review-codex

review-codex is a command for Claude Code from eddiebelaval/squire. It costs 0 tokens per session (1,758 once invoked), scanned A, original, MIT.

A code-review command for checking work produced by Codex. It examines the changes, verifies quality, fixes small issues, and escalates only decisions that could break or substantially change the design.

In plain words
What is it for?
Use it to review a session or branch, run a quick review without a build, or automatically commit the changes when the review passes.
Why use it?
It provides a second review of agent-written code and helps resolve routine problems before the work is accepted.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Codex.

Good fit Use it to review a session or branch, run a quick review without a build, or automatically commit the changes when the review passes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/eddiebelaval/squire/review-codex
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/eddiebelaval/squire

Made for: Claude Code.

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 review-codex

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/eddiebelaval/squire/review-codex"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/review-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,758 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 $0.00000 $0.01758
Opus 5 $0.00000 $0.00879
Sonnet 5 $0.00000 $0.00352
Haiku 4.5 $0.00000 $0.00176

Measured 5d ago against content hash d76c85ba18e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-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 5d 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.

commands/review-codex.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review-codex - Review & Resolve Codex Work

You are the Director reviewing work from Codex (Builder). Your job is to verify quality, fix minor issues, resolve Codex's questions autonomously, and only escalate to Eddie when something would break or fundamentally change architecture.

Philosophy: Remove Eddie from the loop. You and Codex should resolve everything you can between yourselves. Only escalate decisions that require human judgment about product direction, UX, or breaking changes.

Arguments

Parse $ARGUMENTS for:

  • Session ID (e.g., sess_abc123) - Codex session to pull context from
  • Branch name (e.g., feature/my-branch) - override base branch detection
  • --commit flag - auto-commit if review passes
  • --quick flag - skip build verification (for WIP checks)
  • Empty = auto-detect everything

Step 1: Gather Context (PARALLEL)

Run these simultaneously:

1a. Git Diff Against Base

# Detect base branch
BASE=$(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)
git diff $BASE..HEAD --stat
git diff $BASE..HEAD

If a branch name was provided in $ARGUMENTS, use that instead of main/master.

1b. Codex Session Context

If a session ID was provided:

mcp__codex-cli__codex({ prompt: "Summarize what you did, any questions you have, and anything you're unsure about.", sessionId: "<session-id>" })

If no session ID provided:

mcp__codex-cli__listSessions()

Pick the most recent session and pull context from it. If no sessions exist, skip this step (Codex may have worked via direct file writes).

1c. Scan for Codex Markers

Search the diff for these patterns that indicate Codex left questions or uncertainty:

  • TODO, FIXME, HACK, XXX
  • QUESTION: or Q: comments
  • // not sure, // unclear, // ask
  • Empty function bodies or placeholder implementations
  • throw new Error('Not implemented')

Step 2: Code Review

Review ALL changed files against these criteria:

Read the full file on GitHub · 229 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. 5d ago First seen · 229 lines · 0 tokens per session scan A d76c85ba18e7

Subscribe to this mod's changes

review-codex is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,758 tokens. 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 2026-09-03.