diff --git a/prompts/08_subagents.md b/prompts/08_subagents.md
index e1ecbbd..6fe8b37 100644
--- a/prompts/08_subagents.md
+++ b/prompts/08_subagents.md
@@ -46,11 +46,13 @@ execute_code: steps=[
   {code: "subagent_spawn 'Summarize core/pkg/agent/loop.go'"},
   {code: "subagent_spawn 'Summarize core/pkg/backend/anthropic.go'"},
   {code: "subagent_spawn 'Summarize 9p/internal/p9/server.go'"}
-]
+], timeout=300
 ```
 
 Three concurrent subagents, three different prompts. Results appear under `=== step N ===` headers from `execute_code`.
 
+Set `timeout` to at least 300 seconds when subagents are doing non-trivial work — the default 30 seconds is not enough.
+
 ## Design rules
 
 **Same agent across parallel subagents.** Different agents produce different output schemas; concatenating them is incoherent.