Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    xreview: Claude Code and Codex review each other's work

    1

    Before your agent calls substantial work done, another agent reviews it read-only from the real git diff: Codex checks Claude Code, Claude Code checks Codex. Needs the Codex or Claude Code CLI installed and logged in.

    Free

    Security scanned
    xreview: Claude Code and Codex review each other's work

    xreview: Claude Code and Codex review each other's work

    Example session with this skill installed

    Add a hit_rate() helper for the cache dashboard, then have Codex review it before you tell me it's done.

    • Read your context and instructions
    • Compiled the xreview

    Summary

    The agent runs xreview before it reports the work as done. Codex reads the change in its own read-only session, opens the helper the new code depends on, and finds a blocker that the diff alone does not show. The output below is real: it comes from the change that xreview's built-in self-test (doctor --live) plants, with only local folder paths removed.

    
    # Codex review 20261021-084040-a568
    
    - Verdict: **changes_requested**
    - Reviewed: uncommitted changes (staged, unstaged and untracked) against HEAD (branch main)
    - Model: gpt-6-astra, effort medium, sandbox read-only
    - Review copy: 2 files; git-ignored, private and credential files left out
    
    hit_rate() returns the inverse of the intended cache hit fraction.
    
    ## Findings
    
    1. [BLOCKER] Account for safe_div's reversed arguments (`metrics.py:6`)
       Impact: For ordinary nonzero cache counts, the dashboard reports an incorrect hit rate, often exceeding 100%.
       helpers.py explicitly implements safe_div(numerator, denominator) as denominator / numerator. Consequently, hit_rate(25, 100) returns 4.0 instead of 0.25.
       Fix: Call safe_div(total, hits) to compute hits / total and return 0.0 when total is zero.
    
    ## Not verified by the reviewer
    - Tests and code execution were not performed, as requested.
    
    XREVIEW 20261021-084040-a568: changes_requested (1 blocker, 0 major, 0 minor, 0 nit)
    
    FieldValue
    ReviewerCodex (author: Claude Code)
    Verdictchanges_requested (exit code 2)
    Time14 seconds
    Files the reviewer could open2, in a private review copy

    Next steps

    • The skill tells the agent to check each finding against the code, fix the real ones and re-run the tests.
    • It then runs xreview.py start --followup, so Codex first checks whether its previous findings are fixed.
    • Finally it reports the verdict, what it fixed, anything it disputes and why, and where review.md is.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    xreview gets your coding agent a second opinion from another model before it tells you that substantial work is done. Codex reviews Claude Code's work, and Claude Code reviews Codex's. From any other agent that can run shell commands, you choose either one as the reviewer.

    Requirements

    • The reviewer's command-line tool, installed and logged in on the machine where your agent runs. That is the Codex CLI (codex login) for Codex reviews and the Claude Code CLI (claude auth login) for Claude Code reviews. xreview cannot review anything without one of them, and reviews use that account's quota.
    • Python 3.8 or newer and git. The project must be a git repository.

    What it does

    • Tells your agent when to ask for a review: new features or algorithms, multi-file or tricky changes, refactors, non-obvious bug fixes, and changes to data loading, splits, training, evaluation, metrics or job scripts. Questions, docs and small edits get no review.
    • Builds the review from git itself: staged, unstaged and untracked changes, code first. Your agent's own notes go to the reviewer marked as unverified claims.
    • Keeps the reviewer read-only and away from your data. It works in a private copy of the repository that holds only what git would commit. Git-ignored data and outputs, files that look like credentials, and paths you mark private in .xreview.json never reach it. Whatever the reviewer does read is sent to its provider (OpenAI or Anthropic) under your account.
    • Returns a structured verdict: findings with severity, impact and suggested fixes, plus what the reviewer could not check. A crash, timeout or malformed answer is never treated as an approval.
    • Checks research and ML code too: data leakage, train/validation/test separation, checkpoint and hyperparameter selection, metric correctness and baseline fairness.
    • Supports follow-ups and partial reviews: a follow-up round checks the previous findings first, and --paths reviews one part of a larger change.

    Install

    Put the xreview folder where your agent loads skills, for example ~/.claude/skills/xreview/ for Claude Code or ~/.agents/skills/xreview/ for Codex. Then run python3 <skill-folder>/scripts/xreview.py doctor --live once to check the CLIs, logins and sandbox.

    Claude Code users: add this line to ~/.claude/CLAUDE.md, so that Claude reviews its own finished work:

    xreview is installed. When you finish a substantial or risky code change (new logic, multi-file edits, refactors, non-obvious bug fixes, or data, training, evaluation, metrics or job-script code), invoke the xreview skill before telling the user the work is done. Skip it for questions, docs, formatting and small obvious edits, and when the user says not to.

    Updates and source

    This listing is a snapshot of version 0.5.0 and does not update itself. For automatic updates in Claude Code and Codex, plus the built-in reminder for Claude Code, install the plugin from GitHub: https://github.com/Armin-Saadat/xreview (MIT license).

    The reviewer reads code but never runs it or your tests; your agent passes its test results in its notes. It needs the Codex CLI or the Claude Code CLI installed and logged in, and each review uses that account's quota. Git-ignored files (data, outputs) are not visible to the reviewer unless the project allows them in a committed .xreview.json. On hosts where Codex's sandbox cannot start (some HPC and container login nodes), Codex reviews need "tools": "repo" in ~/.config/xreview/config.json and read files without a shell. This listing does not update itself; the GitHub plugin does.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 21 days ago

    • Free with an Agensi account

    Requires

    OpenAI
    Anthropic
    Chatgpt
    Codex CLI
    Claude Code
    Python 3.8+
    Git
    Python

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files
    Environment Variables

    Allowed Hosts

    chatgpt.com
    api.openai.com
    api.anthropic.com

    File Scopes

    **
    ~/.local/share/xreview/**
    ~/.config/xreview/config.json

    Shell: the agent runs scripts/xreview.py, which runs git and then the reviewer CLI (codex or claude). Read files: it reads the repository's changes and copies the files git would commit into a private review copy. Write files: only under ~/.local/share/xreview (review jobs and the temporary copy, deleted after each review); it never edits the repository. Network: xreview itself opens no connections, but the reviewer CLI sends the review to its provider (OpenAI for Codex, Anthropic for Claude Code) under your account. Environment variables: optional XREVIEW_HOME and XREVIEW_CONFIG, and the agent's own variables to tell Claude Code and Codex apart. The reviewer runs read-only: Codex's shell can read only the review copy, and Claude Code gets only Read, Grep and Glob there.

    Listed21 days ago

    What's inside

    Frequently Asked Questions

    A different model reads the change in a fresh session, with none of the author's context or assumptions: Codex reviews Claude Code's work, and Claude Code reviews Codex's. xreview builds the review from the git diff itself rather than from the author's summary, and passes the author's notes as unverified claims.

    Python 3.8 or newer, git, and the reviewer's command-line tool installed and logged in on the same machine: the Codex CLI (codex login) for Codex reviews, or the Claude Code CLI (claude auth login) for Claude Code reviews. Using xreview in both Claude Code and Codex needs both. Run python3 <skill-folder>/scripts/xreview.py doctor --live once to check the setup.

    It runs from any agent that can run shell commands, but there are only two reviewers: Codex (GPT-6 Astra at medium effort by default) and Claude Code (Opus 5.5 at high effort by default). Both can be changed in ~/.config/xreview/config.json. In Claude Code the reviewer is Codex, and in Codex it is Claude Code; in other agents, such as Cursor, Copilot or Gemini CLI, the agent picks one with --reviewer.

    The diff, git status, your agent's notes, and whatever the reviewer opens in a private copy of the repository that holds only what git would commit. That goes to OpenAI or Anthropic under your account. Git-ignored files, files that look like credentials, and paths listed as private in .xreview.json never reach the reviewer. To let it check specific ignored outputs, such as a metrics file, list them under readable in .xreview.json; they count only once that file is committed.

    Yes, it is free and MIT-licensed. The package holds SKILL.md, the xreview.py script (Python standard library only), a setup and troubleshooting reference, and the license. Reviews use your Codex or Claude account's usual quota.

    No. It is read-only: Codex's shell can read only the review copy, with no writes or network access (or has no shell at all in repo-tools mode), and Claude Code gets only Read, Grep and Glob. Running tests is your agent's job; it passes the results in its notes, which the reviewer treats as claims to check.

    This listing is a snapshot of version 0.5.0. The plugin from GitHub (github.com/Armin-Saadat/xreview) updates itself in Claude Code and Codex, and adds a reminder that makes Claude Code review its own finished work. If you install only this skill in Claude Code, add the line from the description to your CLAUDE.md instead.

    New in Code Quality & Review