building-multiagent-systems SKILL.md skillA

building-multiagent-systems from 2389-research/building-multiagent-systems is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add 2389-research/building-multiagent-systems/building-multiagent-systems@git:20260706.3b03b92

Pins git:20260706.3b03b92 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
2389-research/building-multiagent-systems
Path
skills/SKILL.md
Versions recorded
5
Latest version
git:20260706.3b03b92, committed Jul 6, 2026
First version recorded
Dec 5, 2025
Size
8,159 bytes
Repository stars
8
License
MIT

Provides architecture patterns for multi-agent systems — orchestrator/sub-agent design, coordination patterns including MAKER voting, lifecycle management, and production hardening. Use when designing or implementing systems with multiple AI agents: fan-out/fan-in, pipelines, recursive delegation, work-stealing queues, map-reduce, peer councils, zero-error MAKER voting, cascading stop, orphan detection, cost tracking, or checkpointing.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Building Multi-Agent, Tool-Using Agentic Systems

## Overview

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.

## Discovery Questions (Required)

Before architecting any system, ask these six mandatory questions:

1. **Starting Point** - Greenfield, adding to existing system, or fixing current implementation?
2. **Primary Use Case** - Parallel work, sequential pipeline, recursive delegation, peer collaboration, work queues, or other?
3. **Scale Expectations** - Small (2-5 agents), medium (10-50), or large (100+)?
4. **State Requirements** - Stateless runs, session-based, or persistent across crashes?
5. **Tool Coordination** - Independent agents, shared read-only resources, write coordination, or rate-limited APIs?
6. **Existing Constraints** - Language, framework, performance needs, compliance requirements?

## Foundational Architecture

### Four-Layer Stack

Every agent follows the four-layer architecture for testability, safety, and modularity:

| Layer | Name | Responsibility |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add 2389-research/building-multiagent-systems/building-multiagent-systems@sha256:d6dcc6212f4699f8

The line at the top of this page pins the label git:20260706.3b03b92, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_upuan6s35wjqygoh.svg)](https://markdownregistry.com/a/art_upuan6s35wjqygoh)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Dec 5, 2025 and Jul 6, 2026, about one every 53 days.

versioncommittedcommitsizeaudit
git:20260706.3b03b92 latest2026-07-06 3b03b92 8,159 BA view · diff
git:20260108.6b0a5112026-01-08 6b0a511 8,873 BA view · diff
git:20251207.ee779ba2025-12-07 ee779ba 24,996 BA view · diff
git:20251207.9ad74952025-12-07 9ad7495 19,100 BA view · diff
git:20251205.4ed241b2025-12-05 4ed241b 6,617 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8159 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

2389-research/building-multiagent-systems · 8 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_upuan6s35wjqygoh
GET https://markdownregistry.com/api/v1/resolve?ref=2389-research/building-multiagent-systems/building-multiagent-systems
GET https://markdownregistry.com/api/v1/blob/d6dcc6212f4699f8422b213897c9557432b6c0cbbc68c25e6bce05f83102321e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from 2389-research/building-multiagent-systems

CLAUDE.md CLAUDE.md file
2389-research/building-multiagent-systems · CLAUDE.md
git:20260706.3b03b92 · audit A · 8 stars

Every file in 2389-research/building-multiagent-systems

Other files named building-multiagent-systems

building-multiagent-systems SKILL.md skill
aiskillstore/marketplace · skills/2389-research/building-multiagent-systems/SKILL.md · This skill should be used when designing or implementing systems with multiple AI agents that coordinate to accomplish…
git:20260113.222b7de · audit A · 471 stars

Browse by kind, by grade A, or by owner.