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.
not rated 9 3mo ago A 32 tokens
Command Claude Code
Analyze LLM API usage in a codebase and recommend model right-sizing to reduce cost, carbon, and complexity.
not rated 9 3mo ago A 22 tokens
Skill Claude Code
One-line description of what this skill does and when to invoke it.
not rated 9 3mo ago A 18 tokens
Skill Claude Code
Detect the 7 types of agentic bloat in a codebase or system design.
not rated 9 3mo ago A 22 tokens
Skill Claude Code
Estimate the carbon footprint of an agentic AI system based on its LLM usage.
not rated 9 3mo ago A 20 tokens
Skill Claude Code
Generate a lean cost analysis report with model right-sizing recommendations and savings estimates.
not rated 9 3mo ago A 18 tokens
Skill Claude Code
Recommend the right model tier for each LLM task type.
not rated 9 3mo ago A 16 tokens
Skill Claude Code
Estimate token usage for LLM API calls found in code.
not rated 9 3mo ago A 14 tokens
Agent Claude Code
One-line description. Add PROACTIVELY if Claude should auto-invoke this agent.
not rated 9 3mo ago A 22 tokens
TEMPLATE
10Command Claude Code
One-line description shown in autocomplete when user types /.
not rated 9 3mo ago A 10 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: