claude-to-codex-migrator

claude-to-codex-migrator is a plugin for Claude Code from ahmedawan-oracle/claude-code-plugins. Its manifest loads nothing; the 1 skill, 2 plugins it bundles cost 85 tokens per session together, scanned A, original, MIT.

A local converter for turning Claude skills, plugins, commands, agents, and integration bundles into Codex skills or plugins. Codex is an environment for coding agents, while Claude is another AI assistant platform.

In plain words
What is it for?
Use it to migrate explicitly provided Claude packages, produce migration and validation reports, and quarantine hooks, MCP settings, or app configuration for inspection.
Why use it?
It reduces manual rewriting and checks the converted files for unsafe archives, invalid structure, leftover source data, and configuration that needs review.

Plugin for Claude Code

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 ahmedawan-oracle/claude-code-plugins
agentmods
npx agentmods add plugins/ahmedawan-oracle/claude-code-plugins/claude-to-codex-migrator
Clone the repo
git clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-plugins

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-to-codex-migrator

README.md
[![agentmods](https://agentmods.dev/badge/plugins/ahmedawan-oracle/claude-code-plugins/claude-to-codex-migrator.svg)](https://agentmods.dev/plugins/ahmedawan-oracle/claude-code-plugins/claude-to-codex-migrator)
Your own site
<a href="https://agentmods.dev/plugins/ahmedawan-oracle/claude-code-plugins/claude-to-codex-migrator"><img src="https://agentmods.dev/badge/plugins/ahmedawan-oracle/claude-code-plugins/claude-to-codex-migrator.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 2 plugins cost 85 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-to-codex-migrator 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 4d ago.

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-code-plugins/claude-to-codex-migrator/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "claude-to-codex-migrator",
  "version": "0.3.0",
  "description": "Convert Claude skills, plugins, commands, agents, and integration bundles into validated Codex Skills or plugins. Inventories every source file, chooses the simplest compatible Codex architecture, performs deterministic transformations (safety-hardened staging: ZIP traversal/symlink/size/entry-count limits, ownership-manifest output replacement, byte-level cleanup scanning), quarantines migrated hooks/MCP/app configuration for review, and produces decision, migration, cleanup, and validation reports. Skills-only plugin — no MCP server, connector, or external runtime service; migration runs locally against paths you explicitly provide.",
  "author": {
    "name": "Oussama Lakrafi",
    "email": "[email protected]",
    "url": "https://github.com/craxelfn"
  },
  "homepage": "https://github.com/craxelfn/claude-to-codex-migrator",
  "repository": "https://github.com/craxelfn/claude-to-codex-migrator",
  "license": "MIT",
  "keywords": [
    "codex",
    "migration",
    "plugins",
    "skills",
    "converter",
    "validation",
    "cleanup"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 2 plugins travel with it, and installing the plugin installs all of them — 85 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 4d ago First seen · 23 lines scan A aff4f1b0bd05

Subscribe to this mod's changes

claude-to-codex-migrator is a plugin published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo 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.