multi-agent-patterns

multi-agent-patterns is a skill for Claude Code from frank-luongt/faos-skills-marketplace. It costs 0 tokens per session (2,506 once invoked), scanned A, original, Apache-2.0.

A guide to designing systems that divide work among multiple AI agents instead of relying on one agent. It covers coordinating agents, isolating their context, reaching agreement, and handling failures.

In plain words
What is it for?
Use it when designing an AI system with parallel, peer-to-peer, or hierarchical agents. It helps plan task partitioning, coordination, consensus, and failure recovery.
Why use it?
It helps decide when multiple agents will make a task easier and when coordination will add unnecessary complexity. It also provides patterns for managing shared work safely.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the faos-ai-engineer plugin — 14 skills, 8 commands shipped together

Good fit Use it when designing an AI system with parallel, peer-to-peer, or hierarchical agents. It helps plan task partitioning, coordination, consensus, and failure recovery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frank-luongt/faos-skills-marketplace/multi-agent-patterns
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.

Any agent
npx skills add frank-luongt/faos-skills-marketplace --skill multi-agent-patterns
Clone the repo
git clone --depth 1 https://github.com/frank-luongt/faos-skills-marketplace

Made for: Claude Code.

Or install faos-ai-engineer, the plugin that ships this one along with the rest of its 14 skills, 8 commands.

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 multi-agent-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/frank-luongt/faos-skills-marketplace/multi-agent-patterns/github.svg)](https://agentmods.dev/skills/frank-luongt/faos-skills-marketplace/multi-agent-patterns)
Your own site
<a href="https://agentmods.dev/skills/frank-luongt/faos-skills-marketplace/multi-agent-patterns"><img src="https://agentmods.dev/badge/skills/frank-luongt/faos-skills-marketplace/multi-agent-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.

agentmods 80×15 button for multi-agent-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/frank-luongt/faos-skills-marketplace/multi-agent-patterns"><img src="https://agentmods.dev/badge/skills/frank-luongt/faos-skills-marketplace/multi-agent-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.02506
Opus 5 $0.00000 $0.01253
Sonnet 5 $0.00000 $0.00501
Haiku 4.5 $0.00000 $0.00251

Measured 12d ago against content hash 3da4dcdda4d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

multi-agent-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 12d 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.

plugins/faos-ai-engineer/skills/multi-agent-patterns/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: multi-agent-patterns description: Orchestrator, peer-to-peer, and hierarchical multi-agent architectures with context isolation, consensus protocols, and failure mitigation. Use when designing multi-agent systems, partitioning context across agents, or scaling beyond single-agent limits. tags: [multi-agent, orchestration, patterns]

Multi-Agent Architecture Patterns

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.

When to Activate

Activate this skill when:

  • Single-agent context limits constrain task complexity
  • Tasks decompose naturally into parallel subtasks
  • Different subtasks require different tool sets or system prompts
  • Building systems that must handle multiple domains simultaneously
  • Scaling agent capabilities beyond single-context limits
  • Designing production agent systems with multiple specialized components

Core Concepts

Multi-agent systems address single-agent context limitations through distribution. Three dominant patterns exist: supervisor/orchestrator for centralized control, peer-to-peer/swarm for flexible handoffs, and hierarchical for layered abstraction. The critical design principle is context isolation--sub-agents exist primarily to partition context rather than to simulate organizational roles.

Effective multi-agent systems require explicit coordination protocols, consensus mechanisms that avoid sycophancy, and careful attention to failure modes including bottlenecks, divergence, and error propagation.

Detailed Topics

Why Multi-Agent Architectures

The Context Bottleneck Single agents face inherent ceilings in reasoning capability, context management, and tool coordination. As tasks grow more complex, context windows fill with accumulated history, retrieved documents, and tool outputs. Performance degrades according to predictable patterns: the lost-in-middle effect, attention scarcity, and context poisoning.

Read the full file on GitHub · 242 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. 12d ago First seen · 242 lines · 0 tokens per session scan A 3da4dcdda4d0

Subscribe to this mod's changes

multi-agent-patterns is a skill published in the GitHub repository frank-luongt/faos-skills-marketplace (33 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,506 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

task-observer

Monitors task execution for skill improvement opportunities. Use during ANY multi-step task, agentic workflow, or work session where the agent uses tools and produces deliverables. Captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers in post-task…

rebelytics/one-skill-to-rule-them-all · 193 tokens

resume-tailor

Use when the user has a specific job posting and wants to customize their resume, CV, work document, and/or cover letter for that role. Also use when they say "I'm applying to..." or share a job link.

Remotivated/job-hunt-skills · 49 tokens

resume-builder

Use when the user wants to create or update a source work document in resume or CV format, or create a source cover letter from scratch. Triggers on US resumes ("build my resume") and UK/EU-style work CVs ("build my CV", "I need a CV for a UK role", "European CV"). US academic CVs are out of scope. For first-time…

Remotivated/job-hunt-skills · 94 tokens

claim-check

Use when the user wants a final truth pass before submitting a resume, CV, cover letter, LinkedIn section, or application package. Also use when they ask whether a draft contains unsupported, inflated, or hallucinated claims.

Remotivated/job-hunt-skills · 48 tokens

linkedin-optimizer

Use when the user wants to improve their LinkedIn profile, rewrite their headline, about, or experience sections, or audit individual profile fields.

Remotivated/job-hunt-skills · 32 tokens

proof-asset-creator

Use when the user wants to figure out what proof-of-value asset to build — case study, portfolio piece, personal site content, or any artifact that demonstrates their skills to employers. Ideation and scoping only; once an idea is chosen, the user continues in a fresh agent conversation to produce the asset. Triggers…

Remotivated/job-hunt-skills · 89 tokens