General skillCode review and quality
llm-cost-guard
Finds the dominant cost waste in LLM-calling code and proposes cheaper rewrites with explicit trade-offs.
Finds the dominant cost waste in LLM-calling code and proposes cheaper rewrites with explicit trade-offs.
llm-cost-guard statically reviews LLM-calling code for repeated uncached prefixes, oversized model tiers, bloated context, unbounded output, unbudgeted agent loops, and repeated embeddings. It estimates the dominant tokens-times-price-times-volume term, then proposes prompt caching, model routing, context trimming, output caps, or batching while naming latency and quality trade-offs. It has no billing access, and projected savings still require current prices and evaluation results.
Resource types
Use cases
Platforms
Public GitHub facts last synced Jul 10, 2026.
Review high-risk code through independent specialist agents and synthesis.
Audit a repository locally and turn cited findings into clear priorities.
Review code with adjustable roast levels and actionable fixes.
Score and audit Claude SKILL.md files