workerssuper 5.0.4

package/tests/claude-code/analyze-token-usage.py

@@ -0,0 +1,168 @@
+#!/usr/bin/env python3
+"""
+Analyze token usage from Claude Code session transcripts.
+Breaks down usage by main session and individual subagents.
+"""
+
+import json
+import sys
+from pathlib import Path
+from collections import defaultdict
+
+def analyze_main_session(filepath):
+    """Analyze a session file and return token usage broken down by agent."""
+    main_usage = {
+        'input_tokens': 0,
+        'output_tokens': 0,
+        'cache_creation': 0,
+        'cache_read': 0,
+        'messages': 0
+    }
+
+    # Track usage per subagent
+    subagent_usage = defaultdict(lambda: {
+        'input_tokens': 0,
+        'output_tokens': 0,
+        'cache_creation': 0,
+        'cache_read': 0,
+        'messages': 0,
+        'description': None
+    })
+
+    with open(filepath, 'r') as f:
+        for line in f:
+            try:
+                data = json.loads(line)
+
+                # Main session assistant messages
+                if data.get('type') == 'assistant' and 'message' in data:
+                    main_usage['messages'] += 1
+                    msg_usage = data['message'].get('usage', {})
+                    main_usage['input_tokens'] += msg_usage.get('input_tokens', 0)
+                    main_usage['output_tokens'] += msg_usage.get('output_tokens', 0)
+                    main_usage['cache_creation'] += msg_usage.get('cache_creation_input_tokens', 0)
+                    main_usage['cache_read'] += msg_usage.get('cache_read_input_tokens', 0)
+
+                # Subagent tool results
+                if data.get('type') == 'user' and 'toolUseResult' in data:
+                    result = data['toolUseResult']
+                    if 'usage' in result and 'agentId' in result:
+                        agent_id = result['agentId']
+                        usage = result['usage']
+
+                        # Get description from prompt if available
+                        if subagent_usage[agent_id]['description'] is None:
+                            prompt = result.get('prompt', '')
+                            # Extract first line as description
+                            first_line = prompt.split('\n')[0] if prompt else f"agent-{agent_id}"
+                            if first_line.startswith('You are '):
+                                first_line = first_line[8:]  # Remove "You are "
+                            subagent_usage[agent_id]['description'] = first_line[:60]
+
+                        subagent_usage[agent_id]['messages'] += 1
+                        subagent_usage[agent_id]['input_tokens'] += usage.get('input_tokens', 0)
+                        subagent_usage[agent_id]['output_tokens'] += usage.get('output_tokens', 0)
+                        subagent_usage[agent_id]['cache_creation'] += usage.get('cache_creation_input_tokens', 0)
+                        subagent_usage[agent_id]['cache_read'] += usage.get('cache_read_input_tokens', 0)
+            except Exception:
+                pass
+
+    return main_usage, dict(subagent_usage)
+
+def format_tokens(n):
+    """Format token count with thousands separators."""
+    return f"{n:,}"
+
+def calculate_cost(usage, input_cost_per_m=3.0, output_cost_per_m=15.0):
+    """Calculate estimated cost in dollars."""
+    total_input = usage['input_tokens'] + usage['cache_creation'] + usage['cache_read']
+    input_cost = total_input * input_cost_per_m / 1_000_000
+    output_cost = usage['output_tokens'] * output_cost_per_m / 1_000_000
+    return input_cost + output_cost
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: analyze-token-usage.py <session-file.jsonl>")
+        sys.exit(1)
+
+    main_session_file = sys.argv[1]
+
+    if not Path(main_session_file).exists():
+        print(f"Error: Session file not found: {main_session_file}")
+        sys.exit(1)
+
+    # Analyze the session
+    main_usage, subagent_usage = analyze_main_session(main_session_file)
+
+    print("=" * 100)
+    print("TOKEN USAGE ANALYSIS")
+    print("=" * 100)
+    print()
+
+    # Print breakdown
+    print("Usage Breakdown:")
+    print("-" * 100)
+    print(f"{'Agent':<15} {'Description':<35} {'Msgs':>5} {'Input':>10} {'Output':>10} {'Cache':>10} {'Cost':>8}")
+    print("-" * 100)
+
+    # Main session
+    cost = calculate_cost(main_usage)
+    print(f"{'main':<15} {'Main session (coordinator)':<35} "
+          f"{main_usage['messages']:>5} "
+          f"{format_tokens(main_usage['input_tokens']):>10} "
+          f"{format_tokens(main_usage['output_tokens']):>10} "
+          f"{format_tokens(main_usage['cache_read']):>10} "
+          f"${cost:>7.2f}")
+
+    # Subagents (sorted by agent ID)
+    for agent_id in sorted(subagent_usage.keys()):
+        usage = subagent_usage[agent_id]
+        cost = calculate_cost(usage)
+        desc = usage['description'] or f"agent-{agent_id}"
+        print(f"{agent_id:<15} {desc:<35} "
+              f"{usage['messages']:>5} "
+              f"{format_tokens(usage['input_tokens']):>10} "
+              f"{format_tokens(usage['output_tokens']):>10} "
+              f"{format_tokens(usage['cache_read']):>10} "
+              f"${cost:>7.2f}")
+
+    print("-" * 100)
+
+    # Calculate totals
+    total_usage = {
+        'input_tokens': main_usage['input_tokens'],
+        'output_tokens': main_usage['output_tokens'],
+        'cache_creation': main_usage['cache_creation'],
+        'cache_read': main_usage['cache_read'],
+        'messages': main_usage['messages']
+    }
+
+    for usage in subagent_usage.values():
+        total_usage['input_tokens'] += usage['input_tokens']
+        total_usage['output_tokens'] += usage['output_tokens']
+        total_usage['cache_creation'] += usage['cache_creation']
+        total_usage['cache_read'] += usage['cache_read']
+        total_usage['messages'] += usage['messages']
+
+    total_input = total_usage['input_tokens'] + total_usage['cache_creation'] + total_usage['cache_read']
+    total_tokens = total_input + total_usage['output_tokens']
+    total_cost = calculate_cost(total_usage)
+
+    print()
+    print("TOTALS:")
+    print(f"  Total messages:         {format_tokens(total_usage['messages'])}")
+    print(f"  Input tokens:           {format_tokens(total_usage['input_tokens'])}")
+    print(f"  Output tokens:          {format_tokens(total_usage['output_tokens'])}")
+    print(f"  Cache creation tokens:  {format_tokens(total_usage['cache_creation'])}")
+    print(f"  Cache read tokens:      {format_tokens(total_usage['cache_read'])}")
+    print()
+    print(f"  Total input (incl cache): {format_tokens(total_input)}")
+    print(f"  Total tokens:             {format_tokens(total_tokens)}")
+    print()
+    print(f"  Estimated cost: ${total_cost:.2f}")
+    print("  (at $3/$15 per M tokens for input/output)")
+    print()
+    print("=" * 100)
+
+if __name__ == '__main__':
+    main()

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

@@ -0,0 +1,187 @@
+#!/usr/bin/env bash
+# Test runner for Claude Code skills
+# Tests skills by invoking Claude Code CLI and verifying behavior
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+cd "$SCRIPT_DIR"
+
+echo "========================================"
+echo " Claude Code Skills Test Suite"
+echo "========================================"
+echo ""
+echo "Repository: $(cd ../.. && pwd)"
+echo "Test time: $(date)"
+echo "Claude version: $(claude --version 2>/dev/null || echo 'not found')"
+echo ""
+
+# Check if Claude Code is available
+if ! command -v claude &> /dev/null; then
+    echo "ERROR: Claude Code CLI not found"
+    echo "Install Claude Code first: https://code.claude.com"
+    exit 1
+fi
+
+# Parse command line arguments
+VERBOSE=false
+SPECIFIC_TEST=""
+TIMEOUT=300  # Default 5 minute timeout per test
+RUN_INTEGRATION=false
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --verbose|-v)
+            VERBOSE=true
+            shift
+            ;;
+        --test|-t)
+            SPECIFIC_TEST="$2"
+            shift 2
+            ;;
+        --timeout)
+            TIMEOUT="$2"
+            shift 2
+            ;;
+        --integration|-i)
+            RUN_INTEGRATION=true
+            shift
+            ;;
+        --help|-h)
+            echo "Usage: $0 [options]"
+            echo ""
+            echo "Options:"
+            echo "  --verbose, -v        Show verbose output"
+            echo "  --test, -t NAME      Run only the specified test"
+            echo "  --timeout SECONDS    Set timeout per test (default: 300)"
+            echo "  --integration, -i    Run integration tests (slow, 10-30 min)"
+            echo "  --help, -h           Show this help"
+            echo ""
+            echo "Tests:"
+            echo "  test-subagent-driven-development.sh  Test skill loading and requirements"
+            echo ""
+            echo "Integration Tests (use --integration):"
+            echo "  test-subagent-driven-development-integration.sh  Full workflow execution"
+            exit 0
+            ;;
+        *)
+            echo "Unknown option: $1"
+            echo "Use --help for usage information"
+            exit 1
+            ;;
+    esac
+done
+
+# List of skill tests to run (fast unit tests)
+tests=(
+    "test-subagent-driven-development.sh"
+)
+
+# Integration tests (slow, full execution)
+integration_tests=(
+    "test-subagent-driven-development-integration.sh"
+)
+
+# Add integration tests if requested
+if [ "$RUN_INTEGRATION" = true ]; then
+    tests+=("${integration_tests[@]}")
+fi
+
+# Filter to specific test if requested
+if [ -n "$SPECIFIC_TEST" ]; then
+    tests=("$SPECIFIC_TEST")
+fi
+
+# Track results
+passed=0
+failed=0
+skipped=0
+
+# Run each test
+for test in "${tests[@]}"; do
+    echo "----------------------------------------"
+    echo "Running: $test"
+    echo "----------------------------------------"
+
+    test_path="$SCRIPT_DIR/$test"
+
+    if [ ! -f "$test_path" ]; then
+        echo "  [SKIP] Test file not found: $test"
+        skipped=$((skipped + 1))
+        continue
+    fi
+
+    if [ ! -x "$test_path" ]; then
+        echo "  Making $test executable..."
+        chmod +x "$test_path"
+    fi
+
+    start_time=$(date +%s)
+
+    if [ "$VERBOSE" = true ]; then
+        if timeout "$TIMEOUT" bash "$test_path"; then
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            echo ""
+            echo "  [PASS] $test (${duration}s)"
+            passed=$((passed + 1))
+        else
+            exit_code=$?
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            echo ""
+            if [ $exit_code -eq 124 ]; then
+                echo "  [FAIL] $test (timeout after ${TIMEOUT}s)"
+            else
+                echo "  [FAIL] $test (${duration}s)"
+            fi
+            failed=$((failed + 1))
+        fi
+    else
+        # Capture output for non-verbose mode
+        if output=$(timeout "$TIMEOUT" bash "$test_path" 2>&1); then
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            echo "  [PASS] (${duration}s)"
+            passed=$((passed + 1))
+        else
+            exit_code=$?
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            if [ $exit_code -eq 124 ]; then
+                echo "  [FAIL] (timeout after ${TIMEOUT}s)"
+            else
+                echo "  [FAIL] (${duration}s)"
+            fi
+            echo ""
+            echo "  Output:"
+            echo "$output" | sed 's/^/    /'
+            failed=$((failed + 1))
+        fi
+    fi
+
+    echo ""
+done
+
+# Print summary
+echo "========================================"
+echo " Test Results Summary"
+echo "========================================"
+echo ""
+echo "  Passed:  $passed"
+echo "  Failed:  $failed"
+echo "  Skipped: $skipped"
+echo ""
+
+if [ "$RUN_INTEGRATION" = false ] && [ ${#integration_tests[@]} -gt 0 ]; then
+    echo "Note: Integration tests were not run (they take 10-30 minutes)."
+    echo "Use --integration flag to run full workflow execution tests."
+    echo ""
+fi
+
+if [ $failed -gt 0 ]; then
+    echo "STATUS: FAILED"
+    exit 1
+else
+    echo "STATUS: PASSED"
+    exit 0
+fi

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

@@ -0,0 +1,177 @@
+#!/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