# Second Opinion

> Cross-check the current work against an independent model (Codex/GPT) as an ADVERSARIAL reviewer — it tries to break the work, not co-sign it. Use for 'second opinion', 'cross-check this', 'what would codex say', 'have another model review this', or before shipping something high-stakes/irreversible. NOT for routine diffs.

- Skill: `dylanpulver/second-opinion` (Agent Skill)
- Install (CLI): `npx skillmds@latest add dylanpulver/second-opinion`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dylanpulver/second-opinion/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: dylanpulver (https://skillmd.com/u/dylanpulver)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/dylanpulver/second-opinion

---


# second-opinion

Get an **independent** model to attack the current work. The value is uncorrelated failure:
Codex/GPT was trained differently than Claude, so it catches blind spots Claude systematically
shares with itself. This is adversarial review, **not** consensus voting — a second model
agreeing means little (correlated priors); a second model finding a real hole is the whole point.

Claude stays the driver. Codex is an on-call consultant invoked as a subprocess.

## GATE — don't fire on routine work

Only worth the round-trip when the work is **high-stakes or hard to reverse**: a security/money
path, a migration, a tricky invariant or proof, a load-bearing refactor, a claim that's expensive
if wrong. Routine CRUD, config tweaks, obvious fixes → skip it, say so in one line, move on.

If the user invoked this explicitly, honor it regardless of stakes.

## Preflight

1. `command -v codex` — if missing, stop and tell the user:
   `npm i -g @openai/codex`, then either `codex login` (ChatGPT account) or set
   `OPENAI_API_KEY` in your environment.
2. First run only: `codex exec --help | head -30` to confirm the flag names below match the
   installed version, and adapt if they drifted.

## Run

Default target is the uncommitted working diff. Let Codex read the repo itself:

```
codex exec --sandbox read-only "You are an adversarial code reviewer. Review the uncommitted changes (run 'git diff' and 'git diff --staged') in this repo. Hunt ONLY for: correctness bugs, wrong assumptions, missing edge cases, race conditions, security holes, silent failures. Be concrete: file:line + the exact failing input/scenario. Rank most-severe first. Skip style, naming, and formatting entirely. If you find nothing real, say so — do not manufacture findings."
```

- Checking something other than the diff (a claim, a design, a specific file)? Swap the target
  clause; keep the "hunt for holes, be concrete, don't manufacture" framing.
- `--sandbox read-only` keeps Codex from editing files — it reviews, Claude decides.
- Large diff or Codex can't see it? Pipe explicitly: `git diff | codex exec --sandbox read-only "Adversarially review this diff from stdin: ..."`.

## Reconcile — this is the actual work

Codex's output is an input, not a verdict. For each finding:

- **Real + Claude missed it** → fix it, credit the catch.
- **Real but already handled** → note why it's covered, drop it.
- **Wrong / hallucinated** → say so plainly with the reason. Codex hallucinates too; don't
  launder its confidence into yours.

Then report to the user, tight: what Codex flagged, which held up, what you changed. Disagreement
between the models is the signal — surface it, don't average it away.

## Keep it small

This is a subprocess call, not a framework. No multi-model voting, no consensus tally, no wrapper
script — if it grows one, it's over-built. One model, one adversarial pass, Claude reconciles.