codex-review

codex-review is a skill for Claude Code, Codex from AlexAtmtit/custom-skills. It costs 57 tokens per session (686 once invoked), scanned A, original, MIT.

A skill that opens Codex CLI in a tmux session and runs its review command on uncommitted code changes. Tmux is a terminal tool that keeps a command-line session running separately from your current window.

In plain words
What is it for?
Use it to inspect uncommitted code with Codex's review workflow and capture the review results.
Why use it?
It provides a second review of changes that have not yet been committed, which can reveal issues you missed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to inspect uncommitted code with Codex's review workflow and capture the review results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexatmtit/custom-skills/codex-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.

Any agent
npx skills add AlexAtmtit/custom-skills --skill codex-review
Clone the repo
git clone --depth 1 https://github.com/AlexAtmtit/custom-skills

Made for: Claude Code, Codex.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexatmtit/custom-skills/codex-review/github.svg)](https://agentmods.dev/skills/alexatmtit/custom-skills/codex-review)
Your own site
<a href="https://agentmods.dev/skills/alexatmtit/custom-skills/codex-review"><img src="https://agentmods.dev/badge/skills/alexatmtit/custom-skills/codex-review/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.

agentmods 80×15 button for codex-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexatmtit/custom-skills/codex-review"><img src="https://agentmods.dev/badge/skills/alexatmtit/custom-skills/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 686 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00686
Opus 5 $0.00028 $0.00343
Sonnet 5 $0.00011 $0.00137
Haiku 4.5 $0.00006 $0.00069

Measured 9d ago against content hash d21f886bda5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

codex-review 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 9d 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.

codex-review/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Review via Tmux

Overview

Launch OpenAI's Codex CLI in a tmux session and run the /review command to get a code review of uncommitted changes. The skill handles the full lifecycle: setup, command execution, waiting for completion (up to 60 minutes), capturing output, and cleanup.

Prerequisites

Before running, verify:

  • tmux is installed and available
  • codex CLI is installed and available

The Process

Step 1: Setup Tmux Session

SOCKET="${TMPDIR:-/tmp}/codex-review-$$.sock"
SESSION="codex-review-$$"
tmux -S "$SOCKET" new-session -d -s "$SESSION"

Step 2: Launch Codex and Send Commands

# Launch codex
tmux -S "$SOCKET" send-keys -t "$SESSION" "codex" Enter

# Wait for codex to initialize
sleep 5

# Type /review command
tmux -S "$SOCKET" send-keys -t "$SESSION" -l "/review"

# Press Enter to execute the /review command
tmux -S "$SOCKET" send-keys -t "$SESSION" Enter

# Wait for menu to appear
sleep 2

# Select option 2: Review uncommitted changes (no Enter needed)
tmux -S "$SOCKET" send-keys -t "$SESSION" -l "2"

Step 3: Wait for Completion

Poll every 60 seconds for up to 60 minutes:

wait_for_completion() {
  local timeout=3600 interval=60 elapsed=0
  while [ $elapsed -lt $timeout ]; do
    output=$(tmux -S "$SOCKET" capture-pane -p -t "$SESSION" -S -100)

    # Check for completion (shell prompt returned)
    if echo "$output" | grep -qE '(❯|\$|>>>)\s*$'; then
      return 0
    fi

    sleep $interval
    elapsed=$((elapsed + interval))
  done
  return 1
}

wait_for_completion

Step 4: Capture Output

# Capture full pane output (last 500 lines)
tmux -S "$SOCKET" capture-pane -p -t "$SESSION" -S -500

Step 5: Cleanup

tmux -S "$SOCKET" kill-session -t "$SESSION"
rm -f "$SOCKET"

To Monitor Manually

If you want to watch the session while it runs:

tmux -S "$SOCKET" attach -t "$SESSION"

Detach with Ctrl+b d.

Success Criteria

  • Codex review output is captured and displayed
  • Tmux session is cleaned up
  • No orphaned processes or sockets

Read the full file on GitHub · 103 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. 9d ago First seen · 103 lines · 57 tokens per session scan A d21f886bda5d

Subscribe to this mod's changes

codex-review is a skill published in the GitHub repository AlexAtmtit/custom-skills (22 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 686 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.