skills.rest
sixscripts-ai
sixscripts-aiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

cost-aware-llm-pipeline

Enforce token budgets and provider selection across multi-provider LLM calls.

Updated Mar 20, 2026
Search Tags:#routing#llm#pipeline#budget#multi-provider#prompting#cost
One-click install
npx skills add https://github.com/sixscripts-ai/ghostssh --skill cost-aware-llm-pipeline-sixscripts-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cost-aware-llm-pipeline
Source: https://github.com/sixscripts-ai/ghostssh/tree/main/ghostssh-skills/cost-aware-llm-pipeline
Command: npx skills add https://github.com/sixscripts-ai/ghostssh --skill cost-aware-llm-pipeline-sixscripts-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps prevent budget overruns in multi-provider LLM pipelines by enforcing token budgets and providing guardrails during provider selection and caching.

Core Features & Use Cases

  • Enforces token budgets and manages provider selection to prevent overspending.
  • Caching strategies across provider chain to reuse results and reduce costs.
  • Supports batching and safe fallbacks in ghostssh workflows.

Quick Start

Configure the system to route LLM calls across providers with token budgets and caching enabled.

Frequently Asked Questions about cost-aware-llm-pipeline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce token budgets across multi-provider LLM calls?▼

To route LLM calls across multiple providers, configure the system to enforce token budgets and enable caching strategies across the Minimax, Anthropic, and OpenAI provider chain with a per-search cost cap.

Can I use caching strategies to reduce LLM spend in ghostssh workflows?▼

Yes, you can implement caching strategies to reuse results and reduce LLM spend in ghostssh workflows. The caching mechanism operates across the provider chain to support batching and safe fallbacks.

What is the best way to manage provider selection for cover letter generation?▼

The best way to manage provider selection for cover letter generation is to route calls through the Minimax, Anthropic, and OpenAI provider chain with enforced token budgets and caching enabled to cap per-search costs.

Does this approach work with the withFallback() function in ghostssh?▼

Yes, this budget enforcement approach works with the withFallback() function in ghostssh. It provides guardrails during provider selection and caching to support safe fallbacks while enforcing token budgets.

What workflows are applicable for a per-search cost cap in LLM pipelines?▼

Applicable workflows for a per-search cost cap include ranking batches, opinion engine tasks, profile condensation, and cover letter generation. Any workflow using withFallback() in ghostssh benefits from this budget enforcement.

Related Skills

Explore More Software Engineering Skills→
layeddielayeddie
1

ai-orchestration

Manage and rotate LLM API keys across multiple providers.

Community
Advanced
MBojerMBojer

CV Writer

Generate tailored CVs and cover letters for specific job applications.

Community
Advanced
patricio0312revpatricio0312rev
5

cost-latency-optimizer

Optimize LLM applications for cost and latency via caching, model selection, batching, and prompt optimization.

Community
Advanced
richardnpaulrichardnpaul

cost-aware-llm-pipeline

Route LLM API calls by task complexity and track immutable costs.

Community
Advanced