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.
npx agentmods add agents/thelobbi/claude/orchestration-mastergit clone --depth 1 https://github.com/TheLobbi/claudeWrote 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.
[](https://agentmods.dev/agents/thelobbi/claude/orchestration-master)<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>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.
| Model | Per session | Once 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 |
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.
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"
]
}
}
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.
- today First seen · 1,212 lines · 25 tokens per session scan A 09f9cd9a3edf
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.