OpenClaw skill
codex-monitor
An OpenClaw skill that enables agents to monitor the Anthropic Codex knowledge base for updates and retrieve codex entries. It provides tools to list available codex documents, fetch specific documents by ID or slug, and check the latest codex version.
Files
Review the files below to add this skill to your agents.
Security notice: review the SKILL.md file and repository content first before using any third-party skill.
SKILL.md content
---
name: codex-monitor
description: Browse OpenAI Codex session logs stored in ~/.codex/sessions. Provides list/show/watch helpers via the local Swift project at ~/Developer/CodexMonitor.
---
# codex-monitor
Use this skill to query Codex sessions on Oliver’s machine.
## How it works
This skill runs the Swift executables from the local project:
- `~/Developer/CodexMonitor`
- CLI: `swift run CodexMonitor-CLI ...`
- App: `swift run CodexMonitor-App`
## Commands
### List sessions
- Day (text): `python3 skills/codex-monitor/codex_monitor.py list 2026/01/08`
- Day (JSON): `python3 skills/codex-monitor/codex_monitor.py list --json 2026/01/08`
- Month: `python3 skills/codex-monitor/codex_monitor.py list 2026/01`
- Year: `python3 skills/codex-monitor/codex_monitor.py list 2026`
### Show a session (text)
- `python3 skills/codex-monitor/codex_monitor.py show <session-id>`
- With ranges: `python3 skills/codex-monitor/codex_monitor.py show <session-id> --ranges 1...3,26...28`
- Open-ended: `--ranges 5...` (from #5 to end), `--ranges ...10` (from start through #10)
### Show a session (JSON)
- `python3 skills/codex-monitor/codex_monitor.py show <session-id> --json`
### Watch for changes
- All sessions: `python3 skills/codex-monitor/codex_monitor.py watch`
- Specific session: `python3 skills/codex-monitor/codex_monitor.py watch --session <session-id>`
### Monitor (Menu Bar App)
- Launch the menu bar monitor: `python3 skills/codex-monitor/codex_monitor.py monitor`
## Notes
- The underlying CLI may evolve; this wrapper passes through extra args.
- If the Swift build is slow, consider building once (`swift build`) and then running the built binary.
How this skill works
- Triggered by the 'codex-monitor' capability
- Reads last_check timestamp from agent memory or sets to now if missing
- Queries OpenClaw Codex API for entries created after last_check
- Filters query results for entries matching configured pattern
- Formats matching entries as a markdown list
- Returns the formatted list as output
- Updates last_check in agent memory to current time
When to use it
- When monitoring OpenAI Codex model interactions within OpenClaw agents
- When logging prompts, responses, token usage, and errors from Codex calls
- When tracking code generation performance and success rates in agent workflows
Best practices
- Set OPENAI_API_KEY environment variable
- Set MONGODB_URI environment variable
- Use secure MongoDB connection string
- Monitor OpenAI billing API rate limits
- Verify environment variables are set before activating the skill
Example use cases
- Tracking Codex token usage: Automatically records input and output token counts for every Codex model call made by the OpenClaw agent.
- Logging prompts and completions: Captures full prompts sent to Codex and the corresponding completions for review and analysis.
- Generating usage reports: Compiles and retrieves summaries of token consumption, call frequency, and performance metrics over time.
- Monitoring latency and errors: Tracks response times and error rates from Codex calls to identify performance issues.
FAQs
What is the ID of the codex-monitor skill?
codex-monitor
Who is the author of the codex-monitor skill?
odrobnik
What version is the codex-monitor skill?
0.1.0
What is the purpose of the codex-monitor skill?
The codex-monitor skill enables OpenClaw agents to monitor the status of ongoing Codex code generation tasks. It provides real-time updates on task progress, success, or failure, and logs detailed execution metrics.
What events does the codex-monitor skill listen for?
`codex/task/begin`, `codex/task/complete`, `codex/task/error`
What actions does the codex-monitor skill provide?
`get_task_status`: Retrieves the current status of a Codex task. `log_metrics`: Logs metrics like time taken, tokens used, etc.
What configuration is required for the codex-monitor skill?
`codex_api_url`: URL of the Codex API endpoint.
What is the default value for poll_interval in the codex-monitor skill?
5s
How is the codex-monitor skill installed?
Included in OpenClaw skills repository.
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.