What is codex-review?

A repository command that shows or changes how Codex reviews code: disabled, local only, or local plus a required GitHub bot review.

Use it to check the current mode or set the mode before preparing a branch or pull request. A pull request is a proposed code change for review.

It makes the review policy explicit and stores it only in the current clone, without changing shared repository files.

codex-review — Command for Claude Code by oalders/kitchen-sink

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/oalders/kitchen-sink

Made for: Claude Code.

Or install kitchen-sink, the plugin that ships this one along with the rest of its 11 skills, 23 commands, 12 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/oalders/kitchen-sink/codex-review/github.svg)](https://agentmods.dev/commands/oalders/kitchen-sink/codex-review)

Your own site

<a href="https://agentmods.dev/commands/oalders/kitchen-sink/codex-review"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/oalders/kitchen-sink/codex-review"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 737 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	$0.00041	$0.00737
Opus 5.5	$0.00016	$0.00295
Sonnet 5.5	$0.00008	$0.00147
Haiku 4.5	$0.00004	$0.00074

Measured 6d ago against content hash dbc4edc63003, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 6d 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/codex-review.md · 34 lines

What it actually says

Show or change how the codex-review-loop skill behaves in this repository. The setting is the per-clone git config key kitchen-sink.codexReview. It is written with --local, so it is never committed and never affects other repos.

Argument: $ARGUMENTS (empty means status)

Argument	Sets `kitchen-sink.codexReview` to	Effect
`on` / `github`	`github`	Local Codex loop, plus a mandatory `@codex review` gate from the GitHub bot before the PR is marked ready
`local`	`local`	Local Codex loop only. Never comments on the PR.
`off`	`off`	Skips Codex entirely, even when `codex` is installed
`default`	(key removed)	Back to the default: `off`
`status` / empty	(unchanged)	Reports the effective mode

Steps:

Map the argument to a value using the table. If the argument is anything else, show the table and stop without changing anything.

Apply it, running only the line that matches the argument:

git config --local kitchen-sink.codexReview github   # on / github
git config --local kitchen-sink.codexReview local    # local
git config --local kitchen-sink.codexReview off      # off
git config --local --unset kitchen-sink.codexReview  # default (exit code 5 = already unset; that's fine)

Report the effective mode. Run python3 <skill base dir>/codex_loop.py mode, where the base directory is the codex-review-loop skill's, and read mode, source, codex, codex_version and outer_sandbox from its JSON.

Say whether the mode came from config or from the default (unset means off). When the mode isn't off and codex runs, codex_version shows the version that actually runs. Otherwise, for github or local, the command exits 2 with an error field (codex missing or unable to run): warn the user that every codex-review-loop run in this repo will stop with an error until they install or fix codex or change the mode. For off there is no version check.

Also report the outer-sandbox state: outer_sandbox.enabled shows whether Codex's own sandbox is bypassed, and outer_sandbox.source says why: git-config (set via kitchen-sink.codexOuterSandbox), nono (on by default under nono), or default (off; no outer sandbox detected). Never change kitchen-sink.codexOuterSandbox or NONO_CAP_FILE yourself.
When the mode is github, remind the user that the repo needs the Codex GitHub integration set up to review PRs. Without it, @codex review gets no answer and the gate times out.

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.

6d ago Changed · +12 tokens per session dbc4edc63003
12d ago Changed · -1 lines e30272929799
13d ago First seen · 35 lines · 29 tokens per session scan A e88611c1d6b9

Subscribe to this mod's changes

codex-review is a command published in the GitHub repository oalders/kitchen-sink (5 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 737 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 2026-10-03.

Code review Git and workflow

codex-review

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

speckit.spex.submit

git

merge-conflict-analysis

release-tag

factory

repo-audit