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.
npx skills add j4flmao/agent-skills --skill multi-agent-systemsgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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.
[](https://agentmods.dev/skills/j4flmao/agent-skills/multi-agent-systems)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/multi-agent-systems"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/multi-agent-systems/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.
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/multi-agent-systems"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/multi-agent-systems.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00468 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
multi-agent-systems 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Systems (MAS)
1. Skill Context
Focus: Designing systems where multiple autonomous AI agents collaborate, argue, or sequentialize tasks to solve complex problems that a single LLM prompt cannot handle. Triggers: multi-agent, swarm, langgraph, autogen, orchestration, state-machine.
2. The Multi-Agent Philosophy
A single LLM acting as a "God Agent" with 50 tools will eventually fail. The context window becomes polluted, and the model forgets its original objective.
Multi-Agent Systems (MAS) solve this by specializing. You create a CoderAgent, a ReviewerAgent, and a QA_Agent, each with distinct system prompts and narrowly scoped tools.
3. Orchestration Architectures
A. State Graphs (Deterministic Routing)
Frameworks: LangGraph The system is explicitly modeled as a Directed Cyclic Graph (DCG).
- Nodes: Represent the Agents (or python functions).
- Edges: Represent the conditional logic routing the flow from one agent to another.
- Pros: Highly predictable, easy to debug, guarantees the workflow will eventually terminate or follow business rules.
- Cons: Rigid. If the user asks for something outside the predefined graph flow, the system cannot adapt dynamically.
B. Swarm Intelligence (Dynamic Orchestration)
Frameworks: AutoGen, OpenAI Swarm Agents act autonomously without a hardcoded graph.
- A user submits a complex request.
- The Manager Agent broadcasts the request to a pool of specialized agents.
- Agents dynamically volunteer to handle parts of the task, pass messages directly to each other, and decide organically when the task is complete.
- Pros: Incredibly flexible. Can solve novel problems the developer never anticipated.
- Cons: Prone to infinite conversational loops ("No, you do it", "No, you do it") and hallucinations. Extremely difficult to debug in an enterprise production environment.
4. References
references/communication-protocols.md— How agents share data (Blackboard vs. Actor Model).references/human-in-the-loop.md— Pausing agent execution for human approval.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 33 lines · 0 tokens per session scan A f24c9a18d434
multi-agent-systems is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 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 2026-09-05.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…