claude-and-codex-settings
My Claude Code and OpenAI Codex setup with skills, commands, hooks, subagents, and MCP servers.
"They make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs. They really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves." -- Andrej Karpathy
This repo's guidelines are structured to fix exactly these pitfalls.
Installation • Plugins • Configuration
Installation
Plugins add skills, commands, and automations to your AI coding tool. Install only what you need from the plugin list below.
Prerequisites: See INSTALL.md for setup requirements.
Claude Code
# Add marketplace (one time)
/plugin marketplace add funsaized/claude-and-codex-settings
# Install any plugin by name
/plugin install <plugin-name>@claude-and-codex-settings
Codex CLI
Codex installs plugins from a local marketplace rather than a direct shell install command.
- Clone this repo locally and open it in Codex.
- This repo already includes
.agents/plugins/marketplace.json.
- If Codex was already open when you added or changed that file, restart Codex.
- In Codex, open
/plugins.
- Choose
Claude & Codex Settings and install the plugins you want.
This README only covers installing this marketplace.
For generic Codex marketplace examples and maintainer docs, see CLAUDE.md.
Create the symlink for cross-tool compatibility:
ln -sfn CLAUDE.md AGENTS.md
Plugins
intelligent-compact - Stop Claude Code from forgetting file paths, root causes, and open questions when it auto-summarizes long sessions
| Claude Code | Codex CLI |
|---|
/plugin install intelligent-compact@claude-and-codex-settings | Open /plugins -> Claude & Codex Settings -> install intelligent-compact |
When Claude Code auto-summarizes a long session, the default summary routinely drops the highest-signal facts. This plugin tells the summarizer to keep them:
- File paths under investigation so the next turn doesn't re-discover where you were
- Confirmed root causes so you don't re-debug what's already solved
- Open questions, metrics, and IDs that prose summaries usually round away
- Findings from expensive subagent runs that took minutes to gather
Runs on every /compact (manual) and every auto compaction. Claude Code only; Codex doesn't yet expose a comparable summary hook.
claude-telemetry-hooks - Track per-device Claude Code usage, rejection reasons, and per-session stats from a single dashboard
| Claude Code | Codex CLI |
|---|
/plugin install claude-telemetry-hooks@claude-and-codex-settings | n/a |
Adds the two missing pieces Claude Code's telemetry needs to power a usage dashboard:
- Sticky session ID per project: resumed conversations stay one session, not dozens
- Categorized rejection reasons (profanity, wrong target, scope drift, retry, and more): chart why Claude pushes back
Per-device data is already in Claude Code's built-in OpenTelemetry stream.
python-skills - Python best practices from PEP 8, Zen of Python, Google Style Guide, Effective Python
| Claude Code | Codex CLI |
|---|
/plugin install python-skills@claude-and-codex-settings | Open /plugins -> Claude & Codex Settings -> install python-skills |