arc-metrics-dashboard
от trypto1019
DevOps & CloudКратко
Track and visualize your agent's operational metrics.
Описание
Что делает этот навык
Records operational metrics for agents: API calls, task completions, errors, and timed durations. Generates text-based dashboards and exports data as JSON or CSV. Data is stored as daily JSON files in ~/.openclaw/metrics/ with no database required.
Stores metrics as flat JSON files with no database or infrastructure setup, making it usable immediately in any agent environment.
Когда его использовать
- Tracking API call volume across providers over a week
- Monitoring error rates during overnight agent runs
- Measuring average task duration after a code change
- Identifying which skills an agent uses most frequently
- Exporting daily metrics to CSV for external analysis
Пример сценария
User asks: What's my agent's error rate and average API call duration this week?
- 1
Run metrics.py view --name api_calls --period week to retrieve API call history
- 2
Run metrics.py view --name errors --period week to check recorded error events
- 3
Run metrics.py dashboard to generate a summary showing error rate and average durations
- 4
Run metrics.py export --format json to save full data for external review
Text dashboard showing weekly API call count, error rate, average task duration, and a JSON export file with complete metric history
Установка
clawhub install trypto1019/arc-metrics-dashboardВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.