multi-agent-topology

multi-agent-topology is a skill for Claude Code, Codex from j4flmao/agent-skills. It costs 18 tokens per session (782 once invoked), scanned A, original, MIT.

A guide to arranging several AI agents and defining how they share tasks, information, and authority. It describes structures such as a supervisor assigning work to specialized agents and sequential agent pipelines.

In plain words
What is it for?
Use it to design supervisor-worker systems, linear processing chains, and other multi-agent interaction structures.
Why use it?
It helps you choose how agents should coordinate and where decisions, routing, and possible failure points belong.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design supervisor-worker systems, linear processing chains, and other multi-agent interaction structures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/j4flmao/agent-skills/multi-agent-topology
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 j4flmao/agent-skills --skill multi-agent-topology
Clone the repo
git clone --depth 1 https://github.com/j4flmao/agent-skills

Made for: Claude Code, Codex.

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-topology

README.md
[![agentmods](https://agentmods.dev/badge/skills/j4flmao/agent-skills/multi-agent-topology/github.svg)](https://agentmods.dev/skills/j4flmao/agent-skills/multi-agent-topology)
Your own site
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/multi-agent-topology"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/multi-agent-topology/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-topology

Your own site · 80×15
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/multi-agent-topology"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/multi-agent-topology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 782 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00018 $0.00782
Opus 5 $0.00009 $0.00391
Sonnet 5 $0.00004 $0.00156
Haiku 4.5 $0.00002 $0.00078

Measured 13d ago against content hash deda9caa3ff2, 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-topology 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 13d 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.

skills/ai/ai-agents/multi-agent-topology/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Topology: The Societal Structures of AI

At the ontological core of multi-agent systems lies the concept of Topology: the formalized graph of interaction, authority, and information flow between autonomous nodes (agents). A single agent possesses limited cognitive aperture; a topology binds multiple cognitive units into a singular, macro-intelligent organism. To master multi-agent design is to architect the sociology of synthetic minds.

These structures transcend frameworks. They are the mathematical and sociological primitives of distributed intelligence.

I. The Primitives of Topology

  1. Supervisor-Worker (Hierarchical) The classical delegation paradigm. A central orchestrator (Supervisor) decompose tasks, dispatches sub-routines to specialized nodes (Workers), and synthesizes the outputs. This structure minimizes cognitive overload on individual nodes but risks centralizing points of failure. Axiom of Delegation: The Supervisor must not compute the task; it computes the routing and aggregation of the task.

  2. Sequential Pipelines (Linear Autonomy) A deterministic chain of cognitive processing. Agent $A_n$ transforms state $S_n$ into $S_{n+1}$, which serves as the immutable input for Agent $A_{n+1}$. This topology enforces extreme strictness and narrow-focus optimization. Axiom of Linearity: Information flows unilaterally. Entropy decreases at each node as raw data is refined into structured conclusions.

  3. Debate & Reflection Swarms (Polyphonic Convergence) The dialectical approach to truth-seeking. Multiple nodes are instantiated with adversarial or orthogonal personas, iterating on a shared context until a consensus metric is achieved or a maximum reflection depth is reached. Axiom of Divergence: Epistemic certainty is achieved not by a single genius node, but through the cross-examination of multiple probabilistic priors.

II. Topological State Flow

1. Hierarchical Topology

%%{init: {"theme": "default", "flowchart": {"useMaxWidth": true}}}%%
flowchart TD
    S((Supervisor)) -->|Decomposes| W1(Worker: Analyze)
    S -->|Decomposes| W2(Worker: Synthesize)
    W1 -.->|State Refinement| S
    W2 -.->|State Refinement| S

Read the full file on GitHub · 59 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. 13d ago First seen · 59 lines · 18 tokens per session scan A deda9caa3ff2

Subscribe to this mod's changes

multi-agent-topology is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 782 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens