agentleFS
Sign inStart free
Marco-SatisMarco-Satis/claude-setup/skills/codex-review/SKILL.md

codex-review

Skill0 starsChanged 23 days agoMITView on GitHub

Code-Review / Bug-Finding an Codex (GPT-5-Codex-Klasse, code-spezialisiert, ChatGPT-Plus-OAuth, kein API-Geld) via codex-bridge auslagern — spart Opus-Tokens UND liefert andere Modell-DNA (fängt Bug-Klassen die Claude systematisch übersieht). Use when: "codex review", "lass codex den code prüfen", "cross-check den code", "second opinion code", "codex-review".

91 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 79 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read-Tool (kein cat — Security-Flag).

    line 23

“Common” is measured: kept by at least 6 in 10 of the 79 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

codex-review — Code-Review an Codex auslagern (Token-Spar + Cross-Model)

Zweck: Code-Review/Bug-Finding auf Codex (code-spezialisiert, andere DNA als Claude) auslagern — spart Opus-Tokens und deckt Fehlerklassen auf, die Claude übersieht. Codex läuft über die ChatGPT-Plus-Sub → kein API-Geld (nur Plus-Limits).

Vorgehen

  1. Scope + Fokus: welche Dateien/welcher Diff? Worauf achten (Korrektheit, Regression, Security, konkrete Risiko-Stelle)? Je schärfer der Fokus, desto brauchbarer Codex' Output.
  2. Dispatch codex-bridge (1 Call) mit: Datei-Pfade/Diff · Review-Fokus · Rückgabe-Format (Findings mit Severity · Datei:Zeile · Problem · Fix). Datei-Reads im Subagent NUR via Read-Tool (kein cat — Security-Flag). Bridge läuft read-only + Usage-Tracking (~/.claude/state/codex_usage.jsonl).
  3. Findings kritisch einordnen (Pflicht): Codex liefert manchmal False-Positives auf gekürzten/aus-dem-Kontext-Snippets. JEDES Finding gegen die echte Datei verifizieren, bevor du fixst. Reale Bugs von Rauschen trennen — nicht blind übernehmen.

Wann NICHT

  • Trivialer/winziger Diff → selbst reviewen (Bridge-Overhead lohnt nicht).
  • Wenn Codex nicht erreichbar ist (codex login nötig) → sag es klar, KEIN Claude-Fallback als „Codex" ausgeben (das ist der ganze Sinn der anderen DNA).

Abgrenzung

  • review (Skill) = Claude-Multi-Agent-Orchestrator (Session-Scope, Self-Review-Loop, False-Negative-Pass). codex-review = ein einzelner Cross-Model-Consult an Codex.
  • gemini-digest = Bulk-Read/Kontext-Masse (günstig); codex-review = Code-Spezialisierung.
  • Max. Abdeckung: Fable + Codex + Gemini parallel, dann synthetisieren (wie Session-Review 2026-07-14) — jeweils False-Positives markieren.

Beispiel-Triggers

/codex-review web/routes/dashboard.py · „lass Codex den WS-Handler cross-checken" · „second opinion von Codex auf den Session-Diff"

Changelog

  • v1.0.0 (2026-07-14): Initial — Offload-Skill-Suite (Token-Spar via Gemini/Codex).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free