AI Cost Optimizer — Data & AI agent for Claude Code
Audits an LLM application or AI agent for token cost and rate-limit risk, using its usage logs and code, and returns a prioritised savings plan with concrete fixes.
How to install AI Cost Optimizer
Installs to ~/.claude/agents/dutchy313-ai-cost-optimizer-ai-cost-optimizer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dutchy313/ai-cost-optimizer/HEAD/.claude/agents/ai-cost-optimizer.md -o ~/.claude/agents/dutchy313-ai-cost-optimizer-ai-cost-optimizer.md Restart Claude Code, or start a new session, for it to be picked up.
What AI Cost Optimizer does
name: ai-cost-optimizer description: Audits an LLM application or AI agent for token cost and rate-limit risk, using its usage logs and code, and returns a prioritised savings plan with concrete fixes. Use proactively when asked to cut AI spend, review LLM calls, fix 429s, or design quotas. tools: Read, Grep, Glob, Bash, Agent, Edit, Write model: sonnet effort: medium maxTurns: 40 skills:
- llm-cost-and-rate-limits memory: project color: green
You are an AI cost-reduction engineer. Yo
Alternatives in Data & AI
- API Cost Scanner — Scans codebase for AI/API cost optimization opportunities including model usage, token estimates, caching stra 160 ★
- Database Optimizer 147 ★
- Review Code Correctness — A code review agent that checks analysis scripts for logical errors, incorrect function usage, wrong variable 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cost Analyst
Analyzes AI spend and budget via PromptWise - cost breakdown, forecast, and routing savings. Use when asked wh
LLM FinOps Architect
LLM FinOps Architect specializing in model-tier routing, cost-envelope governance, burn-rate monitoring, per-p
Cost Optimizer
Cloud and LLM cost optimization specialist — FinOps, right-sizing, caching strategies, Claude/OpenAI token red
Pipeline Optimizer
Reviews the LLM/agent pipeline — model selection, LangGraph wiring, MCP client lifecycle, async/streaming beha
LLM Performance Analyst
Evaluates LLM agent performance from session transcripts — token usage, tool-call efficiency, and error patter
Usage Scout
Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage
Related Skills
Database Optimizer
Optimize SQL queries, design efficient indexes, and handle database migrations. Solves N+1 problems, slow quer
Codemesh
Query the code knowledge graph before reading code. One-call context assembly via codemesh_answer returns inli
Shuten
Two plugins that cut an agent's excess text: CCShut - comments in the code (against context rot), Shut - chatt