Lift drill into evals/ at 013fcb8b7dbefd6d3fa4653493e5d2ec8e7f985b

rsync of obra/drill@013fcb8b7d into superpowers/evals/, excluding
.git/, .venv/, results/, .env/, __pycache__/, *.egg-info/,
.private-journal/.

The drill repo is unaffected by this commit; archival is a separate
manual step after this PR merges.

Source SHA recorded at evals/.drill-source-sha for divergence
detection.

evals/scenarios/codex-subagent-wait-mapping.yaml

@@ -0,0 +1,53 @@
+scenario: codex-subagent-wait-mapping
+description: >
+  Measures whether a Codex agent follows Superpowers' Codex tool mapping
+  when translating Claude Code Task subagent result collection.
+user_posture: spec-aware
+
+setup:
+  helpers:
+    - create_base_repo
+  assertions:
+    - "git rev-parse --is-inside-work-tree"
+    - "test -f .agents/skills/superpowers/using-superpowers/references/codex-tools.md"
+
+turns:
+  - intent: >
+      When Codex is at its input prompt, type this exact message and press
+      Enter. Do not type a placeholder, a period, or a shorter paraphrase:
+
+      "Read .agents/skills/superpowers/using-superpowers/references/codex-tools.md.
+      Treat that file as authoritative for translating Claude Code tool
+      names to Codex tool names. Do not use your prior knowledge of Codex
+      tool names when the file gives a mapping. Now simulate this Claude
+      Code workflow using the mapped Codex tools: Task tool dispatches a
+      subagent; Task returns result; Task completes automatically. The
+      subagent's whole job is to answer exactly PR963_OK. Wait for the
+      subagent result using the mapped equivalent for 'Task returns result',
+      then report the result. Do not edit files."
+  - intent: >
+      If the agent asks a short clarifying question, answer briefly and
+      tell it to follow the mapping file. If it reports PR963_OK or says
+      it cannot complete the mapped wait step, you are done.
+
+limits:
+  max_turns: 8
+  turn_timeout: 240
+
+verify:
+  assertions:
+    - "tool-called spawn_agent"
+    - "tool-called wait_agent"
+    - "tool-not-called wait"
+    - "tool-before spawn_agent wait_agent"
+    - "grep -q PR963_OK session.log"
+  criteria:
+    - >
+      Agent read the Codex tool mapping file before choosing which tool
+      waits for a spawned subagent result.
+    - >
+      Agent used wait_agent, not wait, to collect the spawned subagent
+      result.
+    - >
+      Agent successfully reported the spawned subagent sentinel PR963_OK.
+  observe: true