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/backends/claude-haiku.yaml

@@ -0,0 +1,26 @@
+name: claude-haiku
+cli: claude
+args:
+  - "--dangerously-skip-permissions"
+  - "--plugin-dir"
+  - "${SUPERPOWERS_ROOT}"
+  - "--model"
+  - "haiku"
+required_env:
+  - ANTHROPIC_API_KEY
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run: []
+  post_run: []
+shutdown: "/exit"
+idle:
+  quiescence_seconds: 3
+  ready_pattern: "^❯|^\\$|Human:|Enter to confirm"
+busy_pattern: "esc to cancel|Thinking\\.\\.\\.|\\(esc to cancel[^)]*\\)|[⠇⠏⠋⠙⠹⠸⠼⠴⠦⠧⠶⠾⠽⠻⠿]"
+max_busy_seconds: 1800
+startup_timeout: 60
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.claude/projects/**/session-*.jsonl"

evals/backends/claude-opus-4-6-1m.yaml

@@ -0,0 +1,26 @@
+name: claude-opus-4-6-1m
+cli: claude
+args:
+  - "--dangerously-skip-permissions"
+  - "--plugin-dir"
+  - "${SUPERPOWERS_ROOT}"
+  - "--model"
+  - "claude-opus-4-6[1m]"
+required_env:
+  - ANTHROPIC_API_KEY
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run: []
+  post_run: []
+shutdown: "/exit"
+idle:
+  quiescence_seconds: 3
+  ready_pattern: "^❯|^\\$|Human:|Enter to confirm"
+busy_pattern: "esc to cancel|Thinking\\.\\.\\.|\\(esc to cancel[^)]*\\)|[⠇⠏⠋⠙⠹⠸⠼⠴⠦⠧⠶⠾⠽⠻⠿]"
+max_busy_seconds: 1800
+startup_timeout: 60
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.claude/projects/**/session-*.jsonl"

evals/backends/claude-opus-4-6.yaml

@@ -0,0 +1,26 @@
+name: claude-opus-4-6
+cli: claude
+args:
+  - "--dangerously-skip-permissions"
+  - "--plugin-dir"
+  - "${SUPERPOWERS_ROOT}"
+  - "--model"
+  - "claude-opus-4-6"
+required_env:
+  - ANTHROPIC_API_KEY
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run: []
+  post_run: []
+shutdown: "/exit"
+idle:
+  quiescence_seconds: 3
+  ready_pattern: "^❯|^\\$|Human:|Enter to confirm"
+busy_pattern: "esc to cancel|Thinking\\.\\.\\.|\\(esc to cancel[^)]*\\)|[⠇⠏⠋⠙⠹⠸⠼⠴⠦⠧⠶⠾⠽⠻⠿]"
+max_busy_seconds: 1800
+startup_timeout: 60
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.claude/projects/**/session-*.jsonl"

evals/backends/claude-opus-4-7-1m.yaml

@@ -0,0 +1,26 @@
+name: claude-opus-4-7-1m
+cli: claude
+args:
+  - "--dangerously-skip-permissions"
+  - "--plugin-dir"
+  - "${SUPERPOWERS_ROOT}"
+  - "--model"
+  - "claude-opus-4-7[1m]"
+required_env:
+  - ANTHROPIC_API_KEY
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run: []
+  post_run: []
+shutdown: "/exit"
+idle:
+  quiescence_seconds: 3
+  ready_pattern: "^❯|^\\$|Human:|Enter to confirm"
+busy_pattern: "esc to cancel|Thinking\\.\\.\\.|\\(esc to cancel[^)]*\\)|[⠇⠏⠋⠙⠹⠸⠼⠴⠦⠧⠶⠾⠽⠻⠿]"
+max_busy_seconds: 1800
+startup_timeout: 60
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.claude/projects/**/session-*.jsonl"

evals/backends/claude-opus-4-7.yaml

@@ -0,0 +1,26 @@
+name: claude-opus-4-7
+cli: claude
+args:
+  - "--dangerously-skip-permissions"
+  - "--plugin-dir"
+  - "${SUPERPOWERS_ROOT}"
+  - "--model"
+  - "claude-opus-4-7"
+required_env:
+  - ANTHROPIC_API_KEY
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run: []
+  post_run: []
+shutdown: "/exit"
+idle:
+  quiescence_seconds: 3
+  ready_pattern: "^❯|^\\$|Human:|Enter to confirm"
+busy_pattern: "esc to cancel|Thinking\\.\\.\\.|\\(esc to cancel[^)]*\\)|[⠇⠏⠋⠙⠹⠸⠼⠴⠦⠧⠶⠾⠽⠻⠿]"
+max_busy_seconds: 1800
+startup_timeout: 60
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.claude/projects/**/session-*.jsonl"

evals/backends/claude.yaml

@@ -0,0 +1,32 @@
+name: claude
+cli: claude
+args:
+  - "--dangerously-skip-permissions"
+  - "--plugin-dir"
+  - "${SUPERPOWERS_ROOT}"
+  - "--model"
+  - "opus"
+required_env:
+  - ANTHROPIC_API_KEY
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run: []
+  post_run: []
+shutdown: "/exit"
+idle:
+  quiescence_seconds: 3
+  ready_pattern: "^❯|^\\$|Human:|Enter to confirm"
+# Matches when Claude is actively working — spinners, "Thinking", time counter,
+# or "esc to cancel". Engine extends its wait deadline when any of these match
+# so the Actor doesn't interrupt long-running subagent work (e.g., wave execution).
+busy_pattern: "esc to cancel|Thinking\\.\\.\\.|\\(esc to cancel[^)]*\\)|[⠇⠏⠋⠙⠹⠸⠼⠴⠦⠧⠶⠾⠽⠻⠿]"
+# Maximum total seconds the engine will extend the deadline across all busy
+# detections during a single _wait_for_ready call. Wave execution can take
+# 10-20 minutes per wave, so 30 minutes gives plenty of headroom.
+max_busy_seconds: 1800
+startup_timeout: 60
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.claude/projects/**/session-*.jsonl"

evals/backends/codex.yaml

@@ -0,0 +1,21 @@
+name: codex
+cli: codex
+args:
+  - "--dangerously-bypass-approvals-and-sandbox"
+required_env:
+  - OPENAI_API_KEY
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run:
+    - symlink_superpowers
+  post_run: []
+shutdown: "<<KEY:ctrl-d>>"
+idle:
+  quiescence_seconds: 5
+  ready_pattern: "^›|codex>|^>"
+startup_timeout: 60
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.codex/sessions/rollout-*.jsonl"

evals/backends/gemini.yaml

@@ -0,0 +1,24 @@
+name: gemini
+cli: gemini
+args:
+  - "--yolo"
+  - "-m"
+  - "gemini-2.5-flash"
+required_env:
+  - SUPERPOWERS_ROOT
+hooks:
+  pre_run:
+    - link_gemini_extension
+  post_run: []
+shutdown: "/exit"
+idle:
+  quiescence_seconds: 5
+  ready_pattern: "Type your message|^\\s*>"
+busy_pattern: "Thinking\\.\\.\\.|Executing"
+startup_timeout: 60
+turn_timeout: 300
+terminal:
+  cols: 200
+  rows: 50
+session_logs:
+  pattern: "~/.gemini/tmp/*/chats/session-*.json"