Skip to content
TrustedSkillsbeta
Back to all skills

Codex Review

Checked
alinaqi·vlatest·backend·MIT

Analyzes backend code for potential bugs, security vulnerabilities, and adherence to coding standards.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add alinaqi/maggy --skill codex-review -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

alinaqi

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned alinaqi/claude-bootstrap at 72a456e6cc.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
72a456e6cc
Manifest
skills/codex-review/SKILL.md
Scanned
1 file, 471 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Codex Review skill leverages OpenAI's GPT-5.2-Codex model to perform specialized code reviews for backend projects. It analyzes code for potential bugs, security vulnerabilities (like SQL injection), and adherence to coding standards. The tool provides structured output in JSON format and integrates with GitHub by adding review comments directly within pull requests. It can also be used in headless mode for CI/CD automation.

When to use it

  • Before opening a Pull Request: Review changes against the base branch (e.g., main) to identify issues before merging.
  • Before committing code: Analyze staged, unstaged, and untracked changes to catch problems early.
  • Analyzing specific commits: Examine particular commit SHAs from your project's history.
  • Automated CI/CD pipelines: Integrate Codex Review into automated workflows for continuous code quality checks.

Key capabilities

  • Uses OpenAI’s GPT-5.2-Codex, specifically trained for code review.
  • Detects bugs, security flaws, and style issues (reported 88% detection rate on LiveCodeBench).
  • Provides structured output in JSON schema format.
  • Integrates natively with GitHub to add comments directly to pull requests.
  • Supports headless mode for CI/CD automation.
  • Offers review presets for common use cases (base branch, uncommitted changes, specific commits).
  • Allows custom instructions to focus the review on particular areas (e.g., security vulnerabilities).

Example prompts

  • /review - Initiates an interactive code review session.
  • "Review against base branch" - Compares current changes with the main branch.
  • "Focus on security vulnerabilities" - Instructs Codex to prioritize identifying potential security issues.

Tips & gotchas

  • Prerequisites: Requires Node.js version 22 or higher and either a ChatGPT Plus/Pro/Team/Edu/Enterprise subscription or an OpenAI API key.
  • Authentication: Ensure you are properly authenticated with either your ChatGPT account or by setting the OPENAI_API_KEY environment variable.
  • Interactive Mode: The initial interaction is through a text-based user interface (TUI).