cross-review SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

cross-review from dmitriyyukhanov/agent-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dmitriyyukhanov/agent-plugins/cross-review@git:20260930.5a36b74

Pins git:20260930.5a36b74 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dmitriyyukhanov/agent-plugins
Path
plugins/codex-collaboration/skills/cross-review/SKILL.md
Versions recorded
5
Latest version
git:20260930.5a36b74, committed Sep 30, 2026
First version recorded
Apr 16, 2026
Size
33,793 bytes
Repository stars
8
License
MIT

Parallel dual review between Claude and Codex. Both models review independently. Findings confirmed by reviewer agreement, cross-validation, or evidence research are auto-applied each round; only genuinely inconclusive disagreements surface for user decision. Use for reviewing existing work with independent perspectives.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dmitriyyukhanov/agent-plugins/cross-review@sha256:a9e43d3f8295d7b0

The line at the top of this page pins the label git:20260930.5a36b74, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_z7igln46npcgmt7o.svg)](https://markdownregistry.com/a/art_z7igln46npcgmt7o)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Apr 16, 2026 and Sep 30, 2026, about one every 42 days.

versioncommittedcommitsizeaudit
git:20260930.5a36b74 latest2026-09-30 5a36b74 33,793 BA view · diff
git:20260923.9ff8a362026-09-23 9ff8a36 34,652 BA view · diff
git:20260508.c653fa42026-05-08 c653fa4 34,393 BA view · diff
git:20260421.d4b1fe02026-04-21 d4b1fe0 27,267 BA view · diff
git:20260416.3c4404b2026-04-16 3c4404b 26,470 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (33793 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

dmitriyyukhanov/agent-plugins · 8 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_z7igln46npcgmt7o
GET https://markdownregistry.com/api/v1/resolve?ref=dmitriyyukhanov/agent-plugins/cross-review
GET https://markdownregistry.com/api/v1/blob/a9e43d3f8295d7b0dd07cd19395f78fc9fe498a4ec13927ac6c22c6512df8e18

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dmitriyyukhanov/agent-plugins

AGENTS.md AGENTS.md file
dmitriyyukhanov/agent-plugins · AGENTS.md
git:20261012.62b1a89 · audit A · 8 stars
setup SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/agent-dispatch/skills/setup/SKILL.md · Set up agent-dispatch on this machine: check what a tick needs, ask each repo's auto-merge threshold, check the…
git:20261001.624c811 · audit A · 8 stars
slim-claude-md SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/claude-md-slim/skills/slim-claude-md/SKILL.md · Slim or restructure an oversized CLAUDE.md into path-scoped .claude/rules/ files, verifying nothing was lost. Use when…
git:20261012.62b1a89 · audit A · 8 stars
collaborative-loop SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/codex-collaboration/skills/collaborative-loop/SKILL.md · Sequential drive/validate/act collaboration between Claude and Codex. Claude analyzes, Codex validates each finding…
git:20260930.5a36b74 · audit A · 8 stars
humanizer SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/humanizer/skills/humanizer/SKILL.md · Use when removing AI-generation patterns from text in English or Russian. Auto-detects language by Cyrillic ratio and…
git:20260814.aa948c7 · audit A · 8 stars
implementation-prd SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/implementation-prd/skills/implementation-prd/SKILL.md · Create implementation-ready PRD/spec bundles for new apps, products, services, platforms, mobile or desktop software…
git:20261012.62b1a89 · audit A · 8 stars
run SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/issue-to-pr/skills/run/SKILL.md · Drive a GitHub issue — bare or tracked on a Project board — from triage to a merge-ready PR through a gated pipeline…
git:20261011.faf2ccf · audit A · 8 stars
setup SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/issue-to-pr/skills/setup/SKILL.md · Check issue-to-pr prerequisites in Claude Code or Codex: shell, GitHub access, optional config and available companion…
git:20260915.37bea13 · audit A · 8 stars
analyze SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/learning-guide/skills/analyze/SKILL.md · Reads input artifact(s) — codebase, planning session, refactor plan, or generic doc — and writes a tour-spec.json…
git:20260630.f2104e5 · audit A · 8 stars
learning-guide SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/learning-guide/skills/learning-guide/SKILL.md · Use when the user asks to "create a learning guide", "make an interactive tour", "generate onboarding doc", "build a…
git:20261012.62b1a89 · audit A · 8 stars
render SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/learning-guide/skills/render/SKILL.md · Renders an existing tour-spec.json to a single-file interactive HTML guide via the bundled Node renderer. Use when the…
git:20261012.62b1a89 · audit A · 8 stars
python-architect SKILL.md skill
dmitriyyukhanov/agent-plugins · plugins/python-dev/skills/python-architect/SKILL.md · Creates high-level Python architecture with protocols, test stubs, and module structure. Use when designing Python…
git:20260306.25081b7 · audit A · 8 stars

Every file in dmitriyyukhanov/agent-plugins

Other files named cross-review

cross-review SKILL.md skill
smart-ai-memory/attune-ai · .claude/skills/cross-review/SKILL.md · One-shot second-opinion review of a real diff by a DIFFERENT model (Claude, Codex or Antigravity) — advisory only…
git:20260906.a9e98f6 · audit A · 10 stars
cross-review SKILL.md skill
smart-ai-memory/attune-ai · plugin/skills/cross-review/SKILL.md · One-shot second-opinion review of a real diff by a DIFFERENT model (Claude, Codex or Antigravity) — advisory only…
git:20260912.eae7252 · audit A · 10 stars
cross-review SKILL.md skill
smart-ai-memory/attune-ai · .agents/skills/cross-review/SKILL.md · One-shot second-opinion review of a real diff by a DIFFERENT model (Claude, Codex or Antigravity) — advisory only…
git:20260912.eae7252 · audit A · 10 stars
cross-review SKILL.md skill
dmitriyyukhanov/claude-plugins · plugins/codex-collaboration/skills/cross-review/SKILL.md · Parallel dual review between Claude and Codex. Both models review independently. Findings confirmed by reviewer…
git:20260930.5a36b74 · audit A · 8 stars
cross-review SKILL.md skill
sentimony/skills · plugins/devflow/skills/cross-review/SKILL.md · You MUST use this when an implementation plan or a finished implementation needs an independent review by the other…
v1.4.1 · audit A · 6 stars
cross-review SKILL.md skill
zzoretich/unidex-agent-harness · codex-plugin/skills/cross-review/SKILL.md · Harden a plan with an independent review by the other provider (Claude Code and Codex review each other), then…
git:20260924.d400764 · audit A · 4 stars
cross-review SKILL.md skill
zzoretich/unidex-agent-harness · plugin/skills/cross-review/SKILL.md · Harden a plan with an independent review by the other provider (Claude Code and Codex review each other), then…
git:20260924.d400764 · audit A · 4 stars
cross-review SKILL.md skill
broomva/skills · skills/governance/cross-review/SKILL.md · bstack P20 — Cross-Model Adversarial Review Gate. The model that wrote the code cannot be the final judge of the code…
git:20261009.58d7a2f · audit A · 4 stars

Browse by kind, by grade A, or by owner.