codex

A retired name for the second-opinion review command. It was replaced by /second-opinion, which can use Claude, Codex, or Gemini according to project settings.

In plain words
What is it for?
Update hooks, scripts, and documentation that call /codex so they use /second-opinion instead.
Why use it?
It prevents confusion after upgrading by showing which command replaces old /codex references.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/firatcand/forge/codex
Any agent
npx skills add firatcand/forge --skill codex
Clone the repo
git clone --depth 1 https://github.com/firatcand/forge

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.00279
Opus 5 $0.00028 $0.00139
Sonnet 5 $0.00011 $0.00056
Haiku 4.5 $0.00006 $0.00028

Measured 2d ago against content hash c19b7ccc044d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex 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.

skills/codex/SKILL.md · 20 lines

What it actually says

/codex — DEPRECATED

This skill was renamed to /second-opinion in v0.4.x (FORGE-89, P2-T21).

The new name is host-agnostic. /codex was misleading because forge can dispatch second-opinion review to Claude, Codex, or Gemini depending on settings.agents.review_host_cli (FORGE-224 added Claude as a review host via claude -p). The skill behavior, prompt construction, and verdict shape are unchanged — only the canonical name moved.

What to do

Invoke /second-opinion with the same prompt you would have given /codex. The skill body, prompt-construction guidance, evaluation discipline, and integration with /ship and /review are all preserved under the new name.

Removal

This alias is removed in v0.5.0. Update any hooks, scripts, or documentation that reference /codex to use /second-opinion before upgrading.

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 · 20 lines · 57 tokens per session scan A c19b7ccc044d

Subscribe to this mod's changes

codex is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 279 once invoked, about $0.0003 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 2026-08-30.