cost-aware-llm-pipeline
Optimizes LLM API costs through model routing, budget tracking, narrow retry logic, and prompt caching.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill cost-aware-llm-pipelineStats
| Total installs | 1,279 |
| Weekly installs | 1.3K |
| GitHub stars | 112.5K |
| First seen | Feb 17, 2026 |
| Source | @affaan-m/everything-claude-code |
Summary
- Routes requests to cheaper models (Haiku) for simple tasks and expensive models (Sonnet, Opus) only when complexity thresholds are met, reducing spend by 3–19x on routine work
- Tracks cumulative API costs with immutable dataclasses, enforces budget limits, and fails early to prevent overspend
- Implements narrow retry logic that retries only on transient errors (network, rate limit, server errors) and fails immediately on permanent failures (auth, validation)
- Caches long system prompts using Claude's prompt caching feature to reduce token usage and latency on repeated requests
Tags
Related skills
| Skill | Installs | vs cost-aware-llm-pipeline |
|---|---|---|
| day1-onboarding | 1,325 | +46 |
| adk-eval-guide | 1,345 | +66 |
| build-clusters | 1,247 | -32 |
| project-guidelines-example | 1,267 | -12 |
| pandas-pro | 1,197 | -82 |
FAQ
- How many installs does cost-aware-llm-pipeline have?
- cost-aware-llm-pipeline has 1,279 total installs and 1.3K installs this week.
- Where is cost-aware-llm-pipeline hosted?
- cost-aware-llm-pipeline is published by @affaan-m/everything-claude-code at https://github.com/affaan-m/everything-claude-code.
- How many GitHub stars does cost-aware-llm-pipeline have?
- cost-aware-llm-pipeline has 112.5K GitHub stars.
- When was cost-aware-llm-pipeline first indexed?
- OrangeBot.AI first indexed cost-aware-llm-pipeline on Feb 17, 2026.
- How do I install cost-aware-llm-pipeline?
- Run: npx skills add https://github.com/affaan-m/everything-claude-code --skill cost-aware-llm-pipeline