📦 deps(thirdparty): update snapshots

superpowers/tests/claude-code/README.md

@@ -115,17 +115,12 @@ Full workflow execution test (~10-30 minutes):
 - Subagents follow the skill correctly
 - Final code is functional and tested
 
-#### test-requesting-code-review.sh
-Behavioral test for the code reviewer subagent (~5 minutes):
-- Builds a tiny project with a baseline commit
-- Adds a second commit that plants two real bugs (SQL injection, plaintext password handling)
-- Dispatches the code reviewer via the requesting-code-review skill
-- Verifies the reviewer flags the planted bugs at Critical/Important severity and refuses to approve
-
-**What it tests:**
-- The skill actually dispatches a working code reviewer subagent
-- The reviewer template produces reviewers that catch obvious security bugs
-- The reviewer is not sycophantic — it does not approve a diff with planted Critical issues
+#### test-worktree-native-preference.sh
+RED-GREEN-REFACTOR validation for the using-git-worktrees skill (~5 minutes):
+- RED: skill without Step 1a — agent should use `git worktree add`
+- GREEN: skill with Step 1a — agent should use the native EnterWorktree tool
+- PRESSURE: same as GREEN under urgency framing with pre-existing `.worktrees/`
+- Drill scenario `worktree-creation-under-pressure.yaml` covers the PRESSURE phase only
 
 ## Adding New Tests
 

superpowers/tests/claude-code/run-skill-tests.sh

@@ -25,7 +25,7 @@ fi
 # Parse command line arguments
 VERBOSE=false
 SPECIFIC_TEST=""
-TIMEOUT=300  # Default 5 minute timeout per test
+TIMEOUT=600  # Default 10 minute timeout per test
 RUN_INTEGRATION=false
 
 while [[ $# -gt 0 ]]; do
@@ -73,13 +73,13 @@ done
 
 # List of skill tests to run (fast unit tests)
 tests=(
+    "test-worktree-path-policy.sh"
     "test-subagent-driven-development.sh"
 )
 
 # Integration tests (slow, full execution)
 integration_tests=(
     "test-subagent-driven-development-integration.sh"
-    "test-requesting-code-review.sh"
 )
 
 # Add integration tests if requested

superpowers/tests/claude-code/test-document-review-system.sh

@@ -1,177 +0,0 @@
-#!/usr/bin/env bash
-# Integration Test: Document Review System
-# Actually runs spec/plan review and verifies reviewers catch issues
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-source "$SCRIPT_DIR/test-helpers.sh"
-
-echo "========================================"
-echo " Integration Test: Document Review System"
-echo "========================================"
-echo ""
-echo "This test verifies the document review system by:"
-echo "  1. Creating a spec with intentional errors"
-echo "  2. Running the spec document reviewer"
-echo "  3. Verifying the reviewer catches the errors"
-echo ""
-
-# Create test project
-TEST_PROJECT=$(create_test_project)
-echo "Test project: $TEST_PROJECT"
-
-# Trap to cleanup
-trap "cleanup_test_project $TEST_PROJECT" EXIT
-
-cd "$TEST_PROJECT"
-
-# Create directory structure
-mkdir -p docs/superpowers/specs
-
-# Create a spec document WITH INTENTIONAL ERRORS for the reviewer to catch
-cat > docs/superpowers/specs/test-feature-design.md <<'EOF'
-# Test Feature Design
-
-## Overview
-
-This is a test feature that does something useful.
-
-## Requirements
-
-1. The feature should work correctly
-2. It should be fast
-3. TODO: Add more requirements here
-
-## Architecture
-
-The feature will use a simple architecture with:
-- A frontend component
-- A backend service
-- Error handling will be specified later once we understand the failure modes better
-
-## Data Flow
-
-Data flows from the frontend to the backend.
-
-## Testing Strategy
-
-Tests will be written to cover the main functionality.
-EOF
-
-# Initialize git repo
-git init --quiet
-git config user.email "test@test.com"
-git config user.name "Test User"
-git add .
-git commit -m "Initial commit with test spec" --quiet
-
-echo ""
-echo "Created test spec with intentional errors:"
-echo "  - TODO placeholder in Requirements section"
-echo "  - 'specified later' deferral in Architecture section"
-echo ""
-echo "Running spec document reviewer..."
-echo ""
-
-# Run Claude to review the spec
-OUTPUT_FILE="$TEST_PROJECT/claude-output.txt"
-
-PROMPT="You are testing the spec document reviewer.
-
-Read the spec-document-reviewer-prompt.md template in skills/brainstorming/ to understand the review format.
-
-Then review the spec at $TEST_PROJECT/docs/superpowers/specs/test-feature-design.md using the criteria from that template.
-
-Look for:
-- TODOs, placeholders, 'TBD', incomplete sections
-- Sections saying 'to be defined later' or 'will spec when X is done'
-- Sections noticeably less detailed than others
-
-Output your review in the format specified in the template."
-
-echo "================================================================================"
-cd "$SCRIPT_DIR/../.." && timeout 120 claude -p "$PROMPT" --permission-mode bypassPermissions 2>&1 | tee "$OUTPUT_FILE" || {
-    echo ""
-    echo "================================================================================"
-    echo "EXECUTION FAILED (exit code: $?)"
-    exit 1
-}
-echo "================================================================================"
-
-echo ""
-echo "Analyzing reviewer output..."
-echo ""
-
-# Verification tests
-FAILED=0
-
-echo "=== Verification Tests ==="
-echo ""
-
-# Test 1: Reviewer found the TODO
-echo "Test 1: Reviewer found TODO..."
-if grep -qi "TODO" "$OUTPUT_FILE" && grep -qi "requirements\|Requirements" "$OUTPUT_FILE"; then
-    echo "  [PASS] Reviewer identified TODO in Requirements section"
-else
-    echo "  [FAIL] Reviewer did not identify TODO"
-    FAILED=$((FAILED + 1))
-fi
-echo ""
-
-# Test 2: Reviewer found the "specified later" deferral
-echo "Test 2: Reviewer found 'specified later' deferral..."
-if grep -qi "specified later\|later\|defer\|incomplete\|error handling" "$OUTPUT_FILE"; then
-    echo "  [PASS] Reviewer identified deferred content"
-else
-    echo "  [FAIL] Reviewer did not identify deferred content"
-    FAILED=$((FAILED + 1))
-fi
-echo ""
-
-# Test 3: Reviewer output includes Issues section
-echo "Test 3: Review output format..."
-if grep -qi "issues\|Issues" "$OUTPUT_FILE"; then
-    echo "  [PASS] Review includes Issues section"
-else
-    echo "  [FAIL] Review missing Issues section"
-    FAILED=$((FAILED + 1))
-fi
-echo ""
-
-# Test 4: Reviewer did NOT approve (found issues)
-echo "Test 4: Reviewer verdict..."
-if grep -qi "Issues Found\|❌\|not approved\|issues found" "$OUTPUT_FILE"; then
-    echo "  [PASS] Reviewer correctly found issues (not approved)"
-elif grep -qi "Approved\|✅" "$OUTPUT_FILE" && ! grep -qi "Issues Found\|❌" "$OUTPUT_FILE"; then
-    echo "  [FAIL] Reviewer incorrectly approved spec with errors"
-    FAILED=$((FAILED + 1))
-else
-    echo "  [PASS] Reviewer identified problems (ambiguous format but found issues)"
-fi
-echo ""
-
-# Summary
-echo "========================================"
-echo " Test Summary"
-echo "========================================"
-echo ""
-
-if [ $FAILED -eq 0 ]; then
-    echo "STATUS: PASSED"
-    echo "All verification tests passed!"
-    echo ""
-    echo "The spec document reviewer correctly:"
-    echo "  ✓ Found TODO placeholder"
-    echo "  ✓ Found 'specified later' deferral"
-    echo "  ✓ Produced properly formatted review"
-    echo "  ✓ Did not approve spec with errors"
-    exit 0
-else
-    echo "STATUS: FAILED"
-    echo "Failed $FAILED verification tests"
-    echo ""
-    echo "Output saved to: $OUTPUT_FILE"
-    echo ""
-    echo "Review the output to see what went wrong."
-    exit 1
-fi

superpowers/tests/claude-code/test-helpers.sh

@@ -9,14 +9,14 @@ run_claude() {
     local allowed_tools="${3:-}"
     local output_file=$(mktemp)
 
-    # Build command
-    local cmd="claude -p \"$prompt\""
+    # Build command as an argv array so timeout wraps claude directly.
+    local cmd=(claude -p "$prompt")
     if [ -n "$allowed_tools" ]; then
-        cmd="$cmd --allowed-tools=$allowed_tools"
+        cmd+=(--allowed-tools="$allowed_tools")
     fi
 
     # Run Claude in headless mode with timeout
-    if timeout "$timeout" bash -c "$cmd" > "$output_file" 2>&1; then
+    if timeout "$timeout" "${cmd[@]}" > "$output_file" 2>&1; then
         cat "$output_file"
         rm -f "$output_file"
         return 0

superpowers/tests/claude-code/test-requesting-code-review.sh

@@ -1,214 +0,0 @@
-#!/usr/bin/env bash
-# Integration Test: requesting-code-review skill
-# Verifies the code reviewer dispatched via the skill catches a planted bug
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
-source "$SCRIPT_DIR/test-helpers.sh"
-
-echo "========================================"
-echo " Integration Test: requesting-code-review"
-echo "========================================"
-echo ""
-echo "This test verifies the code reviewer subagent by:"
-echo "  1. Setting up a tiny project with a baseline commit"
-echo "  2. Adding a second commit that plants an obvious bug"
-echo "  3. Dispatching the code reviewer via the requesting-code-review skill"
-echo "  4. Verifying the reviewer flags the planted bug as Critical/Important"
-echo ""
-
-TEST_PROJECT=$(create_test_project)
-echo "Test project: $TEST_PROJECT"
-trap "cleanup_test_project $TEST_PROJECT" EXIT
-
-cd "$TEST_PROJECT"
-
-# Baseline: a small "safe" implementation
-mkdir -p src
-cat > src/db.js <<'EOF'
-import { Database } from "./database-driver.js";
-
-const db = new Database();
-
-export async function findUserByEmail(email) {
-  if (typeof email !== "string" || !email) {
-    throw new Error("email required");
-  }
-  return db.query(
-    "SELECT id, email, created_at FROM users WHERE email = ?",
-    [email],
-  );
-}
-EOF
-
-cat > package.json <<'EOF'
-{ "name": "test-codereview", "version": "1.0.0", "type": "module" }
-EOF
-
-git init --quiet
-git config user.email "test@test.com"
-git config user.name "Test User"
-git add .
-git commit -m "Initial: parameterized findUserByEmail" --quiet
-BASE_SHA=$(git rev-parse HEAD)
-
-# Second commit: plant two real bugs
-# 1. SQL injection — switch from parameterized to string concatenation
-# 2. Logs the user's password hash on every successful login
-cat > src/db.js <<'EOF'
-import { Database } from "./database-driver.js";
-
-const db = new Database();
-
-export async function findUserByEmail(email) {
-  return db.query(
-    "SELECT id, email, password_hash, created_at FROM users WHERE email = '" + email + "'",
-  );
-}
-
-export async function login(email, password) {
-  const user = await findUserByEmail(email);
-  if (user && user.password_hash === hash(password)) {
-    console.log("login success", { email, password_hash: user.password_hash });
-    return user;
-  }
-  return null;
-}
-
-function hash(s) { return s; }
-EOF
-
-git add .
-git commit -m "Refactor user lookup, add login" --quiet
-HEAD_SHA=$(git rev-parse HEAD)
-
-echo ""
-echo "Planted bugs in $BASE_SHA..$HEAD_SHA:"
-echo "  - SQL injection (string concat instead of parameterized query)"
-echo "  - Password hash logged in plaintext on every successful login"
-echo "  - hash() is the identity function (passwords stored & compared in plaintext)"
-echo ""
-
-OUTPUT_FILE="$TEST_PROJECT/claude-output.txt"
-
-PROMPT="I just finished a refactor. The change is between commits $BASE_SHA and $HEAD_SHA on the current branch.
-
-Use the superpowers:requesting-code-review skill to review these changes before I merge. Follow the skill exactly: dispatch the code reviewer subagent with the template, give the subagent the SHA range, and report back what it found.
-
-Print the reviewer's full output."
-
-# Run claude from inside the test project so its session JSONL lands in a
-# project-specific directory under ~/.claude/projects/, isolated from any
-# other concurrent claude sessions.
-echo "Running Claude (plugin-dir: $PLUGIN_DIR, cwd: $TEST_PROJECT)..."
-echo "================================================================================"
-cd "$TEST_PROJECT" && timeout 600 claude -p "$PROMPT" \
-    --plugin-dir "$PLUGIN_DIR" \
-    --permission-mode bypassPermissions 2>&1 | tee "$OUTPUT_FILE" || {
-    echo ""
-    echo "================================================================================"
-    echo "EXECUTION FAILED (exit code: $?)"
-    exit 1
-}
-echo "================================================================================"
-
-echo ""
-echo "Analyzing reviewer output..."
-echo ""
-
-# Find the session transcript. Because we ran claude from $TEST_PROJECT (a
-# unique tmp dir), its sessions live in their own ~/.claude/projects/ folder.
-# Resolve the real path (macOS mktemp returns /var/... but claude normalizes
-# it to /private/var/...) and replicate claude's normalization (every
-# non-alphanumeric char becomes `-`).
-TEST_PROJECT_REAL=$(cd "$TEST_PROJECT" && pwd -P)
-SESSION_DIR="$HOME/.claude/projects/$(echo "$TEST_PROJECT_REAL" | sed 's|[^a-zA-Z0-9]|-|g')"
-# `|| true` prevents pipefail killing the script if ls gets SIGPIPE'd by head.
-SESSION_FILE=$(ls -t "$SESSION_DIR"/*.jsonl 2>/dev/null | head -1 || true)
-
-FAILED=0
-
-echo "=== Verification Tests ==="
-echo ""
-
-# Test 1: Skill was actually invoked, and a subagent was actually dispatched
-echo "Test 1: requesting-code-review skill invoked + reviewer subagent dispatched..."
-if [ -z "$SESSION_FILE" ] || [ ! -f "$SESSION_FILE" ]; then
-    echo "  [FAIL] Could not locate session transcript in $SESSION_DIR"
-    FAILED=$((FAILED + 1))
-elif ! grep -q '"skill":"superpowers:requesting-code-review"' "$SESSION_FILE"; then
-    echo "  [FAIL] requesting-code-review skill was not invoked"
-    echo "         Session: $SESSION_FILE"
-    FAILED=$((FAILED + 1))
-elif ! grep -q '"name":"Agent"' "$SESSION_FILE"; then
-    echo "  [FAIL] Skill ran but no subagent was dispatched"
-    FAILED=$((FAILED + 1))
-else
-    echo "  [PASS] Skill invoked and subagent dispatched"
-fi
-echo ""
-
-# Test 2: Reviewer caught the SQL injection
-echo "Test 2: SQL injection flagged..."
-if grep -qiE "sql injection|injection|string concat|parameterize|prepared statement|sanitiz" "$OUTPUT_FILE"; then
-    echo "  [PASS] Reviewer flagged the SQL injection vector"
-else
-    echo "  [FAIL] Reviewer missed the SQL injection — most obvious planted bug"
-    FAILED=$((FAILED + 1))
-fi
-echo ""
-
-# Test 3: Reviewer caught the credential / password issue (either logging or no real hashing)
-echo "Test 3: Credential handling issue flagged..."
-if grep -qiE "password|credential|secret|plaintext|log.*hash|hash.*log|sensitive" "$OUTPUT_FILE"; then
-    echo "  [PASS] Reviewer flagged a credential / password handling issue"
-else
-    echo "  [FAIL] Reviewer missed the password/credential issues"
-    FAILED=$((FAILED + 1))
-fi
-echo ""
-
-# Test 4: Reviewer marked at least one issue as Critical or Important (not just Minor)
-echo "Test 4: Severity classification..."
-if grep -qiE "critical|important|severe|high.*risk|security" "$OUTPUT_FILE"; then
-    echo "  [PASS] Reviewer classified findings at Critical/Important severity"
-else
-    echo "  [FAIL] Reviewer did not classify findings as Critical or Important"
-    FAILED=$((FAILED + 1))
-fi
-echo ""
-
-# Test 5: Reviewer did NOT approve the diff for merge
-echo "Test 5: Reviewer verdict..."
-# A correct reviewer says No or "With fixes". A broken/sycophantic reviewer says Yes/Ready.
-if grep -qiE "ready to merge.*yes|approved.*for merge|^\s*yes\s*$|safe to merge" "$OUTPUT_FILE" \
-   && ! grep -qiE "ready to merge.*no|with fixes|do not merge|not ready|block.*merge" "$OUTPUT_FILE"; then
-    echo "  [FAIL] Reviewer approved a diff with planted Critical bugs"
-    FAILED=$((FAILED + 1))
-else
-    echo "  [PASS] Reviewer did not approve the diff"
-fi
-echo ""
-
-echo "========================================"
-echo " Test Summary"
-echo "========================================"
-echo ""
-
-if [ $FAILED -eq 0 ]; then
-    echo "STATUS: PASSED"
-    echo "The code reviewer correctly:"
-    echo "  ✓ Was dispatched via the requesting-code-review skill"
-    echo "  ✓ Flagged the SQL injection"
-    echo "  ✓ Flagged the credential handling issues"
-    echo "  ✓ Classified findings at Critical/Important severity"
-    echo "  ✓ Did not approve the diff for merge"
-    exit 0
-else
-    echo "STATUS: FAILED"
-    echo "Failed $FAILED verification tests"
-    echo ""
-    echo "Output saved to: $OUTPUT_FILE"
-    exit 1
-fi

superpowers/tests/claude-code/test-subagent-driven-development-integration.sh

@@ -1,6 +1,17 @@
 #!/usr/bin/env bash
 # Integration Test: subagent-driven-development workflow
 # Actually executes a plan and verifies the new workflow behaviors
+#
+# Drill coverage: evals/scenarios/sdd-rejects-extra-features.yaml covers the
+# YAGNI enforcement subset (forbidden exports + reviewer-as-gate semantics)
+# and is stricter on that axis. This bash test additionally asserts:
+#   - >=3 git commits (initial + per-task commits, exercising SDD's
+#     commit-per-task workflow shape)
+#   - >=2 Claude Code subagent dispatches via Agent or Task (drill only asserts >=1)
+#   - Claude Code task-tracking tool usage (drill makes no assertion)
+#   - test/math.test.js exists (drill relies on `npm test` succeeding)
+#   - analyze-token-usage.py token-budget telemetry
+# Kept until those assertions are added to drill or explicitly retired.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
@@ -213,13 +224,13 @@ else
 fi
 echo ""
 
-# Test 3: TodoWrite was used for tracking
+# Test 3: Claude Code task-tracking tool was used
 echo "Test 3: Task tracking..."
-todo_count=$(grep -c '"name":"TodoWrite"' "$SESSION_FILE" || echo "0")
+todo_count=$(grep -cE '"name":"(TodoWrite|TaskCreate|TaskUpdate|TaskList|TaskGet)"' "$SESSION_FILE" || echo "0")
 if [ "$todo_count" -ge 1 ]; then
-    echo "  [PASS] TodoWrite used $todo_count time(s) for task tracking"
+    echo "  [PASS] Task tracking used $todo_count time(s)"
 else
-    echo "  [FAIL] TodoWrite not used"
+    echo "  [FAIL] No Claude Code task-tracking tool used"
     FAILED=$((FAILED + 1))
 fi
 echo ""

superpowers/tests/claude-code/test-subagent-driven-development.sh

@@ -1,18 +1,26 @@
 #!/usr/bin/env bash
 # Test: subagent-driven-development skill
 # Verifies that the skill is loaded and follows correct workflow
+#
+# No drill coverage: this test asks the agent to *describe* SDD (string-
+# matches its verbal explanation against expected keywords like
+# "self-review", "skeptical", "worktree", "Step 1", "loop"). Drill scenarios
+# test behavior (real subagent dispatch, plan-following, review loops),
+# not description-recall. Kept by design.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 source "$SCRIPT_DIR/test-helpers.sh"
 
+CLAUDE_PROMPT_TIMEOUT="${CLAUDE_PROMPT_TIMEOUT:-90}"
+
 echo "=== Test: subagent-driven-development skill ==="
 echo ""
 
 # Test 1: Verify skill can be loaded
 echo "Test 1: Skill loading..."
 
-output=$(run_claude "What is the subagent-driven-development skill? Describe its key steps briefly." 30)
+output=$(run_claude "What is the subagent-driven-development skill? Describe its key steps briefly." "$CLAUDE_PROMPT_TIMEOUT")
 
 if assert_contains "$output" "subagent-driven-development\|Subagent-Driven Development\|Subagent Driven" "Skill is recognized"; then
     : # pass
@@ -31,9 +39,11 @@ echo ""
 # Test 2: Verify skill describes correct workflow order
 echo "Test 2: Workflow ordering..."
 
-output=$(run_claude "In the subagent-driven-development skill, what comes first: spec compliance review or code quality review? Be specific about the order." 30)
+output=$(run_claude "In the subagent-driven-development skill, what comes first: spec compliance review or code quality review? Answer using exactly this structure:
+First: <review type>
+Second: <review type>" "$CLAUDE_PROMPT_TIMEOUT")
 
-if assert_order "$output" "spec.*compliance" "code.*quality" "Spec compliance before code quality"; then
+if assert_order "$output" "First:.*spec.*compliance" "Second:.*code.*quality" "Spec compliance before code quality"; then
     : # pass
 else
     exit 1
@@ -44,15 +54,17 @@ echo ""
 # Test 3: Verify self-review is mentioned
 echo "Test 3: Self-review requirement..."
 
-output=$(run_claude "Does the subagent-driven-development skill require implementers to do self-review? What should they check?" 30)
+output=$(run_claude "Does the subagent-driven-development skill require implementers to self-review before handoff, and can self-review replace the external reviews? Answer using exactly this structure:
+Self-review required: <yes or no>
+Self-review replaces external review: <yes or no>" "$CLAUDE_PROMPT_TIMEOUT")
 
-if assert_contains "$output" "self-review\|self review" "Mentions self-review"; then
+if assert_contains "$output" "Self-review required:.*yes" "Mentions self-review"; then
     : # pass
 else
     exit 1
 fi
 
-if assert_contains "$output" "completeness\|Completeness" "Checks completeness"; then
+if assert_contains "$output" "Self-review replaces external review:.*no" "Self-review does not replace external review"; then
     : # pass
 else
     exit 1
@@ -63,7 +75,7 @@ echo ""
 # Test 4: Verify plan is read once
 echo "Test 4: Plan reading efficiency..."
 
-output=$(run_claude "In subagent-driven-development, how many times should the controller read the plan file? When does this happen?" 30)
+output=$(run_claude "In subagent-driven-development, how many times should the controller read the plan file? When does this happen?" "$CLAUDE_PROMPT_TIMEOUT")
 
 if assert_contains "$output" "once\|one time\|single" "Read plan once"; then
     : # pass
@@ -82,7 +94,7 @@ echo ""
 # Test 5: Verify spec compliance reviewer is skeptical
 echo "Test 5: Spec compliance reviewer mindset..."
 
-output=$(run_claude "What is the spec compliance reviewer's attitude toward the implementer's report in subagent-driven-development?" 30)
+output=$(run_claude "What is the spec compliance reviewer's attitude toward the implementer's report in subagent-driven-development?" "$CLAUDE_PROMPT_TIMEOUT")
 
 if assert_contains "$output" "not trust\|don't trust\|skeptical\|verify.*independently\|suspiciously" "Reviewer is skeptical"; then
     : # pass
@@ -101,7 +113,7 @@ echo ""
 # Test 6: Verify review loops
 echo "Test 6: Review loop requirements..."
 
-output=$(run_claude "In subagent-driven-development, what happens if a reviewer finds issues? Is it a one-time review or a loop?" 30)
+output=$(run_claude "In subagent-driven-development, what happens if a reviewer finds issues? Is it a one-time review or a loop?" "$CLAUDE_PROMPT_TIMEOUT")
 
 if assert_contains "$output" "loop\|again\|repeat\|until.*approved\|until.*compliant" "Review loops mentioned"; then
     : # pass
@@ -120,7 +132,9 @@ echo ""
 # Test 7: Verify full task text is provided
 echo "Test 7: Task context provision..."
 
-output=$(run_claude "In subagent-driven-development, how does the controller provide task information to the implementer subagent? Does it make them read a file or provide it directly?" 30)
+output=$(run_claude "In subagent-driven-development, how does the controller provide task information to the implementer subagent? Answer using exactly this structure:
+Controller provides: <directly or by file>
+Implementer must read plan file: <yes or no>" "$CLAUDE_PROMPT_TIMEOUT")
 
 if assert_contains "$output" "provide.*directly\|full.*text\|paste\|include.*prompt" "Provides text directly"; then
     : # pass
@@ -128,7 +142,7 @@ else
     exit 1
 fi
 
-if assert_not_contains "$output" "read.*file\|open.*file" "Doesn't make subagent read file"; then
+if assert_contains "$output" "Implementer must read plan file:.*no" "Doesn't make subagent read file"; then
     : # pass
 else
     exit 1
@@ -139,7 +153,7 @@ echo ""
 # Test 8: Verify worktree requirement
 echo "Test 8: Worktree requirement..."
 
-output=$(run_claude "What workflow skills are required before using subagent-driven-development? List any prerequisites or required skills." 30)
+output=$(run_claude "What workflow skills are required before using subagent-driven-development? List any prerequisites or required skills." "$CLAUDE_PROMPT_TIMEOUT")
 
 if assert_contains "$output" "using-git-worktrees\|worktree" "Mentions worktree requirement"; then
     : # pass
@@ -152,7 +166,7 @@ echo ""
 # Test 9: Verify main branch warning
 echo "Test 9: Main branch red flag..."
 
-output=$(run_claude "In subagent-driven-development, is it okay to start implementation directly on the main branch?" 30)
+output=$(run_claude "In subagent-driven-development, is it okay to start implementation directly on the main branch?" "$CLAUDE_PROMPT_TIMEOUT")
 
 if assert_contains "$output" "worktree\|feature.*branch\|not.*main\|never.*main\|avoid.*main\|don't.*main\|consent\|permission" "Warns against main branch"; then
     : # pass

superpowers/tests/claude-code/test-worktree-native-preference.sh

@@ -2,6 +2,11 @@
 # Test: Does the agent prefer native worktree tools (EnterWorktree) over git worktree add?
 # Framework: RED-GREEN-REFACTOR per testing-skills-with-subagents.md
 #
+# Drill coverage: evals/scenarios/worktree-creation-under-pressure.yaml lifts
+# only the PRESSURE phase (existing .worktrees/ + urgency framing). The RED
+# and GREEN baselines below are not covered by drill — kept here so the
+# RED-GREEN-REFACTOR validation remains rerunnable end-to-end.
+#
 # RED:   Skill without Step 1a (no native tool preference). Agent should use git worktree add.
 # GREEN: Skill with Step 1a (explicit tool naming + consent bridge). Agent should use EnterWorktree.
 # PRESSURE: Same as GREEN but under time pressure with existing .worktrees/ dir.

superpowers/tests/claude-code/test-worktree-path-policy.sh

@@ -0,0 +1,69 @@
+#!/usr/bin/env bash
+# Regression check: Superpowers should not route new worktrees through the old
+# global worktree directory.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+USING_SKILL="$REPO_ROOT/skills/using-git-worktrees/SKILL.md"
+FINISHING_SKILL="$REPO_ROOT/skills/finishing-a-development-branch/SKILL.md"
+ROTOTILL_SPEC="$REPO_ROOT/docs/superpowers/specs/2026-04-06-worktree-rototill-design.md"
+ROTOTILL_PLAN="$REPO_ROOT/docs/superpowers/plans/2026-04-06-worktree-rototill.md"
+
+failures=0
+
+assert_contains() {
+    local file="$1"
+    local pattern="$2"
+    local label="$3"
+
+    if grep -Fq "$pattern" "$file"; then
+        echo "  [PASS] $label"
+    else
+        echo "  [FAIL] $label"
+        echo "    Expected to find: $pattern"
+        echo "    In file: $file"
+        failures=$((failures + 1))
+    fi
+}
+
+assert_not_contains() {
+    local file="$1"
+    local pattern="$2"
+    local label="$3"
+
+    if grep -Fq "$pattern" "$file"; then
+        echo "  [FAIL] $label"
+        echo "    Did not expect to find: $pattern"
+        echo "    In file: $file"
+        failures=$((failures + 1))
+    else
+        echo "  [PASS] $label"
+    fi
+}
+
+echo "=== Worktree Path Policy Test ==="
+echo ""
+
+assert_not_contains "$USING_SKILL" "~/.config/superpowers/worktrees" "using-git-worktrees does not mention old global path"
+assert_not_contains "$USING_SKILL" "global legacy" "using-git-worktrees does not use unclear global legacy shorthand"
+assert_not_contains "$USING_SKILL" "Global path" "using-git-worktrees has no global path quick-reference row"
+assert_contains "$USING_SKILL" 'default to `.worktrees/` at the project root' "using-git-worktrees defaults new manual worktrees to .worktrees/"
+
+assert_not_contains "$FINISHING_SKILL" "~/.config/superpowers/worktrees" "finishing-a-development-branch does not treat old global path as owned"
+assert_contains "$FINISHING_SKILL" '`.worktrees/` or `worktrees/`' "finishing-a-development-branch keeps project-local cleanup ownership"
+
+assert_not_contains "$ROTOTILL_SPEC" "~/.config/superpowers/worktrees" "rototill spec does not preserve old global path policy"
+assert_not_contains "$ROTOTILL_PLAN" "~/.config/superpowers/worktrees" "rototill plan does not preserve old global path policy"
+assert_not_contains "$ROTOTILL_PLAN" "legacy path compat" "rototill plan does not advertise legacy path compatibility"
+
+echo ""
+
+if [ "$failures" -gt 0 ]; then
+    echo "STATUS: FAILED ($failures failures)"
+    exit 1
+fi
+
+echo "STATUS: PASSED"