← 返回 Skills 市场

Smart Router Coding

Name: Smart Router Coding
Author: certainlogicai

作者 CertainLogicAI · GitHub ↗ · v1.0.3 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install smart-router-coding

功能描述

Route coding queries to the right model. Fast for lint, deep for architecture, never waste money on Opus for a one-liner.

使用说明 (SKILL.md)

smart-router-coding

Route coding queries to the right model. Fast for lint. Deep for architecture. Nothing in between.

How it works

Send a coding task. The router decides depth:

INPUT: coding query
  ↓
Is it cached? → Return instantly (0 cost)
  ↓ if no
What kind of task?

SIMPLE
  lint / format / boilerplate / regex
  one-liners / find & replace / rename
  → Qwen3.5 Flash ($0.0008/q)
  → 21s latency

MODERATE
  debug / refactor / implement function
  code review / write tests / SQL / scripts
  → Grok 4.20 ($0.004/q)
  → 11s latency

COMPLEX
  architecture design / security audit
  performance optimization / algorithms
  multi-file changes / critical logic
  → Opus 4.8 ($0.015/q)
  → 45s latency

What you save

Setup	Cost per query	Monthly (1k queries)
All Opus 4.8	$0.015	$15
All Grok 4.20	$0.004	$4
With router	~$0.003	$3

Speed

Router adds 2ms. The rest is the LLM — you'd wait that long anyway.

What changes is your average response time:

Setup	Average wait per query
All Opus 4.8	45s
All Grok 4.20	11s
With router	~13s

Simple tasks go to Qwen (21s). Standard goes to Grok (11s). Opus only when necessary (45s).

131 coding queries benchmarked across 7 languages. Full results: certainlogic.ai/benchmarks

Usage

clawhub install smart-router-coding

Author

Created by CertainLogic — deterministic AI infrastructure. certainlogic.ai

安全使用建议

This appears safe to install for local model-tier recommendations. Treat its model, latency, and cost output as a heuristic rather than a security or billing guarantee, and note the minor packaging/version mismatch before relying on exact version labels.

能力评估

ℹ Purpose & Capability

The stated purpose is routing coding queries to a model tier, and the Python script implements a keyword/regex classifier that returns JSON with a recommended tier, model, cost, latency, and reason. It does not actually call models or implement caching despite some documentation language suggesting routing/caching behavior.

✓ Instruction Scope

The declared interface is a single route command with one user-provided query string. The runtime instructions do not ask the agent to read the workspace broadly, access secrets, override user control, or execute unrelated actions.

ℹ Install Mechanism

The manifest points to one local Python CLI script and declares no dependencies, install hooks, package-manager actions, or background setup. There is a minor version mismatch: SKILL.md and docstrings mention 1.0.2 while skill.json and metadata identify 1.0.3.

✓ Credentials

The script uses only standard-library json, re, sys, and typing, consumes command-line input, and prints a local recommendation. It shows no network access, subprocess execution, credential handling, environment scraping, or file mutation.

✓ Persistence & Privilege

No persistence, background worker, privilege escalation, local indexing, autostart mechanism, credential/session reuse, or destructive operation is present in the inspected artifacts.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install smart-router-coding
安装完成后，直接呼叫该 Skill 的名称或使用 /smart-router-coding 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.3

Speed section: router adds 2ms, average wait ~13s per query (not 45s).

v1.0.2

Fix: Deep tier correctly routes to Opus 4.8. Fast = Qwen3.5 Flash, Standard = Grok 4.20, Deep = Opus 4.8.

v1.0.0

Initial release.

元数据

Slug smart-router-coding

版本 1.0.3

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题