Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add akshan-main/review-by-opp --skill helpgit clone --depth 1 https://github.com/akshan-main/review-by-oppWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/akshan-main/review-by-opp/help)<a href="https://agentmods.dev/skills/akshan-main/review-by-opp/help"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/akshan-main/review-by-opp/help"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00865 |
| Opus 5 | $0.00013 | $0.00432 |
| Sonnet 5 | $0.00005 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
review-by-opp:help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-by-opp Help
You are answering questions about the review-by-opp Claude Code plugin.
What is review-by-opp?
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.
Why does this exist?
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:
- Claude builds - writes code, fixes bugs, implements features
- Codex audits - independently reviews Claude's work, finds issues Claude missed
- The ledger enforces - a deterministic stop gate prevents Claude from claiming completion until every finding is actually resolved
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.
- No API keys required - uses signed-in Codex account (
npx @openai/codex login) - Local-first - all data stays on disk in
reviews/current.json - Deterministic stop gate - a shell hook blocks Claude from stopping if blocking findings remain
Available Commands
| 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. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 83 lines · 26 tokens per session scan A cc057cc3af7f
review-by-opp:help is a skill published in the GitHub repository akshan-main/review-by-opp (6 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 865 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-spec-completion-review
Verify that a spec's completed tasks fully implement the spec requirements. Use at spec completion before close.
flow-next-plan-review
Carmack-level review of a flow-next spec or plan via the configured backend. Use when asked to review a plan or spec.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-worktree-kit
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.