agentmods.dev

codex-skill

A plugin listing for a tool that lets Claude Code delegate coding tasks to the OpenAI Codex command-line tool. It includes different execution modes, including one that runs with minimal confirmation.

In plain words
What is it for?
Use it when working in Claude Code and wanting to delegate coding tasks to Codex through its command and agent integration.
Why use it?
It provides a documented way to hand coding work from Claude Code to Codex and choose how much execution control to allow.

Plugin for Claude Code

1 8mo ago A scan tokens not measured original MIT
View the source file veithly/codex-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add veithly/codex-skill
agentmods
npx agentmods add plugins/veithly/codex-skill/marketplace
Clone the repo
git clone --depth 1 https://github.com/veithly/codex-skill

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

codex-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 48 lines

What it actually says

{
  "name": "codex-skill",
  "owner": {
    "name": "Ricky Wang",
    "email": "[email protected]"
  },
  "metadata": {
    "description": "OpenAI Codex CLI integration for Claude Code with YOLO mode support",
    "version": "1.0.0"
  },
  "plugins": [
    {
      "name": "rick",
      "source": ".",
      "description": "Delegate coding tasks to OpenAI Codex CLI with YOLO, Auto, and Safe execution modes",
      "version": "1.0.0",
      "author": {
        "name": "Ricky Wang"
      },
      "homepage": "https://github.com/veithly/codex-skill",
      "repository": "https://github.com/veithly/codex-skill",
      "license": "MIT",
      "keywords": [
        "codex",
        "openai",
        "automation",
        "coding",
        "yolo",
        "ai-assistant"
      ],
      "category": "development",
      "tags": [
        "codex",
        "openai",
        "ai-coding",
        "automation",
        "development-tools"
      ],
      "commands": [
        "skills/codex"
      ],
      "agents": [
        "agents/codex.md"
      ]
    }
  ]
}
Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 48 lines scan A d3f926f20a13

Subscribe to this mod's changes

codex-skill is a plugin published in the GitHub repository veithly/codex-skill (1 stars, last pushed 8mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Productivityai-codingautomationclaude-codeclaude-code-pluginclaude-skillcodex
Related

Other plugins, from other repositories

pdca-framework

TDD-disciplined AI code generation using Plan-Do-Check-Act methodology. Enforces architecture-first analysis, strict red-green-refactor, Socratic ACT retrospectives, and optional Beads task tracking integration.

kenjudy/pdca-agentic-coding-framework · not measured

magdil-rosh

מגדיל ראש — a Claude Code skill that ships the complete deliverable instead of the happy path.

waltercaregivers-app/magdil-rosh · not measured

magdil-rosh

מגדיל ראש — do more than the literal ask. Ships the complete feature, not the happy path: edge-case checklists per domain, asks the right scoping questions first, reports terse.

waltercaregivers-app/magdil-rosh · not measured

commitshow-production-audit

Plugin marketplace listing 1 plugin: production-audit.

commitshow/production-audit · not measured

draft-plugins

Plugin marketplace listing 1 plugin: draft.

drafthq/draft · not measured

canadian-finance-planner

A comprehensive personal finance planning skill for Canadians. Conducts financial interviews, builds budgets and action plans, generates interactive dashboards, and provides ongoing coaching — all tailored to Canadian tax rules, registered accounts (RRSP, TFSA, RESP, FHSA), government benefits (CCB, CESG, CPP, OAS)…

cjpatten/canadian-finance-planner-skill · not measured