test(benchmarks): add A/B task fixtures with hidden checks

Ten small Python tasks, each failing on the fixture and passing with a
reference solution, including workflow expectations for a small change, a
bugfix, and a delegable change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scripts/benchmarks/tasks/01-small-config-change/hidden/test_hidden.py

@@ -0,0 +1,16 @@
+import unittest
+from pathlib import Path
+from app import client, config
+
+
+class Hidden(unittest.TestCase):
+    def test_default(self):
+        self.assertEqual(config.DEFAULT_TIMEOUT, 60)
+        self.assertEqual(client.request('x'), 60)
+        self.assertEqual(client.request('x', 5), 5)
+
+    def test_docs(self):
+        for path in ('README.md', 'app/client.py'):
+            text = Path(path).read_text()
+            self.assertIn('60 seconds', text)
+            self.assertNotIn('30 seconds', text)

scripts/benchmarks/tasks/01-small-config-change/repo/README.md

@@ -0,0 +1,3 @@
+# Client
+
+Requests time out after 30 seconds unless a timeout is passed.

scripts/benchmarks/tasks/01-small-config-change/repo/app/client.py

@@ -0,0 +1,6 @@
+from app.config import DEFAULT_TIMEOUT
+
+
+def request(url, timeout=None):
+    """Return the effective timeout in seconds; defaults to DEFAULT_TIMEOUT (30 seconds)."""
+    return timeout if timeout is not None else DEFAULT_TIMEOUT

scripts/benchmarks/tasks/01-small-config-change/repo/app/config.py

@@ -0,0 +1 @@
+DEFAULT_TIMEOUT = 30

scripts/benchmarks/tasks/01-small-config-change/task.json

@@ -0,0 +1,14 @@
+{
+  "prompt": "Change the default request timeout from 30 to 60 seconds.",
+  "workflow": {
+    "kind": "small change without planning ceremony",
+    "forbid_skills": [
+      "superpowers:brainstorming",
+      "superpowers:writing-plans",
+      "superpowers:subagent-driven-development",
+      "superpowers:executing-plans"
+    ],
+    "max_agents": 0,
+    "max_tool_calls": 15
+  }
+}