Catch the LLM call that quietly costs 10x what it should. A Claude Agent Skill that reviews LLM code for token/cost blowups and rewrites them cheaper — prompt caching, model tiers, context, batching. Anthropic & OpenAI.

agent-skills ai-engineering anthropic claude-code claude-skill cost-optimization llm llmops openai prompt-engineering rag tokens
3 Open Issues Need Help Last updated: Jul 10, 2026

Open Issues Need Help

View All on GitHub
enhancement good first issue

Catch the LLM call that quietly costs 10x what it should. A Claude Agent Skill that reviews LLM code for token/cost blowups and rewrites them cheaper — prompt caching, model tiers, context, batching. Anthropic & OpenAI.

#agent-skills#ai-engineering#anthropic#claude-code#claude-skill#cost-optimization#llm#llmops#openai#prompt-engineering#rag#tokens
enhancement help wanted good first issue

Catch the LLM call that quietly costs 10x what it should. A Claude Agent Skill that reviews LLM code for token/cost blowups and rewrites them cheaper — prompt caching, model tiers, context, batching. Anthropic & OpenAI.

#agent-skills#ai-engineering#anthropic#claude-code#claude-skill#cost-optimization#llm#llmops#openai#prompt-engineering#rag#tokens
enhancement good first issue

Catch the LLM call that quietly costs 10x what it should. A Claude Agent Skill that reviews LLM code for token/cost blowups and rewrites them cheaper — prompt caching, model tiers, context, batching. Anthropic & OpenAI.

#agent-skills#ai-engineering#anthropic#claude-code#claude-skill#cost-optimization#llm#llmops#openai#prompt-engineering#rag#tokens