Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/selvarajmurugesan90/ops-engineering-skillsnpx agentmods add skills/selvarajmurugesan90/ops-engineering-skills/crewai-and-autogen-multi-agent-frameworksWrote 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/selvarajmurugesan90/ops-engineering-skills/crewai-and-autogen-multi-agent-frameworks)<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/crewai-and-autogen-multi-agent-frameworks"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/crewai-and-autogen-multi-agent-frameworks/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/selvarajmurugesan90/ops-engineering-skills/crewai-and-autogen-multi-agent-frameworks"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/crewai-and-autogen-multi-agent-frameworks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.04340 |
| Opus 5 | $0.00060 | $0.02170 |
| Sonnet 5 | $0.00024 | $0.00868 |
| Haiku 4.5 | $0.00012 | $0.00434 |
Grade A, and why
crewai-and-autogen-multi-agent-frameworks 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.
How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrewAI and AutoGen Multi-Agent Frameworks
Purpose
multi-agent-orchestration describes
the generic topologies (supervisor/worker, pipeline, parallel/aggregation,
critic/debate) that justify splitting a task across multiple agents. CrewAI
and AutoGen are two concrete, higher-level frameworks that implement those
topologies with an opinionated, role-centric abstraction rather than
requiring you to wire message-passing and state by hand. CrewAI models a
multi-agent system as a crew of role-scoped agents, each assigned one
or more tasks, executed under a process (sequential — tasks run in
a fixed order, each consuming prior tasks' output; or hierarchical — a
manager agent delegates and reviews) — it is closest to the pipeline and
supervisor/worker topologies, expressed declaratively. AutoGen models a
multi-agent system as a set of conversable agents that exchange
messages in a shared conversation (a GroupChat with a chat manager
choosing the next speaker, or direct two-agent conversations), with a
distinct built-in role for a UserProxyAgent that can execute code and
optionally pause for human input — it is closest to the critic/debate and
supervisor/worker topologies, expressed as a conversation rather than a
fixed pipeline. Both frameworks trade some of LangGraph's low-level control
(explicit state typing, arbitrary cyclical graphs, durable checkpointing)
for faster time-to-first-working-crew when the task genuinely fits a
role-based mental model. This skill covers configuring each framework
correctly and choosing between them (and against LangGraph) for a given
task — it does not repeat the underlying "should this be multi-agent at
all" justification, which lives in
multi-agent-orchestration.
When to use
- The task is naturally described as a set of named roles collaborating (e.g. "a researcher, a writer, and an editor") and a declarative, role-first framework fits better than hand-wiring a graph.
- Building or reviewing a CrewAI crew's
agents.yaml/tasks.yaml(or equivalent Python config) and choosingsequentialvs.hierarchicalprocess. - Building or reviewing an AutoGen
GroupChat— choosing the speaker- selection strategy, configuring aUserProxyAgent's code-execution and human-input behavior. - Deciding between CrewAI, AutoGen, LangGraph (langchain-and-langgraph-agent-orchestration), and a hand-rolled orchestrator for a specific multi-agent task.
- An existing CrewAI crew or AutoGen group chat loops, has agents talking past each other, or produces redundant work, and needs debugging.
- Migrating a multi-agent prototype built in one of these frameworks toward (or away from) a lower-level graph-based implementation as requirements outgrow the framework's abstraction.
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.
- 12d ago First seen · 375 lines · 121 tokens per session scan A 4651774657c3
crewai-and-autogen-multi-agent-frameworks is a skill published in the GitHub repository selvarajmurugesan90/ops-engineering-skills (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 121 tokens to every session and 4,340 once invoked, about $0.0006 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.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…