codex-advisor

A second-opinion review tool that sends code, plans, or research to another model and has Claude check the findings. It labels findings as agreed, disputed, nuanced, false positives, or uncited.

In plain words
What is it for?
Getting independent code reviews, checking plans and research, investigating difficult tasks, verifying findings, and delegating work to Codex.
Why use it?
It helps catch mistakes, unsupported claims, and made-up or incorrect citations before you act on a review.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add LeeJuOh/claude-code-zero
agentmods
npx agentmods add plugins/leejuoh/claude-code-zero/codex-advisor
Clone the repo
git clone --depth 1 https://github.com/LeeJuOh/claude-code-zero

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

codex-advisor 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 2d 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.

plugins/codex-advisor/.claude-plugin/plugin.json · 8 lines

What it actually says

{
  "name": "codex-advisor",
  "description": "Get Codex's second opinion — and actually trust it: a different model reviews your code, plans, and research, and Claude fact-checks every finding (Agreed/Disputed/Nuanced/False Positive/Uncited) before you act, catching hallucinated citations. Skills: setup, review, adversarial, rescue, verify, research, status, result, cancel, transfer. Task delegation (rescue) wraps your verbatim request in adaptive, preview-approved prompt blocks. Transfer hands the whole session off to a resumable Codex thread (v1.0.5+). Prompt-running skills accept --model/--effort via config.toml.",
  "author": { "name": "LeeJuOh" },
  "license": "MIT",
  "keywords": ["codex", "double-check", "cross-model", "evaluation", "review", "verification", "research", "status", "cancel", "transfer"]
}
Changes

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.

  1. 2d ago First seen · 8 lines scan A 637b26484bd1

Subscribe to this mod's changes

codex-advisor is a plugin published in the GitHub repository LeeJuOh/claude-code-zero (51 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.