workerssuper 5.0.4

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

@@ -0,0 +1,202 @@
+#!/usr/bin/env bash
+# Helper functions for Claude Code skill tests
+
+# Run Claude Code with a prompt and capture output
+# Usage: run_claude "prompt text" [timeout_seconds] [allowed_tools]
+run_claude() {
+    local prompt="$1"
+    local timeout="${2:-60}"
+    local allowed_tools="${3:-}"
+    local output_file=$(mktemp)
+
+    # Build command
+    local cmd="claude -p \"$prompt\""
+    if [ -n "$allowed_tools" ]; then
+        cmd="$cmd --allowed-tools=$allowed_tools"
+    fi
+
+    # Run Claude in headless mode with timeout
+    if timeout "$timeout" bash -c "$cmd" > "$output_file" 2>&1; then
+        cat "$output_file"
+        rm -f "$output_file"
+        return 0
+    else
+        local exit_code=$?
+        cat "$output_file" >&2
+        rm -f "$output_file"
+        return $exit_code
+    fi
+}
+
+# Check if output contains a pattern
+# Usage: assert_contains "output" "pattern" "test name"
+assert_contains() {
+    local output="$1"
+    local pattern="$2"
+    local test_name="${3:-test}"
+
+    if echo "$output" | grep -q "$pattern"; then
+        echo "  [PASS] $test_name"
+        return 0
+    else
+        echo "  [FAIL] $test_name"
+        echo "  Expected to find: $pattern"
+        echo "  In output:"
+        echo "$output" | sed 's/^/    /'
+        return 1
+    fi
+}
+
+# Check if output does NOT contain a pattern
+# Usage: assert_not_contains "output" "pattern" "test name"
+assert_not_contains() {
+    local output="$1"
+    local pattern="$2"
+    local test_name="${3:-test}"
+
+    if echo "$output" | grep -q "$pattern"; then
+        echo "  [FAIL] $test_name"
+        echo "  Did not expect to find: $pattern"
+        echo "  In output:"
+        echo "$output" | sed 's/^/    /'
+        return 1
+    else
+        echo "  [PASS] $test_name"
+        return 0
+    fi
+}
+
+# Check if output matches a count
+# Usage: assert_count "output" "pattern" expected_count "test name"
+assert_count() {
+    local output="$1"
+    local pattern="$2"
+    local expected="$3"
+    local test_name="${4:-test}"
+
+    local actual=$(echo "$output" | grep -c "$pattern" || echo "0")
+
+    if [ "$actual" -eq "$expected" ]; then
+        echo "  [PASS] $test_name (found $actual instances)"
+        return 0
+    else
+        echo "  [FAIL] $test_name"
+        echo "  Expected $expected instances of: $pattern"
+        echo "  Found $actual instances"
+        echo "  In output:"
+        echo "$output" | sed 's/^/    /'
+        return 1
+    fi
+}
+
+# Check if pattern A appears before pattern B
+# Usage: assert_order "output" "pattern_a" "pattern_b" "test name"
+assert_order() {
+    local output="$1"
+    local pattern_a="$2"
+    local pattern_b="$3"
+    local test_name="${4:-test}"
+
+    # Get line numbers where patterns appear
+    local line_a=$(echo "$output" | grep -n "$pattern_a" | head -1 | cut -d: -f1)
+    local line_b=$(echo "$output" | grep -n "$pattern_b" | head -1 | cut -d: -f1)
+
+    if [ -z "$line_a" ]; then
+        echo "  [FAIL] $test_name: pattern A not found: $pattern_a"
+        return 1
+    fi
+
+    if [ -z "$line_b" ]; then
+        echo "  [FAIL] $test_name: pattern B not found: $pattern_b"
+        return 1
+    fi
+
+    if [ "$line_a" -lt "$line_b" ]; then
+        echo "  [PASS] $test_name (A at line $line_a, B at line $line_b)"
+        return 0
+    else
+        echo "  [FAIL] $test_name"
+        echo "  Expected '$pattern_a' before '$pattern_b'"
+        echo "  But found A at line $line_a, B at line $line_b"
+        return 1
+    fi
+}
+
+# Create a temporary test project directory
+# Usage: test_project=$(create_test_project)
+create_test_project() {
+    local test_dir=$(mktemp -d)
+    echo "$test_dir"
+}
+
+# Cleanup test project
+# Usage: cleanup_test_project "$test_dir"
+cleanup_test_project() {
+    local test_dir="$1"
+    if [ -d "$test_dir" ]; then
+        rm -rf "$test_dir"
+    fi
+}
+
+# Create a simple plan file for testing
+# Usage: create_test_plan "$project_dir" "$plan_name"
+create_test_plan() {
+    local project_dir="$1"
+    local plan_name="${2:-test-plan}"
+    local plan_file="$project_dir/docs/superpowers/plans/$plan_name.md"
+
+    mkdir -p "$(dirname "$plan_file")"
+
+    cat > "$plan_file" <<'EOF'
+# Test Implementation Plan
+
+## Task 1: Create Hello Function
+
+Create a simple hello function that returns "Hello, World!".
+
+**File:** `src/hello.js`
+
+**Implementation:**
+```javascript
+export function hello() {
+  return "Hello, World!";
+}
+```
+
+**Tests:** Write a test that verifies the function returns the expected string.
+
+**Verification:** `npm test`
+
+## Task 2: Create Goodbye Function
+
+Create a goodbye function that takes a name and returns a goodbye message.
+
+**File:** `src/goodbye.js`
+
+**Implementation:**
+```javascript
+export function goodbye(name) {
+  return `Goodbye, ${name}!`;
+}
+```
+
+**Tests:** Write tests for:
+- Default name
+- Custom name
+- Edge cases (empty string, null)
+
+**Verification:** `npm test`
+EOF
+
+    echo "$plan_file"
+}
+
+# Export functions for use in tests
+export -f run_claude
+export -f assert_contains
+export -f assert_not_contains
+export -f assert_count
+export -f assert_order
+export -f create_test_project
+export -f cleanup_test_project
+export -f create_test_plan

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

@@ -0,0 +1,314 @@
+#!/usr/bin/env bash
+# Integration Test: subagent-driven-development workflow
+# Actually executes a plan and verifies the new workflow behaviors
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+source "$SCRIPT_DIR/test-helpers.sh"
+
+echo "========================================"
+echo " Integration Test: subagent-driven-development"
+echo "========================================"
+echo ""
+echo "This test executes a real plan using the skill and verifies:"
+echo "  1. Plan is read once (not per task)"
+echo "  2. Full task text provided to subagents"
+echo "  3. Subagents perform self-review"
+echo "  4. Spec compliance review before code quality"
+echo "  5. Review loops when issues found"
+echo "  6. Spec reviewer reads code independently"
+echo ""
+echo "WARNING: This test may take 10-30 minutes to complete."
+echo ""
+
+# Create test project
+TEST_PROJECT=$(create_test_project)
+echo "Test project: $TEST_PROJECT"
+
+# Trap to cleanup
+trap "cleanup_test_project $TEST_PROJECT" EXIT
+
+# Set up minimal Node.js project
+cd "$TEST_PROJECT"
+
+cat > package.json <<'EOF'
+{
+  "name": "test-project",
+  "version": "1.0.0",
+  "type": "module",
+  "scripts": {
+    "test": "node --test"
+  }
+}
+EOF
+
+mkdir -p src test docs/superpowers/plans
+
+# Create a simple implementation plan
+cat > docs/superpowers/plans/implementation-plan.md <<'EOF'
+# Test Implementation Plan
+
+This is a minimal plan to test the subagent-driven-development workflow.
+
+## Task 1: Create Add Function
+
+Create a function that adds two numbers.
+
+**File:** `src/math.js`
+
+**Requirements:**
+- Function named `add`
+- Takes two parameters: `a` and `b`
+- Returns the sum of `a` and `b`
+- Export the function
+
+**Implementation:**
+```javascript
+export function add(a, b) {
+  return a + b;
+}
+```
+
+**Tests:** Create `test/math.test.js` that verifies:
+- `add(2, 3)` returns `5`
+- `add(0, 0)` returns `0`
+- `add(-1, 1)` returns `0`
+
+**Verification:** `npm test`
+
+## Task 2: Create Multiply Function
+
+Create a function that multiplies two numbers.
+
+**File:** `src/math.js` (add to existing file)
+
+**Requirements:**
+- Function named `multiply`
+- Takes two parameters: `a` and `b`
+- Returns the product of `a` and `b`
+- Export the function
+- DO NOT add any extra features (like power, divide, etc.)
+
+**Implementation:**
+```javascript
+export function multiply(a, b) {
+  return a * b;
+}
+```
+
+**Tests:** Add to `test/math.test.js`:
+- `multiply(2, 3)` returns `6`
+- `multiply(0, 5)` returns `0`
+- `multiply(-2, 3)` returns `-6`
+
+**Verification:** `npm test`
+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" --quiet
+
+echo ""
+echo "Project setup complete. Starting execution..."
+echo ""
+
+# Run Claude with subagent-driven-development
+# Capture full output to analyze
+OUTPUT_FILE="$TEST_PROJECT/claude-output.txt"
+
+# Create prompt file
+cat > "$TEST_PROJECT/prompt.txt" <<'EOF'
+I want you to execute the implementation plan at docs/superpowers/plans/implementation-plan.md using the subagent-driven-development skill.
+
+IMPORTANT: Follow the skill exactly. I will be verifying that you:
+1. Read the plan once at the beginning
+2. Provide full task text to subagents (don't make them read files)
+3. Ensure subagents do self-review before reporting
+4. Run spec compliance review before code quality review
+5. Use review loops when issues are found
+
+Begin now. Execute the plan.
+EOF
+
+# Note: We use a longer timeout since this is integration testing
+# Use --allowed-tools to enable tool usage in headless mode
+# IMPORTANT: Run from superpowers directory so local dev skills are available
+PROMPT="Change to directory $TEST_PROJECT and then execute the implementation plan at docs/superpowers/plans/implementation-plan.md using the subagent-driven-development skill.
+
+IMPORTANT: Follow the skill exactly. I will be verifying that you:
+1. Read the plan once at the beginning
+2. Provide full task text to subagents (don't make them read files)
+3. Ensure subagents do self-review before reporting
+4. Run spec compliance review before code quality review
+5. Use review loops when issues are found
+
+Begin now. Execute the plan."
+
+echo "Running Claude (output will be shown below and saved to $OUTPUT_FILE)..."
+echo "================================================================================"
+cd "$SCRIPT_DIR/../.." && timeout 1800 claude -p "$PROMPT" --allowed-tools=all --add-dir "$TEST_PROJECT" --permission-mode bypassPermissions 2>&1 | tee "$OUTPUT_FILE" || {
+    echo ""
+    echo "================================================================================"
+    echo "EXECUTION FAILED (exit code: $?)"
+    exit 1
+}
+echo "================================================================================"
+
+echo ""
+echo "Execution complete. Analyzing results..."
+echo ""
+
+# Find the session transcript
+# Session files are in ~/.claude/projects/-<working-dir>/<session-id>.jsonl
+WORKING_DIR_ESCAPED=$(echo "$SCRIPT_DIR/../.." | sed 's/\//-/g' | sed 's/^-//')
+SESSION_DIR="$HOME/.claude/projects/$WORKING_DIR_ESCAPED"
+
+# Find the most recent session file (created during this test run)
+SESSION_FILE=$(find "$SESSION_DIR" -name "*.jsonl" -type f -mmin -60 2>/dev/null | sort -r | head -1)
+
+if [ -z "$SESSION_FILE" ]; then
+    echo "ERROR: Could not find session transcript file"
+    echo "Looked in: $SESSION_DIR"
+    exit 1
+fi
+
+echo "Analyzing session transcript: $(basename "$SESSION_FILE")"
+echo ""
+
+# Verification tests
+FAILED=0
+
+echo "=== Verification Tests ==="
+echo ""
+
+# Test 1: Skill was invoked
+echo "Test 1: Skill tool invoked..."
+if grep -q '"name":"Skill".*"skill":"superpowers:subagent-driven-development"' "$SESSION_FILE"; then
+    echo "  [PASS] subagent-driven-development skill was invoked"
+else
+    echo "  [FAIL] Skill was not invoked"
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 2: Subagents were used (Task tool)
+echo "Test 2: Subagents dispatched..."
+task_count=$(grep -c '"name":"Task"' "$SESSION_FILE" || echo "0")
+if [ "$task_count" -ge 2 ]; then
+    echo "  [PASS] $task_count subagents dispatched"
+else
+    echo "  [FAIL] Only $task_count subagent(s) dispatched (expected >= 2)"
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 3: TodoWrite was used for tracking
+echo "Test 3: Task tracking..."
+todo_count=$(grep -c '"name":"TodoWrite"' "$SESSION_FILE" || echo "0")
+if [ "$todo_count" -ge 1 ]; then
+    echo "  [PASS] TodoWrite used $todo_count time(s) for task tracking"
+else
+    echo "  [FAIL] TodoWrite not used"
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 6: Implementation actually works
+echo "Test 6: Implementation verification..."
+if [ -f "$TEST_PROJECT/src/math.js" ]; then
+    echo "  [PASS] src/math.js created"
+
+    if grep -q "export function add" "$TEST_PROJECT/src/math.js"; then
+        echo "  [PASS] add function exists"
+    else
+        echo "  [FAIL] add function missing"
+        FAILED=$((FAILED + 1))
+    fi
+
+    if grep -q "export function multiply" "$TEST_PROJECT/src/math.js"; then
+        echo "  [PASS] multiply function exists"
+    else
+        echo "  [FAIL] multiply function missing"
+        FAILED=$((FAILED + 1))
+    fi
+else
+    echo "  [FAIL] src/math.js not created"
+    FAILED=$((FAILED + 1))
+fi
+
+if [ -f "$TEST_PROJECT/test/math.test.js" ]; then
+    echo "  [PASS] test/math.test.js created"
+else
+    echo "  [FAIL] test/math.test.js not created"
+    FAILED=$((FAILED + 1))
+fi
+
+# Try running tests
+if cd "$TEST_PROJECT" && npm test > test-output.txt 2>&1; then
+    echo "  [PASS] Tests pass"
+else
+    echo "  [FAIL] Tests failed"
+    cat test-output.txt
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 7: Git commits show proper workflow
+echo "Test 7: Git commit history..."
+commit_count=$(git -C "$TEST_PROJECT" log --oneline | wc -l)
+if [ "$commit_count" -gt 2 ]; then  # Initial + at least 2 task commits
+    echo "  [PASS] Multiple commits created ($commit_count total)"
+else
+    echo "  [FAIL] Too few commits ($commit_count, expected >2)"
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 8: Check for extra features (spec compliance should catch)
+echo "Test 8: No extra features added (spec compliance)..."
+if grep -q "export function divide\|export function power\|export function subtract" "$TEST_PROJECT/src/math.js" 2>/dev/null; then
+    echo "  [WARN] Extra features found (spec review should have caught this)"
+    # Not failing on this as it tests reviewer effectiveness
+else
+    echo "  [PASS] No extra features added"
+fi
+echo ""
+
+# Token Usage Analysis
+echo "========================================="
+echo " Token Usage Analysis"
+echo "========================================="
+echo ""
+python3 "$SCRIPT_DIR/analyze-token-usage.py" "$SESSION_FILE"
+echo ""
+
+# Summary
+echo "========================================"
+echo " Test Summary"
+echo "========================================"
+echo ""
+
+if [ $FAILED -eq 0 ]; then
+    echo "STATUS: PASSED"
+    echo "All verification tests passed!"
+    echo ""
+    echo "The subagent-driven-development skill correctly:"
+    echo "  ✓ Reads plan once at start"
+    echo "  ✓ Provides full task text to subagents"
+    echo "  ✓ Enforces self-review"
+    echo "  ✓ Runs spec compliance before code quality"
+    echo "  ✓ Spec reviewer verifies independently"
+    echo "  ✓ Produces working implementation"
+    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

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

@@ -0,0 +1,165 @@
+#!/usr/bin/env bash
+# Test: subagent-driven-development skill
+# Verifies that the skill is loaded and follows correct workflow
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+source "$SCRIPT_DIR/test-helpers.sh"
+
+echo "=== Test: subagent-driven-development skill ==="
+echo ""
+
+# Test 1: Verify skill can be loaded
+echo "Test 1: Skill loading..."
+
+output=$(run_claude "What is the subagent-driven-development skill? Describe its key steps briefly." 30)
+
+if assert_contains "$output" "subagent-driven-development\|Subagent-Driven Development\|Subagent Driven" "Skill is recognized"; then
+    : # pass
+else
+    exit 1
+fi
+
+if assert_contains "$output" "Load Plan\|read.*plan\|extract.*tasks" "Mentions loading plan"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 2: Verify skill describes correct workflow order
+echo "Test 2: Workflow ordering..."
+
+output=$(run_claude "In the subagent-driven-development skill, what comes first: spec compliance review or code quality review? Be specific about the order." 30)
+
+if assert_order "$output" "spec.*compliance" "code.*quality" "Spec compliance before code quality"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 3: Verify self-review is mentioned
+echo "Test 3: Self-review requirement..."
+
+output=$(run_claude "Does the subagent-driven-development skill require implementers to do self-review? What should they check?" 30)
+
+if assert_contains "$output" "self-review\|self review" "Mentions self-review"; then
+    : # pass
+else
+    exit 1
+fi
+
+if assert_contains "$output" "completeness\|Completeness" "Checks completeness"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 4: Verify plan is read once
+echo "Test 4: Plan reading efficiency..."
+
+output=$(run_claude "In subagent-driven-development, how many times should the controller read the plan file? When does this happen?" 30)
+
+if assert_contains "$output" "once\|one time\|single" "Read plan once"; then
+    : # pass
+else
+    exit 1
+fi
+
+if assert_contains "$output" "Step 1\|beginning\|start\|Load Plan" "Read at beginning"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 5: Verify spec compliance reviewer is skeptical
+echo "Test 5: Spec compliance reviewer mindset..."
+
+output=$(run_claude "What is the spec compliance reviewer's attitude toward the implementer's report in subagent-driven-development?" 30)
+
+if assert_contains "$output" "not trust\|don't trust\|skeptical\|verify.*independently\|suspiciously" "Reviewer is skeptical"; then
+    : # pass
+else
+    exit 1
+fi
+
+if assert_contains "$output" "read.*code\|inspect.*code\|verify.*code" "Reviewer reads code"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 6: Verify review loops
+echo "Test 6: Review loop requirements..."
+
+output=$(run_claude "In subagent-driven-development, what happens if a reviewer finds issues? Is it a one-time review or a loop?" 30)
+
+if assert_contains "$output" "loop\|again\|repeat\|until.*approved\|until.*compliant" "Review loops mentioned"; then
+    : # pass
+else
+    exit 1
+fi
+
+if assert_contains "$output" "implementer.*fix\|fix.*issues" "Implementer fixes issues"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 7: Verify full task text is provided
+echo "Test 7: Task context provision..."
+
+output=$(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)
+
+if assert_contains "$output" "provide.*directly\|full.*text\|paste\|include.*prompt" "Provides text directly"; then
+    : # pass
+else
+    exit 1
+fi
+
+if assert_not_contains "$output" "read.*file\|open.*file" "Doesn't make subagent read file"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 8: Verify worktree requirement
+echo "Test 8: Worktree requirement..."
+
+output=$(run_claude "What workflow skills are required before using subagent-driven-development? List any prerequisites or required skills." 30)
+
+if assert_contains "$output" "using-git-worktrees\|worktree" "Mentions worktree requirement"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+# Test 9: Verify main branch warning
+echo "Test 9: Main branch red flag..."
+
+output=$(run_claude "In subagent-driven-development, is it okay to start implementation directly on the main branch?" 30)
+
+if assert_contains "$output" "worktree\|feature.*branch\|not.*main\|never.*main\|avoid.*main\|don't.*main\|consent\|permission" "Warns against main branch"; then
+    : # pass
+else
+    exit 1
+fi
+
+echo ""
+
+echo "=== All subagent-driven-development skill tests passed ==="

package/tests/explicit-skill-requests/prompts/action-oriented.txt

@@ -0,0 +1,3 @@
+The plan is done. docs/superpowers/plans/auth-system.md has everything.
+
+Do subagent-driven development on this - start with Task 1, dispatch a subagent, then we'll review.

package/tests/explicit-skill-requests/prompts/after-planning-flow.txt

@@ -0,0 +1,17 @@
+Great, the plan is complete. I've saved it to docs/superpowers/plans/auth-system.md.
+
+Here's a summary of what we designed:
+- Task 1: Add User Model with email/password fields
+- Task 2: Create auth routes for login/register
+- Task 3: Add JWT middleware for protected routes
+- Task 4: Write tests for all auth functionality
+
+Two execution options:
+1. Subagent-Driven (this session) - dispatch a fresh subagent per task
+2. Parallel Session (separate) - open new Claude Code session
+
+Which approach do you want?
+
+---
+
+subagent-driven-development, please