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 agentmods add skills/ag2ai/ag2-claude-plugins/group-chat-auto-patternnpx skills add ag2ai/ag2-claude-plugins --skill group-chat-auto-patterngit clone --depth 1 https://github.com/ag2ai/ag2-claude-pluginsWrote 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/ag2ai/ag2-claude-plugins/group-chat-auto-pattern)<a href="https://agentmods.dev/skills/ag2ai/ag2-claude-plugins/group-chat-auto-pattern"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-claude-plugins/group-chat-auto-pattern.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00628 |
| Opus 5 | $0.00021 | $0.00314 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
group-chat-auto-pattern 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 5d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are creating an AG2 group chat workflow using AutoPattern -- fully LLM-driven agent selection with no handoffs.
Instructions
-
Ask the user for:
- What task the group needs to solve
- How many agents and their specializations
- Maximum conversation rounds (default: 15)
-
Create the group chat following this pattern:
AutoPattern Group Chat
from autogen import ConversableAgent, UserProxyAgent, LLMConfig
from autogen.agentchat import run_group_chat
from autogen.agentchat.group.patterns import AutoPattern
llm_config = LLMConfig({"api_type": "anthropic", "model": "claude-sonnet-4-6"})
# Each agent MUST have a description -- used by Group Chat Manager for routing
agent_a = ConversableAgent(
name="agent_a",
system_message="Your role instructions here...",
description="When to select this agent -- used for routing decisions.",
llm_config=llm_config,
)
agent_b = ConversableAgent(
name="agent_b",
system_message="Your role instructions here...",
description="When to select this agent -- used for routing decisions.",
llm_config=llm_config,
)
user = UserProxyAgent(
name="user",
code_execution_config=False,
)
# AutoPattern -- no handoffs, LLM picks next agent based on descriptions
pattern = AutoPattern(
initial_agent=agent_a,
agents=[agent_a, agent_b],
group_manager_args={"llm_config": llm_config},
user_agent=user,
)
result = run_group_chat(
pattern=pattern,
messages="Your task here",
max_rounds=15,
)
result.process()
print(result.summary)
Key Rules
- AutoPattern requires no handoffs -- the Group Chat Manager decides routing based on agent
descriptionfields - Every agent MUST have a distinct
description(not justsystem_message) -- this is what the Group Chat Manager uses for selection - The
system_messagetells the agent how to behave; thedescriptiontells the manager when to select the agent - Use
LLMConfig({...})-- NOT a raw dict like{"model": "..."} - Use
run_group_chatwith a pattern -- NOTinitiate_chatorGroupChatManager - Keep
max_roundsreasonable (10-20)
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.
- 5d ago First seen · 81 lines · 42 tokens per session scan A b85e96c13589
group-chat-auto-pattern is a skill published in the GitHub repository ag2ai/ag2-claude-plugins (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 628 once invoked, about $0.0002 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.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…