About

Imported from borghei/claude-skills (engineering/llm-cost-optimizer/SKILL.md). Install upstream with npx skills add borghei/claude-skills --skill llm-cost-optimizer. Copyright stays with the author (MIT + Commons Clause).

LLM Cost Optimizer

Name: llm-cost-optimizer
Author: borghei

Category: Engineering Domain: AI Cost Management

Overview

The LLM Cost Optimizer skill provides tools for counting tokens, estimating costs across different LLM providers, and optimizing prompts to reduce token usage without sacrificing quality. Essential for teams managing LLM API budgets at scale.

Clarify First

Before estimating or optimizing, confirm these inputs. If any is unknown or vague, ASK — do not assume:

Input prompt/text — the prompt file or text to count or optimize (the input via --file/--text/--stdin)
Target models — which models to estimate cost for (sets --models and the pricing comparison)
Goal — cost estimation vs prompt optimization, and any target reduction (selects token_counter.py vs prompt_optimizer.py and sets --target-reduction)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Quick Start

# Count tokens in a prompt file and estimate costs
python scripts/token_counter.py --file prompt.txt --models gpt-4o claude-sonnet

# Count tokens from stdin
echo "Hello world" | python scripts/token_counter.py --stdin --models all

# Analyze a prompt for optimization opportunities
python scripts/prompt_optimizer.py --file system_prompt.txt

# Optimize with target reduction
python scripts/prompt_optimizer.py --file prompt.txt --target-reduction 30

Tools Overview

Tool	Purpose	Key Flags
`token_counter.py`	Count tokens and estimate costs across models	`--file`, `--text`, `--stdin`, `--models`
`prompt_optimizer.py`	Analyze prompts for token reduction opportunities	`--file`, `--target-reduction`, `--format`
`cache_savings_calculator.py`	Model prompt-cache economics: naive vs cached cost, break-even reuse, % savings	`--requests`, `--cached-tokens`, `--cache-write-multiplier`, `--cache-read-multiplier`, `--base-input-price`, `--json`

Workflows

Cost Estimation for New Project

Collect sample prompts (system prompt + user messages)
Run token_counter.py with target models
Multiply per-request cost by expected daily volume
Compare models on cost-quality tradeoff

Prompt Optimization Sprint

Identify highest-cost prompts from usage logs
Run prompt_optimizer.py on each
Apply suggested optimizations
Re-count tokens to verify reduction
A/B test optimized vs. original for quality

Reference Documentation

LLM Pricing Guide - Current pricing for major LLM providers, token estimation methods
Caching & Batch Economics - Prompt/context caching break-even math, batch-API cost tradeoff, reasoning-effort cost impact, structured-output token overhead (model-agnostic, user-supplied rates)

Common Patterns

Token Reduction Techniques

Remove redundant instructions and examples
Use shorter variable names in few-shot examples
Compress verbose system prompts
Replace repeated context with references
Use structured output formats (JSON) to reduce response tokens
Batch multiple requests into single prompts where possible

Cost-Effective Model Selection

Use smaller models for classification/extraction tasks
Reserve large models for complex reasoning
Implement model routing based on query complexity
Cache responses for identical or similar queries
Cache the stable system-prompt/context/schema prefix (most-stable first, volatile last) and check the reuse break-even with cache_savings_calculator.py
Route bulk, non-interactive work to the batch API (~half cost for added latency); right-size reasoning effort per route — high only where accuracy demands it

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/borghei-claude-skills-llm-cost-optimizer/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

borghei-claude-skills-llm-cost-optimizer.ocm.jsonjson

{
  "ocm": "1",
  "id": "borghei-claude-skills-llm-cost-optimizer",
  "kind": "skill",
  "name": "llm-cost-optimizer",
  "description": "This skill should be used when the user asks to \"estimate LLM costs\", \"count tokens in prompts\", \"optimize prompt token usage\", \"compare model pricing\", or \"reduce LLM API costs\".",
  "publisher": "borghei",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "coding"
    ],
    "tags": [
      "skill-md",
      "llm",
      "tokens",
      "cost-optimization",
      "prompt-engineering",
      "pricing",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "This skill should be used when the user asks to \"estimate LLM costs\", \"count tokens in prompts\", \"optimize prompt token usage\", \"compare model pricing\", or \"reduce LLM API costs\"."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/borghei/claude-skills",
      "path": "engineering/llm-cost-optimizer/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/borghei/claude-skills/blob/HEAD/engineering/llm-cost-optimizer/SKILL.md",
      "key": "borghei/claude-skills/engineering/llm-cost-optimizer/SKILL.md"
    },
    "license": "MIT + Commons Clause"
  },
  "instructions": "# LLM Cost Optimizer\n\n> **Category:** Engineering\n> **Domain:** AI Cost Management\n\n## Overview\n\nThe **LLM Cost Optimizer** skill provides tools for counting tokens, estimating costs across different LLM providers, and optimizing prompts to reduce token usage without sacrificing quality. Essential for teams managing LLM API budgets at scale.\n\n## Clarify First\n\nBefore estimating or optimizing, confirm these inputs. If any is unknown or vague, ASK — do not assume:\n\n- [ ] **Input prompt/text** — the prompt file or text to count or optimize (the input via `--file`/`--text`/`--stdin`)\n- [ ] **Targe",
  "cost": {
    "context_tokens": 959
  }
}

Fetch it by URL: GET /api/v1/registry/borghei-claude-skills-llm-cost-optimizer/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.