diff --git a/hive-bash-mcp/src/runner.rs b/hive-bash-mcp/src/runner.rs
index 683cab11..424bb9f9 100644
--- a/hive-bash-mcp/src/runner.rs
+++ b/hive-bash-mcp/src/runner.rs
@@ -526,12 +526,15 @@ async fn run_task(mut task: TaskFile, socket: &Path) {
     if let Err(e) = write_task(&task) {
         tracing::warn!(id = %id, error = ?e, "bash_runner: write running state failed");
     }
-    upsert_bash_todo(
-        socket,
-        &id,
-        format!("bash task `{id}` running: `{}`", task.cmd),
-    )
-    .await;
+    // No command text in the summary: `id` is already the human-chosen
+    // `name` when the caller passed one, and even the auto-generated
+    // hex id was already returned to the agent in the `run` tool's own
+    // result — the todo only needs to say which task, not repeat the
+    // command. An unbounded raw command (e.g. a multi-line heredoc
+    // script) would balloon every UI that renders todo summaries; the
+    // full command stays on disk in the task file for `status`/`view`
+    // instead.
+    upsert_bash_todo(socket, &id, format!("bash task `{id}` running")).await;
     // Best-effort: tally the normalised command head for the /stats
     // "favorite tools" view. Counted once per execution, regardless of
     // exit status. Never fails the task.