💰
AI EngineeringJavaScript

Cost-Aware LLM Pipeline

by xu-xiang

Cost-Aware LLM Pipeline is an AI Engineering skill for Claude Code, published by xu-xiang in everything-claude-code-zh.

1.9K stars307 forkson xu-xiang/everything-claude-code-zhAdded 2026/08/18+1% in starsRepository updated 2026/03/05
ai-agentsanthropicclaudeclaude-codedeveloper-toolseverything-claude-codellmmcponeskillproductivity
Install in seconds
Install Cost-Aware LLM Pipeline
Copy Cost-Aware LLM Pipeline into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/xu-xiang/everything-claude-code-zh/tree/main/skills/cost-aware-llm-pipeline ~/.claude/skills/cost-aware-llm-pipeline

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/xu-xiang/everything-claude-code-zh.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/cost-aware-llm-pipeline/SKILL.md in xu-xiang/everything-claude-code-zh
Installs to
~/.claude/skills/cost-aware-llm-pipeline
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What Cost-Aware LLM Pipeline does

Cost-Aware LLM Pipeline combines model routing, budget tracking, retry logic, and prompt caching to control LLM API costs. Use it in applications that call Claude or OpenAI APIs to route simple tasks to cheaper models, stay within budget, and retry only transient errors.

Cost-Aware LLM Pipeline is cataloged under AI Engineering on DirSkills. Cost-Aware LLM Pipeline comes from a repository tagged ai-agents, anthropic, claude, claude-code and developer-tools.

Documentation

README

成本感知型 LLM 流水线 (Cost-Aware LLM Pipeline)

在保持质量的同时控制 LLM API 成本的模式。将模型路由 (Model Routing)、预算跟踪 (Budget Tracking)、重试逻辑 (Retry Logic) 和提示词缓存 (Prompt Caching) 组合成一个可复用的流水线。

何时启用

  • 构建调用 LLM API(Claude、GPT 等)的应用
  • 处理具有不同复杂度的批量项目
  • 需要将 API 支出控制在预算范围内
  • 在不牺牲复杂任务质量的前提下优化成本

核心概念

1. 基于任务复杂度的模型路由 (Model Routing)

为简单任务自动选择更便宜的模型,将昂贵的模型留给复杂任务。

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Cost-Aware LLM Pipeline

  • What else does xu-xiang publish alongside Cost-Aware LLM Pipeline?

    Cost-Aware LLM Pipeline is one of 25 skills that DirSkills catalogs from xu-xiang/everything-claude-code-zh, the repository it ships in. Its siblings there include API Design Patterns, Article Writing and Autonomous Loops. Each one is a separate skill with its own page in this directory, installs the same way Cost-Aware LLM Pipeline does, and is maintained by xu-xiang in that same repository. The rest of the collection is listed on the xu-xiang/everything-claude-code-zh page.

  • How does Cost-Aware LLM Pipeline compare to other AI Engineering skills?

    Cost-Aware LLM Pipeline ranks #913 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Cost-Aware LLM Pipeline against them. Open each page to compare what they document and how they install.

More from xu-xiang/everything-claude-code-zh

Cost-Aware LLM Pipeline is one of 25 skills cataloged on DirSkills from xu-xiang/everything-claude-code-zh.

See all 25 skills
📐
2w ago

API Design Patterns

API Design Patterns provides conventions and best practices for designing consistent, developer-friendly REST APIs, including resource naming, HTTP status codes, pagination, filtering, error responses, versioning, and rate limiting.
DevOps
1.9K307
✍️
2w ago

Article Writing

Article Writing drafts long-form content such as articles, guides, tutorials, and newsletters in a specific voice captured from examples or brand guidelines. Use it when you need polished copy longer than a paragraph with consistent tone, structure, and credibility.
Writing
1.9K307
🔁
2w ago

Autonomous Loops

Autonomous Loops provides patterns and architectures for running Claude Code without human intervention, from simple claude -p pipelines to RFC-driven multi-agent DAG orchestration. Use it to set up autonomous development workflows, CI/CD pipelines, parallel agents, and quality gates.
Automation
1.9K307
⚙️
2w ago

Backend Patterns

Backend Patterns provides architectural patterns and best practices for building scalable server-side applications, covering REST API design, repository/service layers, database optimization, caching, and error handling. Use it when implementing Node.js, Express, or Next.js API routes.
DevOps
1.9K307
🛠️
2w ago

C++ Coding Standards

C++ Coding Standards provides a set of rules and best practices based on the C++ Core Guidelines for writing modern, safe, and idiomatic C++ code. Use it when writing, reviewing, or refactoring C++ code to enforce type safety, resource safety, immutability, and clarity.
Quality
1.9K307
🧪
2w ago

C++ Testing

C++ Testing guides writing and debugging C++17/20 tests with GoogleTest/Mock, CMake/CTest, coverage, and sanitizers. Use it when creating or fixing C++ tests, configuring CI test gates, or diagnosing flaky failures.
Quality
1.9K307