llm-cost-optimizer
Estimates LLM token counts and per-request cost across models, flags wasteful prompt text, and models prompt-cache break-even
Install / Use
npx skills add borghei/Claude-Skills --skill llm-cost-optimizerInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
AI & Machine LearningSupported Platforms
Tags
Our assessment of llm-cost-optimizer
llm-cost-optimizer scores 84/100 on our quality scale, 646th of 950 AI & Machine Learning skills we index.
Its SKILL.md is 4.2 KB long, well organised into 16 sections with 1 code example: a solid amount of guidance for an agent.
It has 817 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so llm-cost-optimizer is actively maintained.
- Our last check on 2026-11-06 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
llm-cost-optimizer compared with similar skills
All 4 of these similar skills score higher than llm-cost-optimizer; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| llm-cost-optimizer (this skill)by borghei | 84 | 817 | 57d ago | SKILL.md |
| claude-memby thedotmack | 100 | 117.9k | today | CLAUDE.md |
| Understand-Anythingby Egonex-AI | 100 | 93.0k | 2d ago | CLAUDE.md |
| headroomby headroomlabs-ai | 100 | 79.9k | today | CLAUDE.md |
| CowAgentby zhayujie | 100 | 48.0k | today | CLAUDE.md |
Frequently asked questions
- How do I install llm-cost-optimizer?
- Run
npx skills add borghei/Claude-Skills --skill llm-cost-optimizer. The install tabs above show the steps for each supported agent. - Which AI agents does llm-cost-optimizer work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is llm-cost-optimizer safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is llm-cost-optimizer still maintained?
- The repository was last updated about 2 months ago, so llm-cost-optimizer is actively maintained.
Skill content
View source on GitHubname: 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". license: MIT + Commons Clause metadata: version: 1.1.0 author: borghei category: engineering domain: ai-cost-management updated: 2026-06-29 tags: [llm, tokens, cost-optimization, prompt-engineering, pricing]
LLM Cost Optimizer
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
--modelsand the pricing comparison) - [ ] Goal — cost estimation vs prompt optimization, and any target reduction (selects
token_counter.pyvsprompt_optimizer.pyand 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.pywith 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.pyon 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
Related Skills
claude-mem
117.9kPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
93.0kGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
headroom
79.9kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
CowAgent
48.0kOpen-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
