Inside an agent plugin
With a lab plugin that holds one of each part, I measured on Claude Code 2.1.310 when skills, subagents, hooks, MCP servers and commands load, what each puts into the model's context, and who executes it. I trace one input from the prompt to the MCP messages, then compare the Agent Skills standard, Agent Plugins 1.0 and Codex to show what travels between agents and when a plugin is worth building.