docs: clarify opencode attach semantics

examples/agent_challenges/browser_click_challenge/README.md

@@ -26,16 +26,18 @@ Results are written to:
 examples/agent_challenges/browser_click_challenge/results/
 ```
 
-## Optional Playwright MCP Attachment
+## Optional Opencode Server Attachment
 
-If you want the agent to have browser-control tools, pass:
+`--attach` is opencode's server attach flag. It connects this non-interactive
+run to an already-running opencode server, for example:
 
 ```powershell
 --attach http://127.0.0.1:4096
 ```
 
-Start that MCP/tool endpoint separately. For example, one possible MCP server
+It is not a direct MCP server URL. If that opencode server is configured with
-command is:
+Playwright MCP tools, then the attached run can use those tools through
+opencode. One possible MCP server command for such an opencode setup is:
 
 ```json
 {

examples/agent_challenges/browser_click_challenge/run_opencode_trials.py

@@ -216,7 +216,15 @@ def main(argv: list[str] | None = None) -> int:
     parser.add_argument("--variant", default="high")
     parser.add_argument("--trials", type=int, default=1)
     parser.add_argument("--timeout-seconds", type=int, default=600)
-    parser.add_argument("--attach", dest="attach_url", default=None)
+    parser.add_argument(
+        "--attach",
+        dest="attach_url",
+        default=None,
+        help=(
+            "Attach to a running opencode server URL. This is not a direct MCP "
+            "server URL."
+        ),
+    )
     parser.add_argument("--prompt", type=Path, default=DEFAULT_PROMPT)
     parser.add_argument("--results-dir", type=Path, default=DEFAULT_RESULTS_DIR)
     args = parser.parse_args(argv)