llm-cost-optimizer — Claude Code plugin: what it does, how to install
Reduces LLM API spend using model routing and prompt caching. Useful when token bills climb or when launching AI features without cost controls.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install llm-cost-optimizer@claude-code-skillsWhat llm-cost-optimizer does
This plugin helps cut expenses on LLM APIs. It routes requests between models based on price and quality trade-offs. The tool sets up prompt caching alongside context compression. You can also track token expenses for individual product features.
It is not meant for RAG pipelines or prompt quality tuning. Those tasks belong to separate skills. The plugin focuses strictly on cost architecture when picking models and launching AI features.
What it helps with
- cut API expenses caused by heavy token consumption
- route requests between models based on cost and quality
- apply prompt caching and context compression
- track AI spend across specific product features
Example prompts for the agent
- Help me reduce LLM API spending across our services
- Set up prompt caching and model routing to save tokens
- Design cost observability for a new AI feature
How to install llm-cost-optimizer
Plugin marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install llm-cost-optimizer@claude-code-skillsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about llm-cost-optimizer
How to install llm-cost-optimizer in Claude Code?
Add the repository by running /plugin marketplace add alirezarezvani/claude-skills. Next, install the package with /plugin install llm-cost-optimizer@claude-code-skills.
What does llm-cost-optimizer do?
It lowers LLM expenses through model routing, prompt compression, and prompt caching. It also provides observability to trace token costs per feature.
Can llm-cost-optimizer help with RAG architecture or prompt quality?
No, it does not handle RAG design or prompt quality refinement. The author assigns those workflows to separate skills.
Source text
llm-cost-optimizer · MIT
Cut LLM API spend via model routing, prompt caching, prompt compression, and per-feature cost observability. Use when AI costs are too high, choosing between models, or launching an AI feature without cost architecture. NOT for RAG design or prompt quality (separate skills).
© Alireza Rezvani · MIT · alirezarezvani/claude-skills
