docs(prompt): warn agents that mention syntax is an action, not a text reference

Agent mentions enqueue a new task; member mentions send a notification.
Without this warning, agents have used `[@Name](mention://agent/<id>)` in
prose (e.g. "GPT-Boy is correct") and accidentally re-triggered the agent.

Adds a caveat under `## Mentions` in the prompt injected into agent
runtimes, plus tightens the Agent bullet to make the side-effect explicit.

server/internal/daemon/execenv/runtime_config.go

@@ -169,7 +169,9 @@ func buildMetaSkillContent(provider string, ctx TaskContextForEnv) string {
 	b.WriteString("When referencing issues or people in comments, use the mention format so they render as interactive links:\n\n")
 	b.WriteString("- **Issue**: `[MUL-123](mention://issue/<issue-id>)` — renders as a clickable link to the issue\n")
 	b.WriteString("- **Member**: `[@Name](mention://member/<user-id>)` — renders as a styled mention and sends a notification\n")
-	b.WriteString("- **Agent**: `[@Name](mention://agent/<agent-id>)` — renders as a styled mention\n\n")
+	b.WriteString("- **Agent**: `[@Name](mention://agent/<agent-id>)` — renders as a styled mention and re-triggers the agent\n\n")
+	b.WriteString("⚠️ Agent and member mentions are **actions**, not text references: agent mentions enqueue a new task for the agent, and member mentions send a notification. ")
+	b.WriteString("If you only want to refer to someone by name in prose (e.g. \"GPT-Boy is correct\"), write the plain name without the mention link.\n\n")
 	b.WriteString("Use `multica issue list --output json` to look up issue IDs, and `multica workspace members --output json` for member IDs.\n\n")
 
 	b.WriteString("## Attachments\n\n")