codex-peer-review

codex-peer-review is a command for Claude Code, Codex from jcputney/agent-peer-review. It costs 48 tokens per session (1,454 once invoked), scanned B, original, MIT.

A command that asks the Codex command-line tool to review code or answer a broad technical question. Its default review compares two independent passes and debates the issues they find; an older single-pass mode is also available.

In plain words
What is it for?
Use it to review a commit, branch, staged or unstaged changes, or a general technical question, and to initialise the Codex review profiles.
Why use it?
It provides a structured way to check code, commits, branches, or technical answers for problems before relying on them. It supports reviews of uncommitted work as well as changes against another branch.

Command for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Codex.

Part of the codex-peer-review plugin — 1 skill, 1 command, 1 agent, 4 hooks shipped together

Good fit Use it to review a commit, branch, staged or unstaged changes, or…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jcputney/agent-peer-review/codex-peer-review
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.

Clone the repo
git clone --depth 1 https://github.com/jcputney/agent-peer-review

Made for: Claude Code, Codex.

Or install codex-peer-review, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent, 4 hooks.

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.

agentmods badge for codex-peer-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/jcputney/agent-peer-review/codex-peer-review.svg)](https://agentmods.dev/commands/jcputney/agent-peer-review/codex-peer-review)
Your own site
<a href="https://agentmods.dev/commands/jcputney/agent-peer-review/codex-peer-review"><img src="https://agentmods.dev/badge/commands/jcputney/agent-peer-review/codex-peer-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01454
Opus 5 $0.00024 $0.00727
Sonnet 5 $0.00010 $0.00291
Haiku 4.5 $0.00005 $0.00145

Measured 7d ago against content hash d7e9ab170f9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

codex-peer-review scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat > ~/.codex/peer-review.config.toml <<'EOF'
plugins/codex-peer-review/commands/codex-peer-review.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Peer Review Command

You have been explicitly asked to run peer review validation using OpenAI Codex CLI.

Parse Arguments

/codex-peer-review                          → ask for scope, run blind-debate (default)
/codex-peer-review --base <branch>          → blind-debate vs branch
/codex-peer-review --uncommitted            → blind-debate of staged/unstaged/untracked
/codex-peer-review --commit <SHA>           → blind-debate of one commit
/codex-peer-review --mode classic [...]     → legacy single-pass validation (deprecated)
/codex-peer-review --mode blind-debate [...] → explicit default
/codex-peer-review init                     → write peer-review profile files to ~/.codex/
/codex-peer-review <question>               → blind-debate of an answer to a broad question

Modes:

  • blind-debate (default): symmetric blind pass + per-issue debate. Best signal. See the codex-peer-review skill for full protocol.
  • classic (deprecated): old behavior — Claude proposes, Codex validates, max 2 rounds. Cheaper but weaker. Will be removed in a future version. When this mode is invoked, warn the user once.

init subcommand

Codex CLI uses profile-v2 files: --profile <name> layers ~/.codex/<name>.config.toml on top of the base ~/.codex/config.toml. Profiles are NOT [profiles.*] tables inside config.toml (that was the pre-0.12 scheme). The plugin writes one standalone file per profile and never edits config.toml — that file holds unrelated user settings.

If the user runs /codex-peer-review init, do not dispatch the agent. Instead:

  1. Check if the profile files already exist:

    if [ -f ~/.codex/peer-review.config.toml ] && [ -f ~/.codex/peer-review-summarizer.config.toml ]; then
      echo "Profile files already exist. Nothing to do."
      exit 0
    fi
    
  2. Write the profile files:

    mkdir -p ~/.codex
    cat > ~/.codex/peer-review.config.toml <<'EOF'
    model = "gpt-5.4"
    model_reasoning_effort = "high"
    EOF
    cat > ~/.codex/peer-review-summarizer.config.toml <<'EOF'
    model = "gpt-5.4-mini"
    model_reasoning_effort = "low"
    EOF
    

Read the full file on GitHub · 146 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.

  1. 7d ago First seen · 146 lines · 48 tokens per session scan B d7e9ab170f9c

Subscribe to this mod's changes

codex-peer-review is a command published in the GitHub repository jcputney/agent-peer-review (33 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,454 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.