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 skills add mickeyyaya/refactoring-skills --skill agent-orchestration-patternsgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWrote 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/skills/mickeyyaya/refactoring-skills/agent-orchestration-patterns)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/agent-orchestration-patterns"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/agent-orchestration-patterns/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/agent-orchestration-patterns"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/agent-orchestration-patterns.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00067 | $0.04453 |
| Opus 5 | $0.00034 | $0.02227 |
| Sonnet 5 | $0.00013 | $0.00891 |
| Haiku 4.5 | $0.00007 | $0.00445 |
Grade A, and why
agent-orchestration-patterns 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 9d ago.
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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Orchestration Patterns
Overview
Single agents hit hard limits: finite context windows, sequential throughput, and single-model reliability. Multi-agent systems unlock parallel execution, specialization, and fault isolation — but introduce new failure modes: coordination overhead, context duplication, inconsistent shared state, and cascading failures.
Use this guide when designing or reviewing systems where multiple AI agents coordinate, share work, or communicate results — whether agents are LLM-backed workers, rule-based processors, or hybrid pipelines. Applies to any system with a planner or orchestrator dispatching work to sub-agents.
Quick Reference
| Pattern | Topology | When to Use | Key Risk |
|---|---|---|---|
| Hierarchical Orchestrator | Orchestrator → N workers | Large tasks with clear decomposition | Orchestrator bottleneck; single point of failure |
| Flat Peer-to-Peer | Agents communicate directly | Negotiation, consensus, emergent behavior | Message explosion; hard to debug |
| Pipeline (Sequential) | A → B → C | Strict ordering, each stage transforms output | No parallelism; one failure halts all |
| Fan-Out / Fan-In | 1 → N parallel → 1 aggregator | Independent sub-tasks, time-sensitive results | Partial failures; aggregation complexity |
| Hybrid | Orchestrator + pipelines + peer links | Real production systems | All of the above |
| Supervisor Pattern | Monitor + restart agents | Long-running agents with known failure modes | Infinite restart loops |
Orchestration Topologies
Hierarchical (Orchestrator + Workers)
The planner or orchestrator decomposes a task and dispatches sub-tasks to specialized worker agents. Workers return results; orchestrator aggregates.
┌─────────────┐
│ Orchestrator│
└──────┬──────┘
┌──────────┼──────────┐
▼ ▼ ▼
┌───────┐ ┌───────┐ ┌───────┐
│Worker │ │Worker │ │Worker │
│ (A) │ │ (B) │ │ (C) │
└───────┘ └───────┘ └───────┘
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.
- 9d ago First seen · 451 lines · 67 tokens per session scan A 0658649a80d6
agent-orchestration-patterns is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 4,453 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…