review

review is a command for Claude Code from vsladkov/claudex-stereo. It costs 13 tokens per session (2,340 once invoked), scanned A, original, Apache-2.0.

A command that asks Codex or Claude to review the current local Git changes or another specified scope. Git is the version-control system that records code changes.

In plain words
What is it for?
Use it to inspect local changes, a selected base, or a pull request for potential implementation issues.
Why use it?
It provides an implementation-quality review while keeping the command review-only, so it does not change the code.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the stereo plugin — 4 skills, 15 commands, 7 agents, 3 hooks shipped together

Good fit Use it to inspect local changes, a selected base, or a pull…

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add vsladkov/claudex-stereo
Claude Code
/plugin install stereo

Made for: Claude Code.

Or install stereo, the plugin that ships this one along with the rest of its 4 skills, 15 commands, 7 agents, 3 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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/vsladkov/claudex-stereo/review.svg)](https://agentmods.dev/commands/vsladkov/claudex-stereo/review)
Your own site
<a href="https://agentmods.dev/commands/vsladkov/claudex-stereo/review"><img src="https://agentmods.dev/badge/commands/vsladkov/claudex-stereo/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,340 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 $0.00013 $0.02340
Opus 5 $0.00006 $0.01170
Sonnet 5 $0.00003 $0.00468
Haiku 4.5 $0.00001 $0.00234

Measured today against content hash 9ab3f8ab1af2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 today.

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.

plugins/stereo/commands/review.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read ${CLAUDE_PLUGIN_ROOT}/skills/model-routing/SKILL.md first and apply its routing and job rules. The rules below are specific to this command.

Run one standard implementation-quality review.

Raw slash-command arguments: $ARGUMENTS

Core constraint:

  • This command is review-only.
  • Do not fix issues, apply patches, or suggest that you are about to make changes.
  • Your only job is to run the review and return Codex's output verbatim to the user.

Parse and route

Parse --model, --wait, --background, --base, --pr, --scope, and any trailing text from the raw arguments. Default to the companion's normal model when --model is absent. No workspace role default applies to this command.

  • A model that does not start with claude: takes the Codex path below, including one with an optional codex: prefix that the companion strips. Preserve the user's raw arguments byte-for-byte when invoking the companion.
  • claude:session, claude:inherit, claude:sonnet, claude:opus, claude:opus-4.8, claude:haiku, and claude:fable take the Claude path. Reject any other claude:* value using the routing skill's availability rule.
  • Reject any trailing focus text on the Codex path before repository work because the built-in reviewer does not accept custom focus text. Name /stereo:adversarial-review <focus> as the Codex-side steerable route. The Claude path accepts trailing focus text as untrusted steering.
  • Reject --effort on a Codex selection because the built-in reviewer exposes no reasoning-effort control. Direct the user to /stereo:adversarial-review --effort <effort> instead.
  • Reject --effort on a claude:* selection because a single-role command's --effort is that role's effort flag, and every Stereo command rejects a role effort flag when its role is Claude-routed. Only a command-wide --effort on a multi-role command is accepted and reported as inert. Tell the user to remove it or choose a Codex model; do not direct this combination to adversarial review.
  • Reject --background with a Claude model before inspecting the repository: "--background creates durable Codex jobs visible in /stereo:status. A Claude agent review is bound to this session and would not survive it. Remove --background to run the Claude review in the foreground, or choose a Codex model for a durable background review."
  • --wait is accepted but redundant on the Claude path, which is always foreground.

Read the full file on GitHub · 172 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. today Changed · +1 lines 9ab3f8ab1af2
  2. 6d ago First seen · 171 lines · 13 tokens per session scan A 23fb098fd149

Subscribe to this mod's changes

review is a command published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 2,340 once invoked, about $0.0001 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 2026-08-31.