codex-review SKILL.md skillB

codex-review from mryll/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mryll/skills/codex-review@v1.3.1

Pins v1.3.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
mryll/skills
Path
skills/codex-review/SKILL.md
Versions recorded
5
Latest version
v1.3.1, committed Oct 13, 2026
First version recorded
Jun 3, 2026
Size
48,938 bytes
Repository stars
9
License
MIT

Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic back-and-forth debate where both agents discuss findings, architecture decisions, or implementation plans until reaching consensus. Codex CLI runs READ-ONLY and never modifies files; model and reasoning effort come from the user's local Codex config. Supports plan mode: when the local agent has a plan ready, Codex evaluates and iterates on it before implementation, producing an…

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

# Codex Review — Iterative Consensus Skill

Orchestrate an iterative debate between the local agent and Codex CLI until both reach consensus on code review findings, architecture decisions, or implementation plans.

**Guiding principle: KISS (Keep It Simple, Stupid).** Both sides should favor the simplest solution that works. Complexity must be justified.

## Codex Independence

Codex is an **independent reviewer**, not a compliance checker. Do NOT instruct Codex to validate against AGENTS.md / CLAUDE.md conventions or treat them as rules to follow. Codex should form its own engineering opinions based on the code/plan it reads.

- **The local agent** follows the project's AGENTS.md / CLAUDE.md conventions (it already does naturally)
- **Codex** reviews with its own engineering judgment — it may agree with, be unaware of, or even challenge AGENTS.md / CLAUDE.md conventions
- **When they disagree**: the local agent may cite AGENTS.md / CLAUDE.md as one argument, but Codex is free to push back if it has a better reasoning. The debate resolves on merits, not authority.
- **If truly unresolved**: flag it for the user to decide
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mryll/skills/codex-review@sha256:72012f47101c0d9d

The line at the top of this page pins the label v1.3.1, 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_wgx27vtuyi24niha.svg)](https://markdownregistry.com/a/art_wgx27vtuyi24niha)

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

Versions

The registry has recorded 5 versions of this file, between Jun 3, 2026 and Oct 13, 2026, about one every 33 days.

versioncommittedcommitsizeaudit
v1.3.1 latest2026-10-13 c5d78c6 48,938 BB view · diff
v1.3.02026-08-04 32df2dd 47,248 BB view · diff
v1.2.22026-07-13 43a1b85 45,671 BB view · diff
v1.2.12026-06-04 bc82b17 45,308 BB view · diff
v1.2.02026-06-03 f47b5fb 43,747 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (48938 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 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

mryll/skills · 9 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wgx27vtuyi24niha
GET https://markdownregistry.com/api/v1/resolve?ref=mryll/skills/codex-review
GET https://markdownregistry.com/api/v1/blob/72012f47101c0d9dd6e54ae6b6aa5d6c0143d0f9f60df3fec0dd02e571d66a6d

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 mryll/skills

AGENTS.md AGENTS.md file
mryll/skills · AGENTS.md
git:20260831.dc93fe8 · audit A · 9 stars
CLAUDE.md CLAUDE.md file
mryll/skills · CLAUDE.md
git:20260601.048b127 · audit A · 9 stars
agent-context-auditor SKILL.md skill
mryll/skills · skills/agent-context-auditor/SKILL.md · Audita y produce los archivos de contexto de un repositorio para coding agents — AGENTS.md, CLAUDE.md…
v0.3.1 · audit A · 9 stars
agentmd SKILL.md skill
mryll/skills · skills/agentmd/SKILL.md · Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding…
v1.2.0 · audit A · 9 stars
c4-model SKILL.md skill
mryll/skills · skills/c4-model/SKILL.md · Create or review C4 model architecture documentation (official c4model.com notation) as diagrams-as-code in Markdown —…
v1.0.0 · audit A · 9 stars
claude-discuss SKILL.md skill
mryll/skills · skills/claude-discuss/SKILL.md · Iterative non-code discussion between the local agent and Claude Code CLI on any open-ended topic: diet, fitness…
v1.0.0 · audit B · 9 stars
claude-review SKILL.md skill
mryll/skills · skills/claude-review/SKILL.md · Iterative code review and planning discussion between the local agent and Claude Code CLI. Orchestrates an automatic…
v1.0.0 · audit B · 9 stars
codex-discuss SKILL.md skill
mryll/skills · skills/codex-discuss/SKILL.md · Iterative non-code discussion between the local agent and Codex CLI on any open-ended topic: diet, fitness, writing…
v1.2.3 · audit B · 9 stars
como-si-fuera-de-boca SKILL.md skill
mryll/skills · skills/como-si-fuera-de-boca/SKILL.md · Explain anything — code, an error, a concept, or a non-technical topic — in the simplest, most plain-language way…
v1.0.0 · audit A · 9 stars
dual-testing SKILL.md skill
mryll/skills · skills/dual-testing/SKILL.md · Language-agnostic strategy for testing code at the boundary with external infrastructure (databases, APIs, queues)…
v1.1.0 · audit A · 9 stars
explain-pr SKILL.md skill
mryll/skills · skills/explain-pr/SKILL.md · Explain a GitHub Pull Request (PR) or GitLab Merge Request (MR) to the user in plain, easy-to-understand language: WHAT…
v1.2.0 · audit B · 9 stars
low-complexity SKILL.md skill
mryll/skills · skills/low-complexity/SKILL.md · Enforce low Cognitive Complexity (SonarSource) and low Cyclomatic Complexity in ALL code written or modified, in any…
v1.0.1 · audit A · 9 stars

Every file in mryll/skills

Other files named codex-review

codex-review SKILL.md skill
ai-analyst-lab/ai-analyst · .claude/skills/codex-review/SKILL.md · Independently validate the current analysis with a second model (OpenAI Codex). Codex re-derives the same answer from…
git:20260902.b370de6 · audit A · 320 stars
codex-review SKILL.md skill
sd0xdev/sd0x-harness · skills/codex-review/SKILL.md · Full second-opinion using Codex exec (with lint:fix + build). Supports review loop with context preservation.
git:20260905.84288da · audit A · 194 stars
codex-review SKILL.md skill
appleboy/skills · plugins/codex-review/skills/codex-review/SKILL.md · Runs a single Codex (ChatGPT/OpenAI) review check-fix cycle on a PR using gh CLI. Use this skill whenever the user…
git:20260621.220ed84 · audit A · 23 stars
codex-review SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/codex-review/SKILL.md · Earlier name of the ask-llm-review skill; use when the user invokes /codex-review.
git:20261002.162238f · audit A · 19 stars
codex-review SKILL.md skill
tonydzi/second-brain-starter-kit · skills/codex-review/SKILL.md · Cross-vendor code review: this agent reviews the other agent's diff and the other agent reviews this one's, so the…
git:20261007.cd6c208 · audit A · 13 stars
codex-review SKILL.md skill
bjornmelin/dev-skills · skills/codex-review/SKILL.md · Independent gpt-6 diff review via the Codex CLI, normal or steerable adversarial with JSON findings. Use before…
git:20261015.8ae5a79 · audit A · 8 stars
codex-review SKILL.md skill
augchan42/inkstone · skills/codex-review/SKILL.md · Run an independent code review of any git scope — uncommitted changes, a commit range, a merge commit, a PR, or…
v1.4.0 · audit A · 5 stars

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