Description
model-usage is an agent skill from the OpenClaw project, listed on skills.sh. It summarizes what you spent on AI coding models from CodexBar's local cost logs, per model, for Codex or Claude, either for the current model or a breakdown of all models. A bundled Python script also reads exported CodexBar JSON anywhere Python runs. Like every skill, it is a SKILL.md file of instructions the agent reads when the task calls for it, so the agent knows which commands to run and what to avoid. It is free and open source in the openclaw/openclaw repository on GitHub.…
Highlights
- Per-model cost from CodexBar logs
- Current-model or all-model summaries
- Works for Codex and Claude
- Bundled Python summarizer
Ratings & Reviews
No ratings yet
Be the first to rate model-usage.
People also visit
model-usage FAQ
What does the model-usage skill do?
It summarizes what you spent on AI coding models from CodexBar's local cost logs, per model, for Codex or Claude, either for the current model or a breakdown of all models.
How do I install the model-usage skill?
Run: npx skills add https://github.com/openclaw/openclaw --skill model-usage
What do I need before using it?
CodexBar on macOS or Linux, or an exported CodexBar JSON file and Python.
Is it free?
Yes. It is open source and part of the openclaw/openclaw repository on GitHub.
What is an agent skill?
A SKILL.md file of instructions, sometimes with scripts and reference notes, that an AI agent loads when a task needs it, so it knows how to use a tool well.
What are the best model-usage alternatives?
Popular alternatives to model-usage include coding-agent, 1password and apple-notes. See all model-usage alternatives