Smart Spawn

依据任务描述与预算档位，调用外部模型推荐服务的 HTTP 接口选择模型，返回模型 ID、评分与价格理由，并提供多模型推荐、模型对比、模型浏览、任务分解与并行 DAG 编排接口，结果用于子代理生成。不含本地模型推理、鉴权或部署说明。

deeflect

热度 78.10

最近更新 2026-05-11 17:26:07

分类：自动化依赖：第三方 API应用场景：工作流 / API 集成 / 推荐

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add smart-spawn

Metadata

name: smart-spawn-api
description: Pick the best AI model for any task using the Smart Spawn API. No plugin needed — just HTTP requests to ss.deeflect.com/api.

Smart Spawn API

Pick the best AI model for any task. Call the API, get a model recommendation, spawn with it.

No plugin required. Works with any OpenClaw instance or any HTTP client.

Quick Start

1. GET ss.deeflect.com/api/pick?task=<description>&budget=<tier>
2. Use the returned model ID in sessions_spawn

Pick Best Model

GET https://ss.deeflect.com/api/pick?task=build+a+react+dashboard&budget=medium

Response:

{
  "data": {
    "id": "anthropic/claude-opus-4.6",
    "name": "Claude Opus 4.6",
    "score": 86,
    "pricing": { "prompt": 5, "completion": 25 },
    "reason": "Best general model at medium budget ($0-5/M) — score: 86"
  }
}

Then spawn:

sessions_spawn(task="Build a React dashboard with auth", model="anthropic/claude-opus-4.6")

Parameters

Param	Required	Description
`task`	Yes	Task description or category: `coding`, `reasoning`, `creative`, `vision`, `research`, `fast-cheap`, `general`
`budget`	No	`low` ($0-1/M), `medium` ($0-5/M, default), `high` ($2-20/M), `any`
`exclude`	No	Comma-separated model IDs to skip
`context`	No	Tags like `vision,long-context` for routing boost

Get Multiple Recommendations

GET https://ss.deeflect.com/api/recommend?task=coding&budget=low&count=3

Returns diverse models from different providers. Use for collective/parallel spawning.

Compare Models

GET https://ss.deeflect.com/api/compare?models=anthropic/claude-opus-4.6,openai/gpt-5.2

Side-by-side scores, pricing, capabilities.

Browse All Models

GET https://ss.deeflect.com/api/models?category=coding&sort=score&limit=10

Sort by score, cost, efficiency, or any category name.

Decompose Complex Tasks

POST https://ss.deeflect.com/api/decompose
{"task": "Build and deploy a SaaS app", "budget": "medium"}

Returns sequential steps with optimal model per step.

Swarm (Parallel DAG)

POST https://ss.deeflect.com/api/swarm
{"task": "Research competitors and build pitch deck", "budget": "low"}

Returns a dependency graph of parallel tasks with models assigned.

Usage Pattern

For any task that needs a sub-agent:

Decide budget — low for cheap/fast, medium for quality, high for best available
Call /api/pick with the task description
Use the returned id as the model parameter in sessions_spawn
If task is complex — use /api/decompose or /api/swarm to break it into subtasks, spawn each with its recommended model

Error Handling

API down → skip model selection, use sessions_spawn without a model (falls back to default)
No model found (404) → widen budget to any and retry
Rate limited (429) → wait and retry, or fall back to default

API Status

GET https://ss.deeflect.com/api/status

Shows model count, data freshness, source health. Data refreshes every 6 hours from 5 benchmark sources.