cross-review

cross-review is a skill for Claude Code, Codex from DmitriyYukhanov/claude-plugins. It costs 55 tokens per session (7,864 once invoked), scanned A, original, MIT.

A review process where Claude and Codex inspect the same work independently, then compare and verify their findings. Confirmed issues can be applied automatically, while unresolved disagreements are surfaced.

In plain words
What is it for?
Use it to review existing code, plans, designs, or other work with two independent reviewers. It supports repeated review rounds until the work is clean or a decision is needed.
Why use it?
It reduces reliance on one reviewer's perspective and uses code or documentation evidence to settle disagreements. This is useful when a change needs broader checking before it is accepted.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also runs codex exec. Also seen: model in frontmatter; mentions subagents; 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 codex-collaboration plugin — 2 skills shipped together

Good fit Use it to review existing code, plans, designs, or other work with two independent reviewers. It supports repeated review rounds until the work is clean or a decision is needed.

Compare 6 skills 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 DmitriyYukhanov/claude-plugins
Claude Code
/plugin install codex-collaboration

Made for: Claude Code, Codex.

Or install codex-collaboration, the plugin that ships this one along with the rest of its 2 skills.

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 cross-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/cross-review"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/cross-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,864 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 $0.00055 $0.07864
Opus 5 $0.00028 $0.03932
Sonnet 5 $0.00011 $0.01573
Haiku 4.5 $0.00006 $0.00786

Measured 10d ago against content hash a1fcbf7ec04a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cross-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 10d 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.

plugins/codex-collaboration/skills/cross-review/SKILL.md · 509 lines

How it starts

The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Review: Parallel Dual Review

Overview

Parallel review workflow between Claude and Codex CLI. Both models review the same artifact simultaneously and independently, then findings go through a three-stage resolution pipeline: initial triage → cross-validation (each model verifies the other's findings) → evidence-based research (documentation/code inspection for remaining disputes). Only genuinely inconclusive disagreements reach the user. Repeats until clean or max rounds reached. Auto-apply is the default; the user is consulted only for needs-decision items where evidence couldn't break a tie.

Core principle: Two independent perspectives are stronger than one. Neither model sees the other's review until triage. Disagreements are resolved by evidence first (cross-validation, then documentation/code research) — the user is only asked to decide when evidence is genuinely inconclusive. Confirmed findings are applied automatically; the user is consulted only for genuinely inconclusive disagreements.

Trigger Phrases

"cross-review", "dual review", "multi-model review", "get a second opinion", "validate with another model", "review with codex", "parallel review"

Invocation

cross-review [--max-rounds N] [--type code|plan|architecture|design] [target files...]
Argument Default Description
--max-rounds 3 Maximum review-fix iteration rounds
--type (auto-detected) Artifact type override
target files (branch diff) Specific files to review

Step 1: Preflight

Read ${CLAUDE_PLUGIN_ROOT}/skills/shared/prerequisites.md and execute the preflight check.

Invoke /codex:setup via the Skill tool. Two failure modes:

  1. Command not recognized (plugin not installed) -- print install instructions from prerequisites and ABORT. Do not continue to Step 2.
  2. Setup reports failure (CLI missing, auth expired) -- report the specific error from /codex:setup and ABORT.

Read the full file on GitHub · 509 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 509 lines · 55 tokens per session scan A a1fcbf7ec04a

Subscribe to this mod's changes

cross-review is a skill published in the GitHub repository DmitriyYukhanov/claude-plugins (7 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 7,864 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 2026-08-31.

Related

Other skills, from other repositories

code-standards

Prabhdeep (Sonu) Singh's personal coding standards — the house rules and quality bar for how code gets written. INVOKE before writing, generating, refactoring, or reviewing ANY code in ANY language — schemas, endpoints, queries, logging, validation, error handling — even when nobody says "standards" or "style".…

PrabhdeepSingh/claude-plugins · 81 tokens

self-review

Surface the riskiest parts of the current diff so a reviewer knows where to look hardest — one inline pass on small diffs, one cold read on a cheaper model tier with in-session synthesis on substantial ones. INVOKE PROACTIVELY whenever a change is finished and about to be handed off, reviewed, or shipped. It points…

PrabhdeepSingh/claude-plugins · 79 tokens

bug-finder

Hunt for one real, previously unreported defect and file it as a well-evidenced ticket — proactive discovery, not reactive diagnosis. INVOKE when asked to sweep code for bugs or hunt risky areas, and when /sonu:factory runs a bug-hunt pass. A known symptom is [[debugging]]; a pending diff is [[self-review]]. It files…

PrabhdeepSingh/claude-plugins · 94 tokens

team-review

Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…

NikiforovAll/claude-code-rules · 65 tokens

github-pr-review

Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…

fvadicamo/dev-agent-skills · 95 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens