This skill summarizes per-model usage and costs from CodexBar local cost logs. It can produce a quick 'current model' view (the most recent daily entry) or a full model breakdown across available data. Outputs can be human-readable text or machine-friendly JSON for integration into reporting pipelines.
Use when you need a concise, scriptable report of model-level cost—for example, auditing which models drive most of spend, daily cost checks, or feeding a dashboard/alerting system. Works for both Codex and Claude provider outputs.
Best used with CLI-friendly assistants and automation runners that can call Python scripts (Copilot/CLI, Codex/CodexBar workflows, shell-savvy agents).
This skill has not been reviewed by our automated audit pipeline yet.