Model Mix is a Data skill for Claude Code, published by hoangsonww in Claude-Code-Agent-Monitor.
Model Mix breaks down Claude Code usage by model family, showing token share, cost share, and gaps that suggest where expensive models are doing cheap work. Use it to decide routing and whether to downshift tasks to a cheaper tier.
Model Mix is cataloged under Data on DirSkills. Model Mix comes from a repository tagged ai-agents, claude-agents, claude-code, claude-skills and express.
Documentation
See where your tokens and dollars go by model family, and where to re-route work.
The user provides: $ARGUMENTS
This may be: empty (analyze the whole fleet), "today" / "this week" / a date range, or a focus like "where is Opus overused?". When empty, analyze all data from /api/pricing/cost and /api/sessions.
This is the opening of the README. Read the full README on GitHub.
Model Mix is one of 20 skills that DirSkills catalogs from hoangsonww/Claude-Code-Agent-Monitor, the repository it ships in. Its siblings there include Cache Efficiency, Config Audit and Cost Breakdown. Each one is a separate skill with its own page in this directory, installs the same way Model Mix does, and is maintained by hoangsonww in that same repository. The rest of the collection is listed on the hoangsonww/Claude-Code-Agent-Monitor page.
Model Mix ranks #460 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Model Mix against them. Open each page to compare what they document and how they install.
Model Mix is one of 20 skills cataloged on DirSkills from hoangsonww/Claude-Code-Agent-Monitor.
Model Mix is one of 668 Data skills cataloged on DirSkills, ranked #460 by stars among them.