How do I install the LLM Cost Optimizer skill?

Run npx skillmds@latest add droodotfoo/llm-cost-optimizer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is LLM Cost Optimizer safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with LLM Cost Optimizer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is LLM Cost Optimizer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published LLM Cost Optimizer?

DROOdotFOO (@droodotfoo) published this skill. Their other Agent Skills are listed on their SkillMD profile.

LLM Cost Optimizer by droodotfoo — Agent Skill

Name: LLM Cost Optimizer
Author: DROOdotFOO

LLM Cost Optimizer

Analyze and reduce LLM API costs through model routing, caching, and prompt optimization. TRIGGER when: user asks about LLM costs, API spend reduction, token optimization, model routing, or prompt caching. DO NOT TRIGGER when: user asks about model quality comparison, fine-tuning, or general prompt engineering.

DROOdotFOO 49f237b 2 files · 10.3 KB Updated Sep 17, 2026

File contents

LLM Cost Optimizer

Reduce LLM API costs systematically without sacrificing output quality.

Three Modes

1. Cost Audit

Assess current spend and find the 80/20 opportunities.

Instrument -- Add token counting and cost tracking per request. Log model, input tokens, output tokens, latency, and use case.
Find 80/20 -- Identify which 20% of use cases drive 80% of cost. Sort by total spend, not per-request cost.
Classify -- Tag each use case by complexity: simple (classification, extraction), medium (summarization, Q&A), complex (reasoning, code generation, multi-step).

2. Optimize Existing

Apply techniques to reduce cost on current workloads.

Routing -- Route simple tasks to cheaper/smaller models. See optimization-techniques.md.
Caching -- Cache repeated or similar queries. Prompt caching for system prompts.
Compression -- Reduce prompt size without losing quality. Trim examples, remove redundancy.

3. Design Cost-Efficient

Build new systems with cost awareness from day one.

Budget envelopes -- Set per-feature monthly cost budgets. Alert at 80%.
Routing layer -- Default to cheapest model that meets quality bar. Escalate on failure.
Observability -- Track cost per user, per feature, per model. Dashboard with trends.

Optimization Order

Apply techniques in this order (highest impact first):

Model routing (60-80% reduction potential)
Prompt caching (40-90% on cached portions)
Output length control (20-40%)
Prompt compression (15-30%)
Semantic caching (30-60% hit rate)
Request batching (10-25%)

See optimization-techniques.md for detailed guidance on each technique.

What You Get

A cost audit identifying which use cases drive the majority of LLM spend, with per-request and total cost breakdowns.
Prioritized optimization recommendations (model routing, caching, compression) ranked by reduction potential.
Concrete implementation steps with expected cost savings percentages for each technique.

Rules

Never optimize before measuring -- instrument first
Never sacrifice quality silently -- A/B test every change
Cost per request is misleading -- optimize total spend per outcome
The cheapest token is the one you never send

---name: llm-cost-optimizerdescription: Analyze and reduce LLM API costs through model routing, caching, and prompt optimization. TRIGGER when: user asks about LLM costs, API spend reduction, token optimization, model routing, or prompt caching. DO NOT TRIGGER when: user asks about model quality comparison, fine-tuning, or general prompt engineering.---# LLM Cost OptimizerReduce LLM API costs systematically without sacrificing output quality.## Three Modes### 1. Cost AuditAssess current spend and find the 80/20 opportunities.1. **Instrument** -- Add token counting and cost tracking per request. Log model, input tokens, output tokens, latency, and use case.2. **Find 80/20** -- Identify which 20% of use cases drive 80% of cost. Sort by total spend, not per-request cost.3. **Classify** -- Tag each use case by complexity: simple (classification, extraction), medium (summarization, Q&A), complex (reasoning, code generation, multi-step).### 2. Optimize ExistingApply techniques to reduce cost on current workloads.1. **Routing** -- Route simple tasks to cheaper/smaller models. See optimization-techniques.md.2. **Caching** -- Cache repeated or similar queries. Prompt caching for system prompts.3. **Compression** -- Reduce prompt size without losing quality. Trim examples, remove redundancy.### 3. Design Cost-EfficientBuild new systems with cost awareness from day one.1. **Budget envelopes** -- Set per-feature monthly cost budgets. Alert at 80%.2. **Routing layer** -- Default to cheapest model that meets quality bar. Escalate on failure.3. **Observability** -- Track cost per user, per feature, per model. Dashboard with trends.## Optimization OrderApply techniques in this order (highest impact first):1. Model routing (60-80% reduction potential)2. Prompt caching (40-90% on cached portions)3. Output length control (20-40%)4. Prompt compression (15-30%)5. Semantic caching (30-60% hit rate)6. Request batching (10-25%)See [optimization-techniques.md](./optimization-techniques.md) for detailed guidance on each technique.## What You Get- A cost audit identifying which use cases drive the majority of LLM spend, with per-request and total cost breakdowns.- Prioritized optimization recommendations (model routing, caching, compression) ranked by reduction potential.- Concrete implementation steps with expected cost savings percentages for each technique.## Rules1. Never optimize before measuring -- instrument first2. Never sacrifice quality silently -- A/B test every change3. Cost per request is misleading -- optimize total spend per outcome4. The cheapest token is the one you never send

Frequently asked questions

LLM Cost Optimizer

File contents

LLM Cost Optimizer

Three Modes

1. Cost Audit

2. Optimize Existing

3. Design Cost-Efficient

Optimization Order

What You Get

Rules

Related skills

Frequently asked questions

How do I install the LLM Cost Optimizer skill?

What does the LLM Cost Optimizer skill do?

Is LLM Cost Optimizer safe to use?

Which AI agents work with LLM Cost Optimizer?

Is LLM Cost Optimizer free to use?

Who published LLM Cost Optimizer?