Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Swarm Orchestrator

An Agent Skill for Claude that designs, builds, and debugs multi-agent systems. Turn Claude into a swarm architect that creates cost-efficient, deterministic-first agent pipelines.

Built by Swarm Labs USA | GitHub

What It Does

This skill teaches Claude to architect multi-agent swarms:

  • Design agent roles using 8 archetypes (Perceiver, Classifier, Analyzer, Synthesizer, Validator, Resolver, Planner, Executor)
  • Orchestrate agents with 5 communication patterns (Sequential Chalkboard, Fan-Out/Fan-In, Pipeline with Gates, Adversarial Pair, Iterative Refinement)
  • Optimize costs with the deterministic-first cascade — try rules before LLMs, start smallest
  • Debug multi-agent failures with chalkboard trace analysis
  • Validate pipeline definitions for cycles, schema mismatches, and budget violations
  • Simulate pipeline execution to verify data flow before building

Why This Exists

Anthropic shipped agent teams in Opus 4.6. 123+ plugins in the marketplace. Zero of them teach how to design, orchestrate, or debug multi-agent systems.

This skill fills that gap with production-tested patterns. The architectures and patterns in this skill are extracted from real systems — see Production Validation below.

Quick Start

Install in Claude Code

# From GitHub
/plugin install github:michaelwinczuk/swarm-orchestrator

Basic Usage

"Design an agent swarm that monitors social media mentions,
 classifies sentiment, and drafts responses for negative ones."

"My pipeline has 12 agents costing $2/run. Help me optimize."

"Agent 3 and Agent 5 produce contradictory outputs. Debug this."

"Validate this pipeline definition for issues."

Core Concepts

8 Agent Archetypes

Archetype Role Typically Deterministic?
Perceiver Extract structure from raw data Always
Classifier Route and categorize Almost always
Analyzer Deep domain analysis Sometimes
Synthesizer Combine multiple outputs Rarely
Validator Quality gates Always
Resolver Handle conflicts Sometimes
Planner Decompose goals Sometimes
Executor Carry out actions Always

5 Communication Patterns

  1. Sequential Chalkboard — Agents execute in order, read/write shared state. Default choice.
  2. Fan-Out / Fan-In — Parallel independent analyses merged by a synthesizer.
  3. Pipeline with Gates — Sequential with quality checkpoints that can halt/redirect.
  4. Adversarial Pair — Advocate + Critic reviewed by a Resolver. For high-stakes decisions.
  5. Iterative Refinement — Generate + validate loop with retry limits.

Deterministic-First Cascade

Rules/Code ($0) → Local Model ($0) → API Model ($0.02) → Frontier ($0.10+)

Always try the cheapest approach first. Most swarm operations don't need LLMs.

Chalkboard Protocol

Shared state that agents read from and write to:

  • Agents can READ any previous agent's output
  • Agents can only WRITE to their own section
  • Each output is immutable once written
  • The chalkboard is the single source of truth and your primary debugging tool

Production Validation

These patterns are extracted from systems built with the Swarm Labs ecosystem. Measured results from deployed swarms:

Swarm Agents Deterministic Rate Latency Cost/Run
Think Tank (research) 10 69 clusters, 77 KGs ~2s ~$0.02
Trading (ETH/BTC/USDC) 5 Oracle + rules-first 46ms $0.00
SBIR Defense (3 swarms) 12 each 95%+ deterministic 46ms $0.00
Math Swarm 6 100% (SymPy) 1.9ms $0.00
Swarm Claw (orchestrator) 10 swarms 4-layer cascade <1ms routing $0.00

Math Swarm — Verified Benchmark

The Math Swarm is the strongest proof of the deterministic-first principle. Full results and code:

System Math Accuracy Speed
Math Swarm (6-agent chalkboard) 1,079/1,079 (100%) 1.9ms
Qwen2.5-3B (alone) 52/94 (55%) 200ms
Qwen2.5-7B (alone) 72/94 (77%) 300ms
Qwen2.5-32B (alone) 87/94 (93%) 2,600ms

A 3B model + deterministic swarm outperforms a 32B model alone. The architecture matters more than the model size.

Project Structure

swarm-orchestrator/
├── SKILL.md                        # Core skill (loaded by Claude)
├── README.md                       # This file
├── LICENSE                         # Apache 2.0
├── scripts/
│   ├── validate_pipeline.py        # Pipeline definition validator
│   └── simulate.py                 # Chalkboard simulation engine
├── references/
│   ├── archetypes.md               # 8 agent archetypes with design rules
│   └── examples.md                 # 4 complete swarm designs + debugging example
└── evals/
    └── evals.json                  # 5 test cases

Swarm Labs Ecosystem

Project What It Does Status
Math Swarm Zero-hallucination computation. 1,079 tests, 100%, 12 categories. 1,079 tests passing
Knowledge Graph Reasoning 77+ KGs, adversarial validation, deterministic reasoning. 77 graphs deployed
PRISM Reliability primitives — VotingMesh, Sentinel, checkpoint/replay. 95 tests passing
Bastion Safety kernel — consensus, verification, SHA-256 audit trails. Rust + Tokio
Swarm Labs USA Autonomous AI systems for government. Active

License

Apache 2.0 — See LICENSE for details.


Built by Michael Winczuk at Swarm Labs USA

About

Agent Skill for Claude: Design, build, and debug multi-agent swarms. 8 archetypes, 5 patterns, deterministic-first cascade, chalkboard protocol.

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages