Summarize per-model CodexBar costs from local JSON logs.
npx skills add https://github.com/lalomorales22/penguins --skill model-usage-lalomorales22
Please help me install this Agent Skill. Skill: model-usage Source: https://github.com/lalomorales22/penguins/tree/main/skills/model-usage Command: npx skills add https://github.com/lalomorales22/penguins --skill model-usage-lalomorales22
CodexBar cost data is often stored locally and scattered; this skill consolidates per-model usage and spend into an accessible summary.
Run the bundled script to summarize per-model CodexBar costs from the local JSON log.
High-intent search queries and answers about installing and using this skill.
You can summarize per-model usage costs by running a script that parses the CodexBar cost payload, aggregates expenses from modelBreakdowns, and outputs a text or JSON summary for Codex and Claude models.
Yes, you can detect the current top-cost model by parsing the local cost JSON logs and comparing the aggregated expenses across the available modelBreakdowns.
The best way to compare provider costs is to aggregate per-model spend from local CodexBar logs, which supports a full per-model breakdown to help you identify which models contribute most to your overall costs.
You can parse the CodexBar cost payload by applying a script that extracts and aggregates model costs from the modelBreakdowns field, allowing you to output the results directly in a structured JSON format.
No, the cost aggregation works with both local CodexBar logs and provided JSON data, allowing you to parse and summarize per-model usage costs from either source.
Aggregating costs from the modelBreakdowns field is necessary because CodexBar cost data is often scattered locally, and consolidating it provides an accessible summary to quickly identify your top-cost models.
sarathi-aimlSummarize per-model costs from CodexBar local cost logs.
JoeyJoziahSummarize CodexBar cost logs by model with per-day aggregation and date filtering.
vut08905Parse CodexBar JSON logs to aggregate per-model costs and identify the top-cost model.
acaprinoAnalyze Claude Code JSONL session logs to generate Markdown usage reports.
