Codex Claude Code Config

Claude Code + Codex Agent Configuration System

A practical configuration kit for Claude Code, Codex, and other coding agents. It contains architectural principles, enforcement hooks, skills, drop-in rules, starter templates, and dynamic-workflow commands. Drop the relevant parts into a project so the agent starts from verified working patterns instead of rediscovering them every session.

This is not a collection of tips. It is a system that teaches your agent *how to work* - when to use one agent vs many, how to verify its own output, how to manage context across long sessions, how to not get poisoned by malicious packages.

Notes

Write-ups of the incidents that produced a rule or a hook here. Each states what was measured,
what is inference, and what the fix does not cover.

Installation

Three paths depending on what you need:

Option 1: Claude Code plugin (fastest)

The plugin brings the skills, agents, workflows, the safe-default hooks, and an
index of rules/ injected at session start. Team distribution with pinned
versions and auto-update, and the one-command Codex update, are in
docs/team-plugin.md.

Then in your Claude Code chat:

Option 2: Global install (hooks + skills available in every project)

The canonical tracked checkout's hooks/ directory stores the global hook scripts;
~/.claude/settings.json and ~/.codex/hooks.json register that exact source.
The installer must not create a second active ~/.claude/hooks/ tree; it merges
safe defaults into the existing manifests and keeps backups before changes.

Option 3: Project-local (hooks/skills only in this project)

This keeps everything under .claude/ in your repo, nothing global.

Choosing what to install

See AGENTS.md for the procedure an agent follows after install,
HOW-IT-WORKS.md for the mechanics of…