codex-review SKILL.md skillA

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

Install it, pinned
mdr add bjornmelin/dev-skills/codex-review@git:20261015.8ae5a79

Pins git:20261015.8ae5a79 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bjornmelin/dev-skills
Path
skills/codex-review/SKILL.md
Versions recorded
4
Latest version
git:20261015.8ae5a79, committed Oct 15, 2026
First version recorded
Jul 22, 2026
Size
4,003 bytes
Repository stars
8
License
none declared

Independent gpt-6 diff review via the Codex CLI, normal or steerable adversarial with JSON findings. Use before shipping nontrivial changes.

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

Independent gpt-6 review of local changes through the Codex CLI. Read-only - never
lets Codex modify the repo. Works identically from the main loop, subagents, and
workflow stages (no plugin runtime required).

Reviews run on `gpt-6-sol` at `"max"` (the Codex
default for almost everything, review included). Escalate to `gpt-6-astra` at
`"max"` when the review is the load-bearing check - a one-way door, a
security or money path, or an adversarial pass whose verdict you will act on
directly. Drop to `gpt-6-luna` at `"high"` only for a fast look at a small
diff where latency matters more than depth.

Pin BOTH the model and the effort on every command below rather than inheriting
CLI defaults. For `codex review`, `-m` is a GLOBAL flag and must come before the
subcommand. Paths written as `<skill-dir>` mean this skill's base directory
(provided when the skill is invoked).

## Mode selection

- **Normal review** (default): overall code-quality pass on a diff, same quality as
  running `/review` inside Codex.
- **Adversarial review**: when the user (or you) wants a specific decision, risk area,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bjornmelin/dev-skills/codex-review@sha256:e3a1584009e2d9c6

The line at the top of this page pins the label git:20261015.8ae5a79, 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_4wga3pjyqswo4ivd.svg)](https://markdownregistry.com/a/art_4wga3pjyqswo4ivd)

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

Versions

The registry has recorded 4 versions of this file, between Jul 22, 2026 and Oct 15, 2026, about one every 28 days.

versioncommittedcommitsizeaudit
git:20261015.8ae5a79 latest2026-10-15 8ae5a79 4,003 BA view · diff
git:20260805.9eb26012026-08-05 9eb2601 4,073 BA view · diff
git:20260724.5ddc0f72026-07-24 5ddc0f7 3,811 BA view · diff
git:20260722.7fdce952026-07-22 7fdce95 3,802 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 (4003 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

bjornmelin/dev-skills · 8 stars · license none declared · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4wga3pjyqswo4ivd
GET https://markdownregistry.com/api/v1/resolve?ref=bjornmelin/dev-skills/codex-review
GET https://markdownregistry.com/api/v1/blob/e3a1584009e2d9c66a5321601666740ed113dff7f5688517c7d2e8fae17c2671

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 bjornmelin/dev-skills

AGENTS.md AGENTS.md file
bjornmelin/dev-skills · AGENTS.md
git:20260805.c6b49e2 · audit A · 8 stars
browser-workbench-setup SKILL.md skill
bjornmelin/dev-skills · archive/skills/browser-workbench-setup/SKILL.md · Set up browser automation and UI QA for a new repository using playwright-interactive as the primary interactive tool…
git:20260730.da338fd · audit A · 8 stars
browser-workbench SKILL.md skill
bjornmelin/dev-skills · archive/skills/browser-workbench/SKILL.md · Browser/UI router--playwright-interactive, agent-browser, browser-workbench-setup. Triggers--UI debug, QA, screens…
git:20260730.da338fd · audit A · 8 stars
bun-audit SKILL.md skill
bjornmelin/dev-skills · archive/skills/bun-audit/SKILL.md · Shared Bun audit/remediation router. Use when auditing a repo for Bun-first correctness, explaining findings, listing…
git:20260720.59a58de · audit A · 8 stars
cleanup-py SKILL.md skill
bjornmelin/dev-skills · archive/skills/cleanup-py/SKILL.md · Python branch review—hard-cut, delete-first cleanup, Google docstrings.
git:20260728.3aaa44b · audit A · 8 stars
codex-session-cleanup SKILL.md skill
bjornmelin/dev-skills · archive/skills/codex-session-cleanup/SKILL.md · Safely scan, triage, quarantine, restore, and purge Codex session/history/state/memory artifacts for current repo…
git:20260728.3aaa44b · audit A · 8 stars
design-motion-system SKILL.md skill
bjornmelin/dev-skills · archive/skills/design-motion-system/SKILL.md · Cross-stack motion & design-system director. Use to turn vague "make it premium / cinematic / standout / hyperrealistic…
git:20260726.b67ae30 · audit A · 8 stars
dmc-py SKILL.md skill
bjornmelin/dev-skills · archive/skills/dmc-py/SKILL.md · Dash + DMC v2—MantineProvider, styles, Styles API, callbacks (pattern, clientside, bg), Pages, charts, modals, full…
git:20260729.efe35f4 · audit A · 8 stars
gh-deps-intel SKILL.md skill
bjornmelin/dev-skills · archive/skills/gh-deps-intel/SKILL.md · JS/TS + Python dep upgrade intel (monorepos). Outdated package-manager checks + GitHub release/changelog →…
git:20260803.4dcf273 · audit A · 8 stars
goal-to-release SKILL.md skill
bjornmelin/dev-skills · archive/skills/goal-to-release/SKILL.md · Orchestrate issue-backed goals from ambiguous request to shipped release with ledgers, adaptive PR graphs, preflight…
git:20260728.3aaa44b · audit A · 8 stars
kimi-ui-advisor SKILL.md skill
bjornmelin/dev-skills · archive/skills/kimi-ui-advisor/SKILL.md · Explicit-only Kimi Code CLI frontend/UI advisor for UI audits, redesigns, components, screenshots, before/after…
git:20260617.d1d0760 · audit A · 8 stars
managing-tech-debt SKILL.md skill
bjornmelin/dev-skills · archive/skills/managing-tech-debt/SKILL.md · Help users manage technical debt strategically. Use when someone is dealing with legacy code, planning refactoring…
git:20260728.3aaa44b · audit A · 8 stars

Every file in bjornmelin/dev-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
mryll/skills · skills/codex-review/SKILL.md · Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic…
v1.3.1 · audit B · 9 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 A, or by owner.