Claude To Codex

Port Claude Artifacts To Codex

Finds Claude Code skills/agents that have no Codex counterpart in this repo and adapts them to Codex conventions, one item at a time with per-item approval.

Procedure

1. Compute The Gap

Run both diffs in parallel:

# Skills missing from codex/
comm -23 \
  /SKILL.md -> global/codex/skills//SKILL.md)
  - 
  ...

Agents to port   (global/claude/agents/.md -> global/codex/agents/.toml)
  - 
  ...

Ask which items to port. Do not proceed without explicit approval per item.

3. Adapt Skills

For each approved skill, read global/claude/skills//SKILL.md, then apply these substitutions:

| Find | Replace with | |---|---| | CLAUDE.md | AGENTS.md | | /\ invocation syntax | $ | | where-claude cross-references | where-agents-md | | audit-claude-md cross-references | audit-agent-docs | | Claude config paths (~/.claude/) | Codex config paths (~/.codex/, $CODEX_HOME when appropriate) | | "Claude Code" when referring to the product/tool | "Codex" | | "Claude" when used as the product/tool name | "Codex" |

Show the adapted content to the user and ask for approval before writing.

Write to global/codex/skills//SKILL.md only after approval.

4. Adapt Agents

For each approved agent, read global/claude/agents/.md.

Extract:

• name from YAML frontmatter;
• description from YAML frontmatter;
• tools from YAML frontmatter;
• the Markdown body as the Codex developer_instructions.

Write global/codex/agents/.toml in this shape:

name = ""
description = ""
sandbox_mode = "read-only"
model_reasoning_effort = "medium"
developer_instructions = """
Codex product references fixed>
"""

Use sandbox_mode = "read-only" when the Claude tools are only read/search tools (Read, Glob, Grep). If the Claude agent has broader tools, flag the conversion for manual review and ask before choosing a Codex sandbox mode. TOML conversion is lossy: quote and escape strings carefully, and do not claim the result is complete until a human has reviewed it.

5. Run install.sh

After all approved writes:

./install.sh --codex

Report which symlinks were created or already correct.

6. Wrap Up

Tell the user:

• which items were ported, with destination paths;
• which items were skipped and why;
• which product-specific equivalents were intentionally not duplicated;
• that new Codex skills and agents are picked up in a new Codex session.

Guardrails

• Never overwrite an existing file in global/codex/ - skip with a warning if the target already exists.
• Never modify any file under claude/ - it is read-only source for this skill.
• Always show adapted content and get per-item approval before writing.
• Markdown agent -> TOML is inherently lossy; flag it explicitly and preserve the role's intent.
• Names that differ between products (where-claude vs where-agents-md,

audit-claude-md vs audit-agent-docs) must be noted, not silently duplicated.

• Do not run ./install.sh --codex until at least one file has been written.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: ada-ggf25
• Source: ada-ggf25/AI-Tools
• License: MIT

Install and usage instructions live in the source repository linked above.