New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Codex Reviewer

by instructa in instructa/agent-skills

Have Codex review a feature or change from Claude Code, then let Claude address the findings and request verification.

No licenceAuto-check passedProduct & Project Management

Install Codex Reviewer

skills CLI
$ npx skills add instructa/agent-skills --skill codex-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install instructa/agent-skills codex-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/instructa/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude/codex-reviewer .claude/skills/codex-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codex-reviewer
GitHub stars
139
Token cost
~1.6k tokens
SKILL.md length
854 words
Files
5 (incl. scripts, references)
Skills in repo
17
Repo updated
First seen
Licence
None found

At a glance

Have Codex review a feature or change from Claude Code, then let Claude address the findings and request verification.

  • Works in 4 steps: Read the findings critically. Confirm… → Claude applies justified corrections and… → Send the changed state, finding IDs,… → …
  • An independent review of implementation
  • SKILL.md covers Establish the scope, Prepare the review, Call the real reviewer and Corrections and verification
  • Runs Python scripts from its folder; calls codex and python3

What it does

Codex Reviewer is an agent skill from instructa/agent-skills. Have Codex review a feature or change from Claude Code, then let Claude address the findings and request verification. Use for an independent review of implementation, acceptance criteria, architecture, or UI evidence while Claude remains the implementer.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `README.md`, `references/review-brief.md` and `scripts/review.py`).

It sits in Product & Project Management, covering User stories. The repository describes itself as: A curated collection of agent-skills.

When your agent uses it

  • An independent review of implementation
  • Acceptance criteria
  • UI evidence while Claude remains the implementer

Example prompts

  • “/codex-reviewer”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read the findings critically. Confirm their relevance and reproduction before changing code. Treat reviewer output as evidence, not…
  2. Claude applies justified corrections and runs the appropriate checks. Record which findings were fixed, disputed with evidence, or remain…
  3. Send the changed state, finding IDs, fixes and evidence to a fresh reviewer session. This matches the tested workflow; never resume an…
  4. Allow at most two correction rounds by default. Thus a complete sequence can be initial review, corrections, second review, corrections…

What it can do on your machine

Read from SKILL.md and the folder at commit d49c149. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • codex
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex Reviewer loads about 1.6k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 854 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 854 words (~1,585 tokens).

“Claude owns implementation, tests, browser checks and corrections. Codex reviews the requested change using a custom prompt in a read-only sandbox. Use this from Claude Code as /codex-reviewer, with either a new feature request or an existing change to review.”

— opening of SKILL.md by instructa
name
codex-reviewer

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (scripts, references) in skills/claude/codex-reviewer of instructa/agent-skills.

  • SKILL.md
  • README.md
  • references/review-brief.md
  • scripts/review.py
  • scripts/test_review.py

Open the folder on GitHubat commit d49c149

Compare with similar skills

Codex Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codex Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Reviewer this skillinstructa/agent-skills139—~1.6kAutomated safety check: PassNone
User Story Writerdeanpeters/Product-Manager-Skills7.2k2 repos~2.9kAutomated safety check: PassCustom licence
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Agile Product Owneralirezarezvani/claude-skills28k3 repos~3.2kAutomated safety check: PassMIT
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT
Ralph Tui Create JSONsubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • User Story Writer

    deanpeters/Product-Manager-Skills

    Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.

    7.2k GitHub starsUsed in 2 repos~2.9k tokens
    Product & Project ManagementAuto-check passed

  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

  • Agile Product Owner

    alirezarezvani/claude-skills

    Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.

    28k GitHub starsUsed in 3 repos~3.2k tokens
    Product & Project ManagementAuto-check passed

  • Ralph Tui Create Beads Rust

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed

  • Ralph Tui Create JSON

    subsy/ralph-tui

    Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

  • Check

    VibiumDev/vibium

    Independently check application acceptance criteria in a live browser or saved recording with the Vibium CLI.

    2.9k GitHub stars~2k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

More from instructa/agent-skills

All 17 skills in this repo

  • App Spec Packager

    instructa/agent-skills

    A skill your agent uses when the user wants to turn an application, product, startup idea, SaaS, mobile app, web app, API, AI product, or internal tool into a production-ready Markdown specification…

    139 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed

  • Search Context

    instructa/agent-skills

    Find, clone, inspect, and summarize high-quality GitHub reference repositories for coding agents.

    139 GitHub stars~2.1k tokensUpdated 9 days ago
    Auto-check passed

  • Secleak Check

    instructa/agent-skills

    Run or install repo security leak checks with BetterLeaks and Trivy.

    139 GitHub stars~557 tokensUpdated 9 days ago
    Auto-check passed

  • Delegate Fable

    instructa/agent-skills

    Delegate a bounded task from a Codex session to a Fable-powered Cursor Agent in the same Herdr workspace, then wait for and collect the result.

    139 GitHub stars~925 tokensUpdated 9 days ago
    Auto-check passed

  • Delegate Grok

    instructa/agent-skills

    Delegate a bounded task from a Codex session to Grok 4.6 with xhigh reasoning in the same Herdr workspace, then wait for and collect the result.

    139 GitHub stars~951 tokensUpdated 9 days ago
    Auto-check passed

  • Delegate Sol

    instructa/agent-skills

    Delegate a bounded task from a Codex session to GPT-5.6 Sol in the same Herdr workspace, then wait for and collect the result.

    139 GitHub stars~1.2k tokensUpdated 9 days ago
    Auto-check passed

Categories

Questions about Codex Reviewer

What does Codex Reviewer do?

Have Codex review a feature or change from Claude Code, then let Claude address the findings and request verification. Codex Reviewer is an agent skill from instructa/agent-skills. Have Codex review a feature or change from Claude Code, then let Claude address the findings and request verification.

When should I use Codex Reviewer?

Codex Reviewer fits situations like: an independent review of implementation; acceptance criteria; UI evidence while Claude remains the implementer.

How do I install Codex Reviewer in Claude Code?

Run `npx skills add instructa/agent-skills --skill codex-reviewer -a claude-code`. Or copy the skill folder (skills/claude/codex-reviewer in instructa/agent-skills) into .claude/skills/codex-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Codex Reviewer in Codex?

Run `npx skills add instructa/agent-skills --skill codex-reviewer -a codex`. Or copy the skill folder (skills/claude/codex-reviewer in instructa/agent-skills) into .agents/skills/codex-reviewer in your project. Codex loads it when a task matches its description.

Can I use Codex Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add instructa/agent-skills --skill codex-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-reviewer, .gemini/skills/codex-reviewer, .github/skills/codex-reviewer and .opencode/skills/codex-reviewer in your project.

What does Codex Reviewer need to run?

Going by SKILL.md and its folder, Codex Reviewer needs Python for the scripts in its folder and the command-line tools its instructions call (codex and python3). Our summary lists: Python 3.

Does Codex Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codex Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codex Reviewer use?

No licence was found for Codex Reviewer or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Codex Reviewer use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 854 tokens, read only when the agent opens those files.

What are the alternatives to Codex Reviewer?

Skills that share tags, products or a category with Codex Reviewer: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Agile Product Owner (alirezarezvani/claude-skills, 28k stars) and Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Reviewer?

instructa (a GitHub organization) maintains it in instructa/agent-skills, which has 139 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 28, 2026.

Source: instructa/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.