agent-discussion vs Benchwarmers
agent-discussion is a plugin bundle for AI coding tools published by cyrusxyl. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Benchwarmers is an MCP server published by WendellResearch-AI. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-11. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  agent-discussion |  Benchwarmers |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.1.0 Forks (GitHub): 0 Stars (GitHub): 4 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.6.5 Downloads/month (npm): 3 310 Downloads/week (npm): 1 420 Forks (GitHub): 0 Stars (GitHub): 1 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | agent-discussion | Benchwarmers |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 4 (better) | 1 (worse) |
| Forks (GitHub) | 0 | 0 |
| Last release (differs) | Not published | 2026-11-10 |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (@wendellresearch-ai/benchwarmers) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 3, secrets among them: 1 |
| Parts of the bundle (differs) | 1 | Not a bundle |
| Licence | Not stated | Not stated |
| Repository (differs) | github.com/cyrusxyl/agent-discussion | github.com/wendellresearch-ai/benchwarmers |
| Changes in the last 7 days (differs) | 0 | 5 |
| First seen (differs) | 2026-10-11 | 2026-10-23 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
agent-discussion
Coordinate multi-agent debates across different AI platforms (Claude Code, Antigravity, Copilot, Gemini CLI, etc.) using a shared file protocol. Each agent reads one skill and handles everything autonomously — intros, turn-taking, and consensus.
Benchwarmers
Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.
How to run each
agent-discussion As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install agent-discussion@claude-communityBenchwarmers As a local MCP server: npm package
claude mcp add --env "BENCHWARMERS_KEY=<YOUR_BENCHWARMERS_KEY>" --transport stdio benchwarmers -- npx -y @wendellresearch-ai/benchwarmers mcpRequires: BENCHWARMERS_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of agent-discussion publish no settings it asks for, so we do not compare settings.
What it can do: agent-discussion · What it can do: Benchwarmers · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.