Arsyn for Codex
Guides installing Arsyn skills into OpenAI Codex via a symlink under `~/.agents/skills/` for automatic skill discovery.
What this file does
Guides installing Arsyn skills into OpenAI Codex via a symlink under ~/.agents/skills/ for automatic skill discovery.
When to use it
- You use OpenAI Codex CLI and want to load Arsyn skills
- You need to set up skill symlinks on macOS or Linux
- You need to set up skill junctions on Windows
- You want to create your own personal Codex skills with SKILL.md
Assumes this stack
Arsyn for Codex
Guide for using Arsyn with OpenAI Codex via native skill discovery.
Manual Installation
Prerequisites
- OpenAI Codex CLI
- Git
Steps
-
Clone the repo:
git clone <your-arsyn-repo-url> ~/.codex/arsyn -
Create the skills symlink:
mkdir -p ~/.agents/skills ln -s ~/.codex/arsyn/skills ~/.agents/skills/arsyn -
Restart Codex.
-
For subagent skills (optional): Skills like
parallelizingandorchestratingrequire Codex's multi-agent feature. Add to your Codex config:[features] multi_agent = true
Windows
Use a junction instead of a symlink (works without Developer Mode):
New-Item -ItemType Directory -Force -Path "$env:USERPROFILE\.agents\skills"
cmd /c mklink /J "$env:USERPROFILE\.agents\skills\arsyn" "$env:USERPROFILE\.codex\arsyn\skills"
How It Works
Codex has native skill discovery — it scans ~/.agents/skills/ at startup, parses SKILL.md frontmatter, and loads skills on demand. Arsyn skills are made visible through a single symlink:
~/.agents/skills/arsyn/ → ~/.codex/arsyn/skills/
The bootstrapping skill is discovered automatically and enforces skill usage discipline — no additional configuration needed.
Usage
Skills are discovered automatically. Codex activates them when:
- You mention a skill by name (e.g., "use ideating")
- The task matches a skill's description
- The
bootstrappingskill directs Codex to use one
Personal Skills
Create your own skills in ~/.agents/skills/:
mkdir -p ~/.agents/skills/my-skill
Create ~/.agents/skills/my-skill/SKILL.md:
---
name: my-skill
description: Use when [condition] - [what it does]
---
# My Skill
[Your skill content here]
The description field is how Codex decides when to activate a skill automatically — write it as a clear trigger condition.
Updating
cd ~/.codex/arsyn && git pull
Skills update instantly through the symlink.
Uninstalling
rm ~/.agents/skills/arsyn
Windows (PowerShell):
Remove-Item "$env:USERPROFILE\.agents\skills\arsyn"
Optionally delete the clone: rm -rf ~/.codex/arsyn (Windows: Remove-Item -Recurse -Force "$env:USERPROFILE\.codex\arsyn").
Troubleshooting
Skills not showing up
- Verify the symlink:
ls -la ~/.agents/skills/arsyn - Check skills exist:
ls ~/.codex/arsyn/skills - Restart Codex — skills are discovered at startup
Windows junction issues
Junctions normally work without special permissions. If creation fails, try running PowerShell as administrator.
What's inside
8 sections: prerequisites, install steps for Unix and Windows, how it works, usage, personal skills, updating, uninstalling, troubleshooting.
Change this for your project
- Replace
~/.codex/arsynwith your actual Arsyn clone path - Replace
~/.agents/skills/arsynwith your desired skills symlink target
Where it goes
Use as the system prompt for your model call, or as the base instructions in your agent framework.
Worth borrowing
- Using a symlink to expose a skill directory without copying files
- Writing SKILL.md frontmatter with a
descriptionfield that doubles as an auto-activation trigger
Related Documents
Character Persona
Defines a Fallout 2 roleplay persona for an LLM agent: charming rogue with social-first combat and moral code.
How to implement tool use
Explains how to define, configure, and control tool use with the Anthropic API, including model selection, tool definitions, output control, and parallel calls.
Gemini by Example
Collects 20+ Gemini API code examples covering text, images, audio, video, PDFs, agents, and token counting.
Claude Tool Use (Function Calling) Documentation
Teaches how to define and use Claude tool use (function calling) with Python, including schema rules, execution patterns, and best practices.