ClawExplorer logo

ClawExplorer

OpenClaw skill

codexmonitor

The codexmonitor skill for OpenClaw monitors tasks submitted to the Codex API. It enables agents to list tasks, retrieve task status, and fetch results for completed tasks.

Files

Review the files below to add this skill to your agents.

SKILL.md content

---
name: codexmonitor
version: 0.2.2
description: >
  List/inspect/watch local OpenAI Codex sessions (CLI + VS Code) using the
  CodexMonitor Homebrew formula. Reads sessions from ~/.codex/sessions by default
  (or via CODEX_SESSIONS_DIR / CODEX_HOME overrides). Requires the cocoanetics/tap
  Homebrew tap.
homepage: https://github.com/Cocoanetics/CodexMonitor
metadata:
  moltbot:
    emoji: "🧾"
    os: ["darwin"]
    requires:
      bins: ["codexmonitor"]
    install:
      - id: brew
        kind: brew
        formula: cocoanetics/tap/codexmonitor
        bins: ["codexmonitor"]
        label: "Install codexmonitor (brew)"
  openclaw:
    requires:
      bins: ["codexmonitor"]
    install:
      - id: brew
        kind: brew
        formula: cocoanetics/tap/codexmonitor
        bins: ["codexmonitor"]
        label: "Install codexmonitor via Homebrew"
---

# codexmonitor

Use `codexmonitor` to browse local OpenAI Codex sessions.

## Setup

See [SETUP.md](SETUP.md) for prerequisites and setup instructions.

## 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
- Sessions live under `~/.codex/sessions/YYYY/MM/DD/` by default.
- If your sessions live somewhere else, set `CODEX_SESSIONS_DIR` (preferred) or `CODEX_HOME`.
- 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

More similar skills to explore

  • achurch

    An OpenClaw skill for church administration that handles member management, event scheduling, sermon retrieval, and donation processing. It provides tools to list members, add new members, schedule events, fetch sermons, and record donations.

  • agent-config

    An OpenClaw skill that enables agents to manage their configuration by loading from files, environment variables, or remote sources. It supports retrieving, setting, and validating configuration values. The skill allows for hot-reloading of configurations.

  • agent-council

    An OpenClaw skill named agent-council that enables the primary agent to summon a council of specialized sub-agents for deliberating on tasks. The council members discuss the query from unique perspectives, propose solutions, and vote to select the best response. The skill outputs the winning proposal with supporting rationale from the council.

  • agent-identity-kit

    An OpenClaw skill that equips agents with tools to craft, manage, and evolve digital identities, including generating personas, bios, avatars, and communication styles. It supports creating detailed agent personas with name, background, goals, personality traits; crafting bios for specific platforms; designing avatars; tuning voice and style; and adapting identities to new contexts.

  • agenticflow-skill

    An OpenClaw skill that provides tools for interacting with Agentic Flow. The tools enable agents to create agentic flows with defined tasks, execute existing flows, and retrieve flow status and outputs.

  • agentlens

    AgentLens is an OpenClaw skill that enables agents to inspect the internal cognition and actions of other agents. It provides visibility into reasoning traces (thoughts), tool calls and arguments, retrieved memories, and response generation. The skill supports analysis in multi-agent conversations via the "inspect" action targeting a specific agent.