What is codex-second-opinion?

Setup guidance for asking OpenAI's Codex command-line tool for an independent opinion on judgment-heavy work such as interface design, writing, research, or document review.

Use it when an escalation calls for another opinion, after checking whether the command-line tool is installed and authenticated.

A second model can identify problems that the original model's self-review may miss.

codex-second-opinion — Skill for Claude Code by nikolamin

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.

Any agent

npx skills add nikolamin/claude-coordinator-kit --skill codex-second-opinion

Clone the repo

git clone --depth 1 https://github.com/nikolamin/claude-coordinator-kit

Made for: Claude Code.

Or install coordinator-kit, the plugin that ships this one along with the rest of its 15 skills, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/codex-second-opinion/github.svg)](https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/codex-second-opinion)

Your own site

<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/codex-second-opinion"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/codex-second-opinion/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/codex-second-opinion"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/codex-second-opinion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 954 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00052	$0.00954
Opus 5.5	$0.00021	$0.00382
Sonnet 5.5	$0.00010	$0.00191
Haiku 4.5	$0.00005	$0.00095

Measured 1mo ago against content hash 550aa30e7145, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-second-opinion 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 1mo 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/coordinator-kit/skills/codex-second-opinion/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex / GPT second-opinion — setup

This skill documents the optional Codex CLI reviewer. On a Claude Code coordinator it can provide a different model's opinion on UI/UX, copy, research or documents. On a Codex coordinator, another Codex process is not automatically a different model. Compare the actual primary and reviewer models; select a genuinely different configured reviewer when the audit requires one. Use the runtime adapter and project permissions.

For a Codex-hosted second opinion, a dispatched agent can use an already configured alternate model or external reviewer, including Claude Code when authorized and available. Check that reviewer's installed CLI/tool contract, permissions and actual model; do not invent flags, install it or authenticate another account implicitly. Record the model, review artifact and disagreements. Keep a required UX audit opinion pending when no suitable reviewer is available. See coordinator-kit:escalation for optional review and its fallback; the following commands apply only when Codex CLI is the selected reviewer.

Install

npm install -g @openai/codex

Requires Node. Same PATH gotcha as the Telegram bridge: launchd/systemd-spawned processes get a minimal PATH that excludes nvm/homebrew-managed bin dirs, so a bare codex (like a bare claude) resolves in your interactive shell but not in a service-spawned one. On Windows, a Task Scheduler task has the same problem — it doesn't see PATH additions made by a shell profile — so use the absolute path to the codex binary there too (typically %APPDATA%\npm\codex.cmd). See telegram-bridge/SETUP.md's PATH note if anything other than an interactive session or a dispatched agent will invoke it.

codex login is an interactive OAuth flow, normally run by whoever owns the OpenAI account it authenticates. Before first use, an agent checks auth state with:

codex login status

If not logged in, that's a graceful-degradation case (below), not something to work around.

Read the full file on GitHub · 86 lines

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.

1mo ago Changed · +4 lines · -89 tokens per session 550aa30e7145
2mo ago Changed · +2 lines 1d29d112642f
2mo ago First seen · 80 lines · 141 tokens per session scan A 400abf71b1f5

Subscribe to this mod's changes

codex-second-opinion is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 29d ago), licensed MIT. It adds 52 tokens to every session and 954 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents

codex-second-opinion next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-second-opinionnikolamin/claude-coordinator-kit	Skill	2	29d ago	MIT	A	52	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

codex-second-opinion

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Codex / GPT second-opinion — setup

Install

Login

What this file has done since we first saw it

codex-second-opinion compared with skills from other repositories