28 tagged ai plugin, measured the same way as everything else here.
Agent
Finds every weakness, flaw, and failure mode in an idea. Authentic dissenter, not assigned devil's advocacy. Use proactively when stress-testing, red teaming, poking holes, or when the user asks what could go wrong, what they're missing, or to challenge something.
Agent
Builds the strongest possible case for an idea with genuine conviction. Not neutral analysis, authentic advocacy. Use proactively when the user asks to steelman, make the best case, argue both sides, or defend an idea.
Agent
Renders dispassionate structured verdict from argument graph evidence. No advocacy in either direction. Use after advocate and adversary have contributed to the graph, or standalone when the user asks for a verdict, bottom line, or final assessment.
Agent
Use this agent when the guild needs architectural planning. The architect reads requirements, analyzes the codebase, and produces implementation plans with specific developer tasks. Spawned directly by the new-requirement skill, alongside the product-owner — not spawned via a board ticket.
Agent
Use this agent when the guild needs code implementation in a Svelte or SvelteKit web application. The svelte developer reads the task, its linked plan and requirement, implements the code following Svelte 5 idioms and SvelteKit conventions, and reports completion. Spawned by the check-in skill when an implementation…
Agent
Use this agent when the guild needs to gather, refine, or document requirements. The product-owner interviews the user, creates requirement documents, and collaborates with the architect. Spawned directly by the new-requirement skill for a live interview with the user (via relay) and, when in scope, the architect …
robbedoo/minimax-plugin-claude-code
Agent
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to MiniMax through the shared runtime.