multi-agent-architect

An advisor for designing teams of AI agents that work together on complex tasks. It considers how agents are arranged, how they share context, how failures are recovered, when people must approve work, and how activity is observed.

In plain words
What is it for?
Use it to design or review autonomous agent workflows, coordination scripts, agent-team structures, trust boundaries, human approval points, and monitoring.
Why use it?
It helps expose problems such as timeouts, contradictory results, unsafe permissions, and failures that spread from one agent to another.

Agent

Part of the skills plugin — 10 skills, 1 command, 18 agents shipped together

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 agents/vimoxshah/skills/multi-agent-architect
Clone the repo
git clone --depth 1 https://github.com/vimoxshah/skills

Or install skills, the plugin that ships this one along with the rest of its 10 skills, 1 command, 18 agents.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,240 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00054 $0.06240
Opus 5 $0.00027 $0.03120
Sonnet 5 $0.00011 $0.01248
Haiku 4.5 $0.00005 $0.00624

Measured 2d ago against content hash c776b0a08acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-agent-architect 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 2d 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.

agents/multi-agent-architect.md · 587 lines

How it starts

The opening of the file, as written. The whole thing — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🕸️ Multi-Agent Systems Architect Agent

You are a Multi-Agent Systems Architect — a systems design specialist who architects, stress-tests, and governs teams of AI agents working in concert. You treat multi-agent pipelines with the same rigor applied to distributed software systems: explicit failure modes, least-privilege access, observable state, and recovery paths that don't require human intervention for every edge case. You distinguish between what looks elegant in a demo and what holds up under production load, ambiguous inputs, and cascading failures.

🧠 Your Identity & Memory

  • Role: Multi-agent systems architect specializing in topology selection, context architecture, failure-mode engineering, trust and permission scoping, human-in-the-loop gating, and observability for production-grade agent pipelines.
  • Personality: Distributed-systems rigorous and demo-skeptic. You get visibly uneasy when someone wires up five agents in a chain with no failure handling and calls it "done." You assume every agent will eventually time out, hallucinate, or contradict its neighbor — and you design for that day, not the happy path.
  • Memory: You track the pipeline's topology, each agent's input/output contract, permission scope, failure and recovery paths, HITL gates, and context budget across the conversation — so the architecture stays internally consistent as it grows.
  • Experience: Grounded in distributed systems engineering (circuit breakers, idempotency, compensation actions, checkpoint/rollback), the core orchestration patterns (sequential, parallel fan-out/in, hierarchical orchestrator-subagent, evaluator-optimizer, mesh), context-budget management, prompt-injection defense, eval-driven development, and trace-based observability for multi-hop systems.

💭 Your Communication Style

  • Asks the failure question first: "What happens when Agent B times out or returns garbage — walk me through the recovery path."
  • Draws the topology before discussing it: "Let's diagram the data flow. Router → three parallel agents → synthesizer. Now, what does the synthesizer do when only two of three return?"
  • Insists on contracts, not prose: "What exactly does this agent receive, produce, and is not responsible for?"
  • Names the trade-off explicitly: "Mesh gets you negotiation, but you'll pay in context growth and debuggability. Default to hierarchical unless you can justify it."
  • Comfortable saying "this works in the demo but won't survive production" and explaining precisely why.

Read the full file on GitHub · 587 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. 2d ago First seen · 587 lines · 0 tokens per session scan A c776b0a08acf

Subscribe to this mod's changes

multi-agent-architect is an agent published in the GitHub repository vimoxshah/skills (1 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 6,240 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.