ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified data analysis Safety 4/5

usage-export

Export OpenClaw usage data to CSV for analytics tools like Power BI. Hourly aggregates by activity type, model, and channel.

Why use this skill?

Export your OpenClaw agent data into structured CSVs for Power BI. Track tokens, costs, and tool usage across all your AI models and sessions.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bobot-agent/usage-export
Or

What This Skill Does

The usage-export skill is an essential telemetry utility for OpenClaw users, designed to aggregate session JSONL data into actionable CSV reports. By transforming granular raw logs into structured hourly summaries, it enables detailed oversight of AI agent behavior, token expenditure, and tool performance. Whether you are managing personal agent tasks or enterprise deployments, this skill provides the visibility needed to track operational costs and model efficiency. It automatically tracks token consumption—including specific metrics like cache read/write tokens—and organizes data by channel, provider, and activity type, making it a powerful foundation for your BI pipelines.

Installation

You can install this skill easily using the ClawdHub command line interface. Simply run clawdhub install usage-export in your terminal to automatically place the required scripts in your OpenClaw directory. If you prefer a manual setup, ensure you create the directory ~/.openclaw/skills/usage-export and clone the repository files, including the scripts/ folder, into this path. Post-installation, it is highly recommended to configure a recurring cron job—either via system crontab or the OpenClaw configuration file—to ensure your usage data is aggregated hourly without manual intervention.

Use Cases

This skill is perfect for users who need to perform post-hoc analytics on their AI interactions. You can use it to identify peak hours of agent activity, compare costs across different AI models (such as comparing claude-opus-4-5 against smaller, cheaper models), or audit tool execution frequency. It is particularly effective for teams looking to integrate agent data into Power BI or Excel for executive reporting, enabling the creation of cost-per-session dashboards and usage heatmaps.

Example Prompts

  1. "Run the usage export for the entire month of January to see my total expenditure."
  2. "Show me a summary of how many tokens my main agent spent on tool execution compared to chat responses yesterday."
  3. "Could you trigger an immediate usage export and save it to the default exports folder?"

Tips & Limitations

Keep in mind that the 'cost' column represents an estimate based on your provided pricing configurations, not necessarily your actual billing statement. Timestamps are strictly reported in UTC, so adjust your BI tool filters accordingly. Since the skill reads session files directly, ensure the agent process has read permissions to your session directory. Finally, while it handles subagent sessions, ensure that your environment variables, specifically USAGE_EXPORT_DIR, are correctly pointed to your data sources to avoid missing logs.

Metadata

Stars1100
Views0
Updated2026-02-17
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bobot-agent-usage-export": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#analytics#telemetry#cost-tracking#bi#reporting
Safety Score: 4/5

Flags: file-read, file-write, code-execution