zuharz

zuharz / ccode-to-codex

Public

Migrate Claude Code skills and Agents to Open AI Codex native skills and agents. Semantic mapping preserves original behavior, classifies migration risk (MECHANICAL / MANUAL / REFACTOR), validates structure, and tracks progress end-to-end. No manual rewrite required. Keep what you built. Run it in Codex CLI. Experimental.

17
3
69% credibility
Found Apr 23, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

An experimental toolkit that converts old Claude Code skills and agents into native Codex formats with validation, tracking, and migration workflows.

How It Works

1
🔍 Discover the migration helper

You find a handy toolkit that moves your old assistant instructions to a shiny new system.

2
📁 Gather your old instructions

Collect your existing skill and agent files from the old setup into one easy spot.

3
🚀 Run the automatic conversion

Hit go and watch it transform everything into new, ready-to-use packages with a progress tracker.

4
👀 Preview and check results

Look over the new versions in a safe preview to see the smooth updates.

5
✅ Validate and review

Run quick checks and give a thumbs up to confirm they're perfect for the new world.

🎉 Assistants live in the new system

Your skills and agents now work flawlessly, bringing your projects to life effortlessly.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 17 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ccode-to-codex?

This Python toolkit migrates Claude Code skills and agents to native OpenAI Codex formats, transforming workflows into Agent Skill packages and roles into custom-agent TOML files. It semantically maps behaviors to preserve original intent, normalizes MCP tool namespaces, and handles delegation via Codex subagents—no manual rewrites needed. Run migrations via CLI scripts in your Codex CLI setup, with outputs landing in .codex/skills/ and .codex/agents/.

Why is it gaining traction?

Unlike blind transliteration tools, it classifies migration risk upfront (MECHANICAL, MANUAL, REFACTOR), validates structures, and tracks progress via a dashboard and JSON state file. Developers get dry-run previews, post-migration validation, and nativeness review handoffs, making claude to codex shifts auditable and low-risk. The focus on agent behavior preservation hooks teams dreading ecosystem lock-in.

Who should use this?

AI workflow engineers with .claude/skills/ directories aiming to migrate claude skills to codex without losing agent orchestration. Teams building multi-agent systems in Codex CLI who need to port Claude agents while flagging refactor needs. Early adopters testing claude code to codex transitions before full production rollout.

Verdict

Grab it if you're migrating claude code to codex—solid for mechanical lifts with smart risk signals, but experimental status (17 stars, 0.699999988079071% credibility) means pair with manual reviews. Docs guide setup well; test on non-critical repos first.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.