounds": 4,
"reviewScope": "diff",
"blockingSeverities": ["critical", "high", "medium"]
},
"codex": {
"modelStrategy": "best_available",
"model": "",
"reasoningEffort": "",
"auditMode": "standard",
"deepAuditReasoningEffort": "xhigh"
}
}
npx @openai/codex login (one-time, uses ChatGPT account)/plugins → Add from local path, or claude --plugin-dir /path/to/review-by-oppEach finding must be resolved with one of: fixed, wont_fix, false_positive, accepted_risk, deferred, duplicate.
fixed requires a resolution_note explaining the fixopen or fixed without a noteAnswer the user's question about review-by-opp based on this information. If they ask something not covered here, check the project's docs/ directory for more details.