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 ag2ai/ag2-skills --skill ag2-network-discussiongit clone --depth 1 https://github.com/ag2ai/ag2-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/ag2ai/ag2-skills/ag2-network-discussion)<a href="https://agentmods.dev/skills/ag2ai/ag2-skills/ag2-network-discussion"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-skills/ag2-network-discussion/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/ag2ai/ag2-skills/ag2-network-discussion"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-skills/ag2-network-discussion.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 | $0.00194 | $0.03151 |
| Opus 5 | $0.00097 | $0.01576 |
| Sonnet 5 | $0.00039 | $0.00630 |
| Haiku 4.5 | $0.00019 | $0.00315 |
Grade A, and why
ag2-network-discussion 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 11d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AG2 Network — Discussion Adapter
discussion is an N-party round-robin channel. Participants speak in a fixed order, cycling indefinitely until you close it. The adapter enforces "wait your turn" via validate_send; the hub's can_send probe lets each agent's default handler skip wasted LLM calls when it isn't that agent's turn.
Prerequisite: read
ag2-network-quickstartfirst. This skill assumes you already knowHub.open,HubClient.register, the channel lifecycle, andEnvelopebasics.
When to use
- "Three agents debating in turn"
- "A panel discussion / brainstorm with a fixed cast"
- "Round-robin reviewers commenting on a draft"
- Any fixed-order N-party turn-taking where each participant gets a slot per cycle
Don't use discussion for:
- Conditional handoffs ("if alice mentions security, hand to the security expert") → use
ag2-network-workflow. - Pipelines where each step happens once → use
ag2-network-workflowwithTransitionGraph.sequence([...]). - Two participants with no fixed order → use
conversation(covered inag2-network-quickstart). - Strict 1Q1R → use
consulting(covered inag2-network-quickstart).
Shape
| Participants | 2+ |
| Turn order | Round-robin (creator first, then participants in registration order) |
| Auto-close | No |
| Termination | Explicit channel.close() or TTL (see "Closing" below) |
| Default view | NamedWindowedSummary(recent_n=N*2) where N is the participant count |
| Default expectations | turn_within(120s, warn), turn_within(600s, hide) |
| Knob | {"ordering": ORDERING_ROUND_ROBIN} (only ordering shipped today) |
The view recent-window is sized to N*2 so each agent's projection covers roughly the last two full cycles — enough context for a coherent reply without ballooning the prompt as the discussion grows.
Discussion agents, the NetworkPlugin, and turn-taking
HubClient.register(...) attaches NetworkPlugin by default — that adds peers / channels / tasks / context / delegate, the identity-level verbs. DiscussionAdapter.tools_for(...) returns []: the discussion adapter offers no channel-specific tools (no say). A participant contributes its turn purely by returning a reply — the default handler posts the round-end EV_TEXT(reply.body) as that turn's contribution.
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.
- 11d ago First seen · 262 lines · 194 tokens per session scan A ff528443ef2c
ag2-network-discussion is a skill published in the GitHub repository ag2ai/ag2-skills (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 194 tokens to every session and 3,151 once invoked, about $0.0010 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…
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…