Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

router

bởi gigabit-eth

Web & Frontend Development
431Lượt tải do clawskills.sh công bố
2Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity.

Mô tả

Kỹ năng này làm gì

Routes AI agent tasks to the cheapest model capable of handling them. Classifies work into routine, moderate, and complex tiers, then maps each to free through premium model options with pricing tables. Includes a decision algorithm and OpenClaw configuration for mid-session model switching and sub-agent spawning.

Reduces AI API costs 6-10x by matching task complexity to model capability instead of running everything on a premium model.

Khi nào nên dùng

  • Switching to a cheap model mid-session for bulk file reformatting
  • Spawning a DeepSeek sub-agent to fetch and parse 50 URLs
  • Escalating to Opus when a Sonnet-level model gets stuck on a multi-step bug
  • Running overnight endpoint health checks on free-tier models at zero cost
  • Batching agentic coding sub-tasks through Qwen3 Coder to cut monthly API spend

Quy trình ví dụ

ĐẦU VÀO

User asks: refactor these 30 test files to use the new shared helper

AGENT
  1. 1

    Classify the task as routine file operations, targeting Tier 1

  2. 2

    Select deepseek/deepseek-chat or qwen/qwen3-coder-next as the dispatch model

  3. 3

    Spawn a sub-agent with an explicit model field set to the Tier 1 choice

  4. 4

    Sub-agent executes refactoring and reports results back to the parent session

  5. 5

    Parent session resumes on its original model without cost bleed from routine work

ĐẦU RA

30 test files refactored at roughly $0.03 instead of $0.45 on Claude Sonnet

Yêu cầu

  • OpenRouter API key from openrouter.ai/keys

Cài đặt

clawhub install gigabit-eth/router

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết