Skip to content
Back to skills

Claudex Second Opinion

ASecurity

Suggests a cross-model second opinion after substantial or risky code changes. Use when a significant implementation, refactor, security-sensitive change, or uncertain bug fix has just been completed and is about to be committed or shipped. Advisory only — it recommends running /claudex:verdict; it never invokes Codex on its own.

  • 930 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 6, 2026
ai-agentssecurity

Works with

  • cli

Security analysis

A100/100

Scanned September 6, 2026

npx -y skills add ccplugins/awesome-claude-code-plugins --skill claudex-second-opinion --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claudex Second Opinion?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Claudex Second Opinion
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ccplugins-claudex-second-opinion/badge)](https://www.skillsdirectory.com/skills/ccplugins-claudex-second-opinion)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: claudex-second-opinion
description: Suggests a cross-model second opinion after substantial or risky code changes. Use when a significant implementation, refactor, security-sensitive change, or uncertain bug fix has just been completed and is about to be committed or shipped. Advisory only — it recommends running /claudex:verdict; it never invokes Codex on its own.
---

# ClauDex Second Opinion

## Overview

When a change is substantial or risky, suggest a cross-model review with
`/claudex:verdict`. Two frontier models trained by rival labs have *different*
blind spots — when both flag the same line it's the strongest free review
signal there is, and where they disagree is exactly where a human should look.

**Hard rule: never run `codex` yourself under this skill.** A cross-model
review spends the user's Codex quota and adds real latency. Explicit
invocation is consent — your job here is one well-timed suggestion, nothing more.

## When to suggest

- The change touches auth, payments, data deletion, migrations, concurrency, or crypto
- A multi-file refactor or roughly 150+ changed lines
- A bug fix where the root cause was never fully confirmed
- The user sounds unsure ("I think this works", "hopefully that's it")
- The user is weighing an architectural choice *before* code exists — then
  the right suggestion is `/claudex:debate <the decision>`, not a verdict
  (a debate needs a question, not a diff)

## When to stay quiet

- Trivial or mechanical changes: docs, formatting, renames, config bumps
- As far as you can tell from the visible conversation, a ClauDex command
  already ran on this diff (best-effort — don't re-suggest what the user
  just did)
- The Codex CLI isn't installed — at most, mention `/claudex:setup` once in
  the visible conversation, then drop it

## How to suggest

One line, at the end of your reply, naming the specific risk. Never more than
one suggestion per change, never as an interruption:

> This touched the payment webhook — worth a cross-model check: `/claudex:verdict payments flow`

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.