Skip to content
TakoAPI
Back to skills

agent-swarm

by runeweaverstudios

Web & Frontend Development
912Downloads reported by clawskills.sh
1Stars
1Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

IMPORTANT: OpenRouter is required.

Description

What This Skill Does

Routes incoming tasks to the appropriate AI model via OpenRouter, then delegates execution to a sub-agent through sessions_spawn. Tasks are classified into eight tiers, including code, reasoning, creative, and vision, with configurable primary and fallback models per tier. The orchestrator never answers tasks directly.

Instead of running every task on one expensive model, it classifies work into tiers and selects the cheapest capable model per task, cutting both cost and latency.

When to Use It

  • Routing a code debugging request to a dedicated coding model
  • Splitting a mixed task into parallel sub-agents for faster completion
  • Sending screenshot analysis to a vision-capable model automatically
  • Using a cheap fast model for simple status checks to reduce cost
  • Delegating research queries to a search-optimized model

Example Workflow

INPUT

User asks: fix the null pointer bug in auth.py and write release notes

AGENT
  1. 1

    Router receives the task and detects two distinct subtasks

  2. 2

    Runs router.py with --multi flag to generate separate spawn configs for CODE and CREATIVE tiers

  3. 3

    Calls sessions_spawn with the CODE-tier model for the bug fix

  4. 4

    Calls sessions_spawn with the CREATIVE-tier model for the release notes

  5. 5

    Returns combined results from both sub-agents to the user

OUTPUT

Bug fix applied by code model, release notes written by creative model, both results returned together

Requirements

  • OpenRouter API key configured in OpenClaw platform settings

Installation

clawhub install runeweaverstudios/agent-swarm

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links