Claude MCP - Lab Building

The Rogue Arena MCP plugin lets Claude Code drive Rogue Architect end-to-end. Describe the lab you want, and Claude handles the canvas — VLANs, machines, plugins, AD topologies, the works.

This page covers the scenario-building skills that ship with the plugin. (For the deployment-side skills, see Claude MCP - Active Deployments. For plugin authoring, see Claude MCP - Plugin Dev.)

/architect-brainstorm

The gold standard for going from nothing to a staged scenario. One command reads design markdown in order (shape → cast → build → validate), then — after you confirm — implements the canvas. It does not Skill() other skills.

It seeds realism: user files, browser histories, mail, file-share layouts — so the lab doesn’t feel like a sterile sandbox.

When the build is staged, you run /architect-final-validate before Apply Plan. That last skill is required.

/architect-freeform

Manual canvas work with the MCP tools — no guided pipeline. Use it to add machines, swap plugins, wire VLANs, or tweak configuration on an existing canvas. Best when you know exactly what you want to change and just need Claude to do the keystrokes.

/architect-final-validate

Read-only pre-deploy audit. Walks every machine and every plugin; checks plugin coupling, run-order, infrastructure correctness, and realism. Use this right before launching a build to catch issues a human eye would miss.

/architect-debug-deploy

Investigates deployment failures — Ansible errors, PowerShell debugging, plugin misconfigurations. Requires a canvas ID. Drop it in when a build errored and you want Claude to triage the failure end-to-end (pull the Ansible log, identify the failing task, propose a fix).

Validate and implement are not separate skills. They are markdown steps inside /architect-brainstorm. The only follow-on command is /architect-final-validate.