How do I install the Codex Compat skill?

Run npx skillmds@latest add tomevault-io/codex-compat in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Codex Compat safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Codex Compat?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Codex Compat free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Codex Compat?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Codex Compat by tomevault-io — Agent Skill

Name: Codex Compat
Author: tomevault-io

Codex Compat

Generate Codex hooks.json and AGENTS.md from Claude Code hooks. Maps supported hooks directly, including Edit|Write apply_patch aliases, and keeps Stop batch checks only as fallback. Use when setting up Codex compatibility or dual-agent support. Use when this capability is needed.

tomevault-io c59432d 2 files · 2.8 KB Updated Sep 17, 2026

File contents

Codex Compatibility Layer

Codex now supports Claude-style lifecycle hooks for SessionStart, UserPromptSubmit, PreToolUse, PermissionRequest, PostToolUse, and Stop. PreToolUse/PostToolUse matchers support Bash, MCP tool names, apply_patch, and Edit|Write aliases. Map Edit|Write hooks direct whenever possible.

What This Creates

.codex/hooks.json -- direct translation for supported Claude hooks
.codex/hooks/codex-batch-check.sh -- fallback only for checks that cannot run per tool event
AGENTS.md + CLAUDE.md -- shared project rules (Codex reads AGENTS.md, Claude Code reads CLAUDE.md)
compatibility matrix -- classify hooks as direct, direct with shim, fallback only, or unsupported

Steps

Read .claude/settings.json and classify every hook with the REFERENCE.md compatibility matrix.
Generate .codex/hooks.json:
- SessionStart, UserPromptSubmit, Stop -> direct
- PreToolUse / PostToolUse with Bash, Edit|Write, apply_patch, mcp__.* -> direct
- PermissionRequest for Bash / MCP / apply_patch -> direct where scripts understand Codex payloads
- Unsupported Claude events or handler types -> omit, document, or route to fallback only when semantics stay safe
Copy scripts/codex-batch-check.sh -> .codex/hooks/ only if fallback hooks are needed. chmod +x.
Generate AGENTS.md + CLAUDE.md from REFERENCE.md template.

Verify

.codex/hooks.json contains direct Edit|Write PostToolUse hooks when source has them
Batch checker is absent unless a real fallback-only hook needs it
AGENTS.md + CLAUDE.md at repo root
.claude/settings.json unchanged

Source: malinskibeniamin/skills — distributed by TomeVault.

---name: codex-compatdescription: Generate Codex hooks.json and AGENTS.md from Claude Code hooks. Maps supported hooks directly, including Edit|Write apply_patch aliases, and keeps Stop batch checks only as fallback. Use when setting up Codex compatibility or dual-agent support. Use when this capability is needed.---# Codex Compatibility LayerCodex now supports Claude-style lifecycle hooks for `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PermissionRequest`, `PostToolUse`, and `Stop`. `PreToolUse`/`PostToolUse` matchers support `Bash`, MCP tool names, `apply_patch`, and `Edit|Write` aliases. Map `Edit|Write` hooks direct whenever possible.## What This Creates- **`.codex/hooks.json`** -- direct translation for supported Claude hooks- **`.codex/hooks/codex-batch-check.sh`** -- fallback only for checks that cannot run per tool event- **`AGENTS.md`** + **`CLAUDE.md`** -- shared project rules (Codex reads AGENTS.md, Claude Code reads CLAUDE.md)- **compatibility matrix** -- classify hooks as `direct`, `direct with shim`, `fallback only`, or `unsupported`## Steps1. Read `.claude/settings.json` and classify every hook with the [REFERENCE.md](REFERENCE.md) compatibility matrix.2. Generate `.codex/hooks.json`: - `SessionStart`, `UserPromptSubmit`, `Stop` -> direct - `PreToolUse` / `PostToolUse` with `Bash`, `Edit|Write`, `apply_patch`, `mcp__.*` -> direct - `PermissionRequest` for `Bash` / MCP / `apply_patch` -> direct where scripts understand Codex payloads - Unsupported Claude events or handler types -> omit, document, or route to fallback only when semantics stay safe3. Copy `scripts/codex-batch-check.sh` -> `.codex/hooks/` only if fallback hooks are needed. `chmod +x`.4. Generate `AGENTS.md` + `CLAUDE.md` from [REFERENCE.md](REFERENCE.md) template.## Verify- [ ] `.codex/hooks.json` contains direct `Edit|Write` PostToolUse hooks when source has them- [ ] Batch checker is absent unless a real fallback-only hook needs it- [ ] `AGENTS.md` + `CLAUDE.md` at repo root- [ ] `.claude/settings.json` unchanged---> Source: [malinskibeniamin/skills](https://github.com/malinskibeniamin/skills) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions