using-agentstacklisted

# Use AgentStack ## Start with the state Run `agentstack status` first. Use `agentstack doctor` only when status points to a problem or deeper verification is needed. Read these facts separately: - `locked`: portable content is pinned; this does not mean a connection is live. - `trusted`: a human approved the current manifest and lock on this machine. - `default toolset`: what a trusted new agent connection opens automatically. - `live toolset`: a process-scoped connection that exists right now. - `delivery`: which capabilities are served live and which are written to files. ## Follow the delivery decision When status says skills or MCP servers are served live: - Do not run `use`, `apply`, or `render-locally` to make them appear. - Do not create `.mcp.json`, `.claude/skills/`, `.agents/skills/`, or similar capability folders. - Use the trusted default toolset. If several toolsets exist without a default, ask the user which one should be selected. - The connection already receives loadable skill names and one-line descriptions. Refresh or filter them with `agentstack_list_loadable(query)`. - Load only a needed full body with `agentstack_load(name, reason)`. The user does not need to say the skill name when its description clearly matches. - Discover proxied runtime tools and their schemas with `tools_search` only when the task needs one. File-only CLIs and capability kinds are rendered automatically. An explicit `render_locally` override is a compatibility ch