Multi Agent Topology

Use when the user asks whether to use multiple agents, supervisor-worker, agent hierarchy, pipeline of agents, handoffs or a critic/debate setup. Produces a topology diagram, role table with least-privilege tools, typed edge contracts and round caps. Not for framework runtime and checkpointing (use ai-multi-agent-systems) or R&D swarms (use swarm-architectures).

45 stars 6 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill multi-agent-topology
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/ai/ai-agents/multi-agent-topology ~/.claude/skills/multi-agent-topology

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Multi-Agent Topology

## Purpose
A topology is the graph of who talks to whom, who decides, and what data crosses each edge. Adding agents adds latency, cost, and failure points, so the first question is whether more than one agent is needed at all. When it is, pick the simplest topology that gives each agent a narrow role, a small tool set, and a typed contract with its neighbours.

## Agent Protocol

### Trigger
"supervisor", "worker agents", "agent hierarchy", "agent pipeline", "handoff", "debate", "critic agent", "should this be multi-agent".

### Input Context
- Task decomposition: subtasks, dependencies, and which need different tools or permissions.
- Tool count and context size if done by one agent.
- Latency/cost budget; need for parallelism.
- Where human approval is required.

### Output Artifact
Topology diagram (Mermaid), role table, edge contracts (typed messages), termination and failure rules.

### Response Format
```
Topology: {single|pipeline|supervisor-worker|hierarchical|handoff|debate}
Why multi-agent: {tool split | context isolation | parallelism | separation of duties}
Roles: {agent: responsibility, tools, can_write?}
Edges: {from -> to: message schema}
Termination: {condition}; max rounds={n}
Failure: {retry | reroute | escalate}
```

### Completion Criteria
- [ ] Single-agent baseline considered and rejected with a reason.
Read the full skill on GitHub

Details

Skill name
multi-agent-topology
Path
skills/ai/ai-agents/multi-agent-topology/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Multi Agent Topology skill do?

Use when the user asks whether to use multiple agents, supervisor-worker, agent hierarchy, pipeline of agents, handoffs or a critic/debate setup. Produces a topology diagram, role table with least-privilege tools, typed edge contracts and round caps. Not for framework runtime and checkpointing (use ai-multi-agent-systems) or R&D swarms (use swarm-architectures).

How do I install the Multi Agent Topology skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill multi-agent-topology. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Multi Agent Topology popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Neuromorphic Computing

45

j4flmao/agent-skills

Use this skill when the user says 'neuromorphic', 'spiking neural network', 'SNN', 'LIF neuron', 'Loihi', 'SpiNNaker', 'event camera', 'surrogate gradient', 'snnTorch', 'Lava framework', 'memristor in-memory computing'. Explains event-driven spiking computation, neuron models, training methods (surrogate gradients, ANN-to-SNN conversion), hardware platforms, and when neuromorphic approaches are worth prototyping. Do NOT use for: conventional GPU deep learning (ml/deep-learning), edge inference on MCUs with standard networks (embedded-systems/edge-ai), or quantum hardware (quantum-computing/*).

AI, LLMs & Agents

LLM RAG Retrieval Internals

45

j4flmao/agent-skills

Use when the user asks to build a RAG pipeline over documentation, tune HNSW (M, efSearch) or IVF-PQ (nprobe), hybrid dense + BM25 search, reciprocal rank fusion, cross-encoder reranking, Self-RAG or DSPy. Produces index choice and parameters, a hybrid+rerank pipeline and recall evals. Not for query rewriting and RAG prompts (use prompt-rag-query-design).

AI, LLMs & Agents

Paged Attention

45

j4flmao/agent-skills

Use when the user asks about PagedAttention, KV cache size, vLLM OOM, gpu-memory-utilization, max-num-seqs, prefix caching, continuous batching or preemption. Produces a KV-cache capacity estimate and serving-engine flags for vLLM, SGLang or TensorRT-LLM. Not for the attention kernel itself (use flash-attention) or general model serving (use ml-model-serving).

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.