Skip to content
Agentmart
Submit a tool

Agent skills for code review in Codex

1,365 agent skills for code review in the catalog list Codex as a supported host. These are the 15 that rank highest, ordered by adoption, freshness and documentation. ai-coding-agent-guardrails, caveman-review and code-review lead the list. Codex reads them from .agents/skills/<name>/SKILL.md in the project, or ~/.agents/skills/<name>/ for every project. A skill is a folder with a SKILL.md file; Codex loads it when a task matches its description. Every listing links to its source and shows a freshness grade.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

How to install in Codex

$skill-installer <name>   (inside a Codex session)

Where it goes: .agents/skills/<name>/SKILL.md in the project, or ~/.agents/skills/<name>/ for every project.

Codex's docs also describe creating a folder with a SKILL.md by hand. They list no codex skills command. Restart Codex if a new skill does not appear. Any folder with a SKILL.md works: copy it in by hand if you prefer.

Each listing page has the exact command for that listing.

Top 15 of 1,365

  1. 1

    Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox…

    • Repository has 48.4K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 48.4KLast active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    caveman-review

    JuliusBrussee

    Compressed code review - one line per finding with location, problem and fix.

    • Largest repository here (114,786 stars)
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 114.8KLast active Oct 13, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    code-review

    langchain-aiOfficial

    Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.

    • Published by the vendor
    • Repository has 30.6K stars
    • Active in the last 30 days

    ★ 30.6KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    code-review

    open-metadata

    Use to review code changes with a two-stage process - first checking spec/requirements compliance, then code quality.

    • Repository has 15.6K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 15.6KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    bmad-code-review

    bmad-code-org

    Review code changes with several independent reviewers in parallel, then triage and present the findings.

    • Repository has 54.5K stars
    • Active in the last 30 days

    ★ 54.5KLast active Oct 18, 2026Claude Code, Claude apps, Codex, Cursor +6

  6. 6
    code-review

    Yeachan-Heo

    Run a comprehensive code review

    • Repository has 33.6K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 33.6KLast active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

  7. 7

    Review code for actionable defects.

    • Repository has 27.3K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 27.3KLast active Oct 10, 2026Claude Code, Claude apps, Codex, Cursor +6

  8. 8
    brooks-review

    hyhmrright

    PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on…

    • Repository has 1.5K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 1.5KLast active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

  9. 9

    Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline…

    • Repository has 1.4K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 1.4KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  10. 10

    Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.

    • Repository has 1.4K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 1.4KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  11. 11

    Triggered when the user submits code or requests a code review.

    • Repository has 1.3K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 1.3KLast active Oct 20, 2026Claude Code, Claude apps, Codex, Cursor +6

  12. 12
    kimi-review

    davidondrej

    Launch an independent Kimi K3.1 Pro Max code review and return it verbatim, falling back across harnesses and routes until one works.

    • Repository has 4.2K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 4.2KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  13. 13
    impl

    markuplint

    Implementation orchestrator — takes an agreed plan through implementation, carry-over approval, code review, security review, QA, docs consistency, lint/test…

    • Active in the last 30 days
    • Open source (MIT)
    • Ships helper scripts

    ★ 629Last active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  14. 14
    muse-review

    davidondrej

    Launch an independent Meta Muse Wonder Max code review through Pi and OpenRouter, and return it verbatim.

    • Repository has 4.2K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 4.2KLast active Oct 18, 2026Claude Code, Claude apps, Codex, Cursor +6

  15. 15
    critical-code-reviewer

    Garrick Aden-Buie (@gadenbuie)

    Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 547Last active Oct 7, 2026Claude Code, Claude apps, Codex, Cursor +6