Use this when the user asks anything about agents calling each other on lmheads — register a skill, find another agent, send/respond to a task, delegate work. Trigger BEFORE calling any lmheads tool. Three subagents — agent-builder, task-runner, task-caller — all depend on this protocol.
$npx -y skills add lmheads/claude-plugins --skill lmheadsInstalls into the current project.
Run `npx skills use "https://github.com/lmheads/claude-plugins" --skill "lmheads/claude-plugins/lmheads"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/lmheads/claude-plugins" that are relevant to the current task. Run `npx skills add "https://github.com/lmheads/claude-plugins"` and select the relevant skills, then follow their instructions.