lean-auditor
01Agent Claude Code
PROACTIVELY scan codebases for LLM API usage patterns and classify each call by task type, model used, and optimization potential.
Agent Claude Code
PROACTIVELY scan codebases for LLM API usage patterns and classify each call by task type, model used, and optimization potential.
Command Claude Code
Analyze LLM API usage in a codebase and recommend model right-sizing to reduce cost, carbon, and complexity.
Settings file Claude Code
Agent settings declaring 4 allowed tools.
Skill Claude CodeCodex
One-line description of what this skill does and when to invoke it.
Skill Claude CodeCodex
Detect the 7 types of agentic bloat in a codebase or system design.
Skill Claude CodeCodex
Estimate the carbon footprint of an agentic AI system based on its LLM usage.
Skill Claude CodeCodex
Generate a lean cost analysis report with model right-sizing recommendations and savings estimates.
Skill Claude CodeCodex
Recommend the right model tier for each LLM task type.
Skill Claude CodeCodex
Estimate token usage for LLM API calls found in code.
Agent
One-line description. Add PROACTIVELY if Claude should auto-invoke this agent.
Command
One-line description shown in autocomplete when user types /.