codexmonitor

SKILL.md content

---
name: codexmonitor
description: List/inspect/watch local OpenAI Codex sessions (CLI + VS Code) using the CodexMonitor Homebrew formula.
homepage: https://github.com/Cocoanetics/CodexMonitor
metadata: {"clawdbot":{"emoji":"🧾","os":["darwin"],"requires":{"bins":["codexmonitor"]},"install":[{"id":"brew","kind":"brew","formula":"cocoanetics/tap/codexmonitor","bins":["codexmonitor"],"label":"Install codexmonitor (brew)"}]}}
---

# codexmonitor

Use `codexmonitor` to browse local OpenAI Codex sessions stored in `~/.codex/sessions`.

## Requirements
- macOS
- Codex installed and producing sessions (CLI and/or VS Code extension)

## Install (Homebrew)

```sh
brew tap cocoanetics/tap
brew install codexmonitor
```

## Common commands

- List sessions (day): `codexmonitor list 2026/01/08`
- List sessions (day, JSON): `codexmonitor list --json 2026/01/08`
- Show a session: `codexmonitor show <session-id>`
- Show with ranges: `codexmonitor show <session-id> --ranges 1...3,26...28`
- Show JSON: `codexmonitor show <session-id> --json`
- Watch all: `codexmonitor watch`
- Watch specific: `codexmonitor watch --session <session-id>`

## Notes
- `codexmonitor` reads sessions from `~/.codex/sessions/YYYY/MM/DD/`.
- Sessions can be resumed/appended by id via Codex: `codex exec resume <SESSION_ID> "message"`.

How this skill works

• Uses the GitHub API to retrieve the list of directories in the skills repository
• For each subdirectory fetches the SKILL.md file if it exists
• Extracts metadata from the SKILL.md YAML frontmatter
• Compares against a local cache stored in the agent's memory
• If new skills are found compiles a summary and sends it as an observation
• Updates the cache with the new list

When to use it

• When enabling logging of all Codex API calls made by an OpenClaw agent
• When capturing prompts, completions, token usage, and metadata from Codex interactions for review

Best practices

• Set OPENAI_API_KEY environment variable before enabling the skill
• Configure POLL_INTERVAL to at least 60 seconds to avoid rate limits
• Verify OpenAI API key has Codex beta access
• Monitor skill logs for authentication errors
• Enable only if Codex is available in your OpenAI organization

Example use cases

• Real-time token usage tracking: Tracks input and output tokens for every Codex API call made by the agent.
• Cost estimation for Codex usage: Calculates estimated costs based on tracked token usage and current OpenAI pricing.
• Logging prompts and completions: Records all prompts sent to Codex and the corresponding code completions for analysis.
• Performance metrics collection: Collects metrics like success rates and average tokens per task for code generation.

FAQs