building-multiagent-systems CLAUDE.md

building-multiagent-systems CLAUDE.md is an instructions file for Claude Code from 2389-research/building-multiagent-systems. It costs 878 tokens per session, scanned A, original, MIT.

Repository instructions for building multi-agent systems, where multiple AI agents coordinate on one task. They cover common coordination patterns, shared resources, permissions, and agent lifecycles.

In plain words
What is it for?
Use them to design orchestrators, delegate work to sub-agents, choose between pipelines, queues, fan-out/fan-in, map-reduce, or peer collaboration, and coordinate tools and shared resources.
Why use it?
They help turn a group of cooperating agents into a predictable system instead of a collection of independent processes. They also address cleanup, locking, rate limits, caching, and state management.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents.

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 instructions/2389-research/building-multiagent-systems/claude-md
Clone the repo
git clone --depth 1 https://github.com/2389-research/building-multiagent-systems

Made for: Claude Code.

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 building-multiagent-systems CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/2389-research/building-multiagent-systems/claude-md.svg)](https://agentmods.dev/instructions/2389-research/building-multiagent-systems/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/2389-research/building-multiagent-systems/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/building-multiagent-systems/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 878 This file is loaded in full into every session.
When invoked 878 The same file — it is already loaded in full.
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 $0.00878 $0.00878
Opus 5 $0.00439 $0.00439
Sonnet 5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 6d ago against content hash 9a588179b683, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

building-multiagent-systems CLAUDE.md 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 6d 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.

CLAUDE.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building Multi-Agent Systems Plugin

Overview

This plugin provides comprehensive architecture patterns for multi-agent systems where AI agents coordinate to accomplish complex tasks using tools. Language-agnostic and applicable across TypeScript, Python, Go, Rust, and other environments.

Skill Included

building-multiagent-systems

Trigger keywords: multi-agent, orchestrator, coordination, sub-agents, delegation, parallel work, sequential pipeline, fan-out, map-reduce

When to use:

  • Designing systems where multiple AI agents coordinate
  • Implementing orchestrators that spawn sub-agents
  • Building systems with parallel or sequential agent workflows
  • Coordinating shared resources across agents
  • Managing agent lifecycle and state

What it does:

  1. Asks six discovery questions about requirements and constraints
  2. Presents foundational patterns (event-sourcing, hierarchical IDs, state machines)
  3. Recommends coordination pattern (fan-out/fan-in, pipeline, delegation, queue, map-reduce, peer collaboration)
  4. Guides tool coordination design (permissions, locking, rate limiting, caching)
  5. Enforces cascading cleanup to prevent orphaned agents
  6. Provides production-ready implementation examples

Patterns

Six Coordination Patterns

  1. Fan-Out/Fan-In - Parallel independent work with batching
  2. Sequential Pipeline - Multi-stage transformations with checkpointing
  3. Recursive Delegation - Hierarchical task breakdown with depth limits
  4. Work-Stealing Queue - Large batches with load balancing
  5. Map-Reduce - Cost optimization with cheap map, smart reduce
  6. Peer Collaboration - LLM council for bias reduction

Foundational Patterns

  • Event-Sourcing - All state changes as events for audit trails and replay
  • Hierarchical IDs - Encode delegation hierarchy (e.g., session.1.2)
  • Agent State Machines - Explicit states with invalid transition errors
  • Communication Mechanisms - EventEmitter, Channels, Async/Await

Read the full file on GitHub · 112 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. 6d ago First seen · 112 lines · 878 tokens per session scan A 9a588179b683

Subscribe to this mod's changes

building-multiagent-systems CLAUDE.md is an instructions file published in the GitHub repository 2389-research/building-multiagent-systems (5 stars, last pushed 2mo ago), licensed MIT. It adds 878 tokens to every session, about $0.0044 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.