OpenClaw Model Usage

Use this skill to inspect local OpenClaw model usage directly from session JSONL files.

When to use

Use this skill when the user asks for:

• - the current / most recent model in use
• recent model usage
• usage summaries by provider/model
• token totals by model
• cost summaries by model when available
• per-agent or per-session usage
• session/subagent rollups
• daily model usage summaries
• a compact summary plus an optional HTML dashboard

What it does

This skill provides a local-first replacement for external model-usage workflows.

It reads OpenClaw session logs directly and does not depend on CodexBar.

Preferred usage

Start with a short human-readable summary:

CODEBLOCK0

Generate the HTML dashboard from real local logs when the user wants a richer artifact:

CODEBLOCK1

Recommended response pattern:

• - return a short human-readable summary first
• optionally generate and attach the HTML dashboard for richer inspection on phone/desktop

JSON output

CODEBLOCK2

Inputs

Default real source:

CODEBLOCK3

Important:

• - use the real local OpenClaw log root for user-facing summaries and dashboards
• do not use tests/fixtures_root unless you are intentionally running development tests
• fixture roots generate sample/test output, not the user's real usage report

References

If you need field-level sourcing details, read:

• - INLINECODE1