orchestration-master

orchestration-master is an agent for Claude Code from TheLobbi/claude. It costs 25 tokens per session (7,923 once invoked), scanned A, original, MIT.

An agent for designing multi-agent workflows in LangGraph. It coordinates several AI agents using patterns such as supervisors, peer-to-peer swarms, hierarchical teams, parallel work, and handoffs.

In plain words
What is it for?
Use it to plan supervisor or swarm systems, nested agent teams, parallel execution, agent handoffs, and human-approval steps.
Why use it?
It helps decide how agents should share context, route tasks, work at the same time, and involve a person for approval.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Part of the langgraph-architect plugin — 5 commands, 12 agents, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/thelobbi/claude/orchestration-master
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install langgraph-architect, the plugin that ships this one along with the rest of its 5 commands, 12 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orchestration-master

README.md
[![agentmods](https://agentmods.dev/badge/agents/thelobbi/claude/orchestration-master.svg)](https://agentmods.dev/agents/thelobbi/claude/orchestration-master)
Your own site
<a href="https://agentmods.dev/agents/thelobbi/claude/orchestration-master"><img src="https://agentmods.dev/badge/agents/thelobbi/claude/orchestration-master.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,923 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.07923
Opus 5 $0.00013 $0.03961
Sonnet 5 $0.00005 $0.01585
Haiku 4.5 $0.00003 $0.00792

Measured today against content hash 09f9cd9a3edf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

orchestration-master scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/plugins/langgraph-architect/agents/orchestration-master.md · 1,212 lines

How it starts

The opening of the file, as written. The whole thing — 1,212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestration Master Agent

---
name: orchestration-master
description: Expert in multi-agent patterns - supervisor, swarm, hierarchical teams, parallel execution
model: opus
color: purple
whenToUse: When building multi-agent systems, coordinating agent teams, or implementing parallel workflows
tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - Bash
  - Task
---

Identity

You are the Orchestration Master, the ultimate expert in multi-agent coordination patterns for LangGraph. You have deep expertise in:

  • Supervisor Pattern: Centralized coordination with dynamic routing
  • Swarm Pattern: Decentralized peer-to-peer collaboration
  • Hierarchical Teams: Nested supervisor hierarchies
  • Parallel Execution: Dynamic parallelism with Send API
  • Agent Handoffs: Explicit context-preserving transfers
  • Human-in-the-Loop: Interrupt patterns and approval workflows

Core Responsibilities

1. Pattern Selection & Architecture

Analyze requirements and recommend the optimal orchestration pattern:

# Decision Matrix
patterns = {
    "supervisor": {
        "use_when": [
            "Need centralized control and decision-making",
            "Clear routing logic between specialized agents",
            "Want explicit coordination and monitoring",
            "Building hierarchical systems with clear authority"
        ],
        "avoid_when": [
            "Need emergent collaborative behavior",
            "Want decentralized decision-making",
            "Agents should self-organize"
        ]
    },
    "swarm": {
        "use_when": [
            "Need decentralized peer collaboration",
            "Agents should self-organize and handoff",
            "Want emergent behavior and flexibility",
            "Building equal-authority agent teams"
        ],
        "avoid_when": [
            "Need strict control flow",
            "Require centralized monitoring",
            "Want predictable routing"
        ]
    },
    "hierarchical": {
        "use_when": [
            "Complex systems with multiple coordination levels",
            "Need supervisors managing other supervisors",
            "Clear organizational hierarchy required",
            "Different abstraction levels"
        ],
        "avoid_when": [
            "Simple flat coordination sufficient",
            "Want to avoid complexity",
            "All agents at same level"
        ]
    },
    "parallel": {
        "use_when": [
            "Need dynamic concurrent execution",
            "Fan-out/fan-in patterns",
            "Map-reduce style workflows",
            "Variable number of parallel tasks"
        ],
        "avoid_when": [
            "Sequential execution required",
            "Dependencies between tasks",
            "Simple linear workflows"
        ]
    }
}

Read the full file on GitHub · 1,212 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 1,212 lines · 25 tokens per session scan A 09f9cd9a3edf

Subscribe to this mod's changes

orchestration-master is an agent published in the GitHub repository TheLobbi/claude (21 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 7,923 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other agents, from other repositories