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/gemini-subagent-tool-mapping-comprehension.yaml

@@ -0,0 +1,63 @@
+scenario: gemini-subagent-tool-mapping-comprehension
+description: >
+  Measures whether a Gemini CLI agent correctly reports the Superpowers Gemini
+  mapping for Claude Code Task subagent dispatch, including parallel dispatch.
+user_posture: spec-aware
+
+setup:
+  helpers:
+    - create_base_repo
+  assertions:
+    - "git rev-parse --is-inside-work-tree"
+    - "test -f GEMINI.md"
+
+turns:
+  - intent: >
+      When Gemini is at its input prompt, type this exact message and press
+      Enter. Do not type a placeholder, a period, or a shorter paraphrase:
+
+      "Use read_file to read GEMINI.md. Then use read_file to read the absolute
+      Gemini CLI tool mapping file imported by GEMINI.md. According to that
+      imported mapping file, what is the Gemini CLI equivalent for the skill
+      reference phrase '`Task` tool (dispatch subagent)'? Do not perform any
+      subagent workflow. Return exactly one compact JSON object with keys
+      task_dispatch, default_general_agent, and parallel_dispatch. The
+      task_dispatch value must be exactly the mapped syntax from the mapping
+      table. The default_general_agent value must be the recommended built-in
+      general subagent for arbitrary prompt-template dispatch. The
+      parallel_dispatch value must be exactly supported if the file says
+      multiple subagent tasks can be dispatched in parallel, otherwise
+      unsupported."
+  - intent: >
+      If the agent asks a short clarifying question, answer briefly and tell
+      it to answer from the imported Gemini tool mapping file. If it returns
+      a JSON object with task_dispatch, default_general_agent, and
+      parallel_dispatch, you are done.
+
+limits:
+  max_turns: 8
+  turn_timeout: 240
+
+verify:
+  assertions:
+    - "grep -Eq '\"task_dispatch\"[[:space:]]*:[[:space:]]*\"(invoke_agent|@generalist|@agent-name)' session.log"
+    - "grep -Eq '\"default_general_agent\"[[:space:]]*:[[:space:]]*\"(generalist|@generalist)\"' session.log"
+    - "grep -Eq '\"parallel_dispatch\"[[:space:]]*:[[:space:]]*\"supported\"' session.log"
+    - "! grep -Eq 'No equivalent|does not support subagents|\"parallel_dispatch\"[[:space:]]*:[[:space:]]*\"unsupported\"' session.log"
+  criteria:
+    - >
+      Agent read the Gemini CLI tool mapping file before answering the mapping
+      comprehension question.
+    - >
+      Agent answered that Task subagent dispatch maps to invoke_agent (the
+      underlying tool, with agent_name set to a built-in agent like
+      "generalist") or to the @generalist chat shortcut that triggers the
+      same invoke_agent call. Either form is correct per Gemini CLI's source
+      and docs.
+    - >
+      Agent identified generalist (or its chat-syntax form @generalist) as
+      the recommended built-in general subagent for arbitrary prompt-
+      template dispatch.
+    - >
+      Agent reported parallel subagent dispatch as supported.
+  observe: true