wip: [01-stabilize] paused at task 1/1 - OCR Hallucination Immune logic via Semantic delta window and fret-isolation

.agent/vendor/superpowers/tests/brainstorm-server/package-lock.json

@@ -0,0 +1,36 @@
+{
+  "name": "brainstorm-server-tests",
+  "version": "1.0.0",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "brainstorm-server-tests",
+      "version": "1.0.0",
+      "dependencies": {
+        "ws": "^8.19.0"
+      }
+    },
+    "node_modules/ws": {
+      "version": "8.19.0",
+      "resolved": "https://registry.npmjs.org/ws/-/ws-8.19.0.tgz",
+      "integrity": "sha512-blAT2mjOEIi0ZzruJfIhb3nps74PRWTCz1IjglWEEpQl5XS/UNama6u2/rjFkDDouqr4L67ry+1aGIALViWjDg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=10.0.0"
+      },
+      "peerDependencies": {
+        "bufferutil": "^4.0.1",
+        "utf-8-validate": ">=5.0.2"
+      },
+      "peerDependenciesMeta": {
+        "bufferutil": {
+          "optional": true
+        },
+        "utf-8-validate": {
+          "optional": true
+        }
+      }
+    }
+  }
+}

.agent/vendor/superpowers/tests/brainstorm-server/package.json

@@ -0,0 +1,10 @@
+{
+  "name": "brainstorm-server-tests",
+  "version": "1.0.0",
+  "scripts": {
+    "test": "node server.test.js"
+  },
+  "dependencies": {
+    "ws": "^8.19.0"
+  }
+}

.agent/vendor/superpowers/tests/brainstorm-server/server.test.js

@@ -0,0 +1,427 @@
+/**
+ * Integration tests for the brainstorm server.
+ *
+ * Tests the full server behavior: HTTP serving, WebSocket communication,
+ * file watching, and the brainstorming workflow.
+ *
+ * Uses the `ws` npm package as a test client (test-only dependency,
+ * not shipped to end users).
+ */
+
+const { spawn } = require('child_process');
+const http = require('http');
+const WebSocket = require('ws');
+const fs = require('fs');
+const path = require('path');
+const assert = require('assert');
+
+const SERVER_PATH = path.join(__dirname, '../../skills/brainstorming/scripts/server.cjs');
+const TEST_PORT = 3334;
+const TEST_DIR = '/tmp/brainstorm-test';
+const CONTENT_DIR = path.join(TEST_DIR, 'content');
+const STATE_DIR = path.join(TEST_DIR, 'state');
+
+function cleanup() {
+  if (fs.existsSync(TEST_DIR)) {
+    fs.rmSync(TEST_DIR, { recursive: true });
+  }
+}
+
+async function sleep(ms) {
+  return new Promise(resolve => setTimeout(resolve, ms));
+}
+
+async function fetch(url) {
+  return new Promise((resolve, reject) => {
+    http.get(url, (res) => {
+      let data = '';
+      res.on('data', chunk => data += chunk);
+      res.on('end', () => resolve({
+        status: res.statusCode,
+        headers: res.headers,
+        body: data
+      }));
+    }).on('error', reject);
+  });
+}
+
+function startServer() {
+  return spawn('node', [SERVER_PATH], {
+    env: { ...process.env, BRAINSTORM_PORT: TEST_PORT, BRAINSTORM_DIR: TEST_DIR }
+  });
+}
+
+async function waitForServer(server) {
+  let stdout = '';
+  let stderr = '';
+
+  return new Promise((resolve, reject) => {
+    server.stdout.on('data', (data) => {
+      stdout += data.toString();
+      if (stdout.includes('server-started')) {
+        resolve({ stdout, stderr, getStdout: () => stdout });
+      }
+    });
+    server.stderr.on('data', (data) => { stderr += data.toString(); });
+    server.on('error', reject);
+
+    setTimeout(() => reject(new Error(`Server didn't start. stderr: ${stderr}`)), 5000);
+  });
+}
+
+async function runTests() {
+  cleanup();
+
+  const server = startServer();
+  let stdoutAccum = '';
+  server.stdout.on('data', (data) => { stdoutAccum += data.toString(); });
+
+  const { stdout: initialStdout } = await waitForServer(server);
+  let passed = 0;
+  let failed = 0;
+
+  function test(name, fn) {
+    return fn().then(() => {
+      console.log(`  PASS: ${name}`);
+      passed++;
+    }).catch(e => {
+      console.log(`  FAIL: ${name}`);
+      console.log(`    ${e.message}`);
+      failed++;
+    });
+  }
+
+  try {
+    // ========== Server Startup ==========
+    console.log('\n--- Server Startup ---');
+
+    await test('outputs server-started JSON on startup', () => {
+      const msg = JSON.parse(initialStdout.trim());
+      assert.strictEqual(msg.type, 'server-started');
+      assert.strictEqual(msg.port, TEST_PORT);
+      assert(msg.url, 'Should include URL');
+      assert(msg.screen_dir, 'Should include screen_dir');
+      return Promise.resolve();
+    });
+
+    await test('writes server-info to state/', () => {
+      const infoPath = path.join(STATE_DIR, 'server-info');
+      assert(fs.existsSync(infoPath), 'state/server-info should exist');
+      const info = JSON.parse(fs.readFileSync(infoPath, 'utf-8').trim());
+      assert.strictEqual(info.type, 'server-started');
+      assert.strictEqual(info.port, TEST_PORT);
+      assert.strictEqual(info.screen_dir, CONTENT_DIR, 'screen_dir should point to content/');
+      assert.strictEqual(info.state_dir, STATE_DIR, 'state_dir should point to state/');
+      return Promise.resolve();
+    });
+
+    // ========== HTTP Serving ==========
+    console.log('\n--- HTTP Serving ---');
+
+    await test('serves waiting page when no screens exist', async () => {
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert.strictEqual(res.status, 200);
+      assert(res.body.includes('Waiting for the agent'), 'Should show waiting message');
+    });
+
+    await test('injects helper.js into waiting page', async () => {
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert(res.body.includes('WebSocket'), 'Should have helper.js injected');
+      assert(res.body.includes('toggleSelect'), 'Should have toggleSelect from helper');
+      assert(res.body.includes('brainstorm'), 'Should have brainstorm API from helper');
+    });
+
+    await test('returns Content-Type text/html', async () => {
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert(res.headers['content-type'].includes('text/html'), 'Should be text/html');
+    });
+
+    await test('serves full HTML documents as-is (not wrapped)', async () => {
+      const fullDoc = '<!DOCTYPE html>\n<html><head><title>Custom</title></head><body><h1>Custom Page</h1></body></html>';
+      fs.writeFileSync(path.join(CONTENT_DIR, 'full-doc.html'), fullDoc);
+      await sleep(300);
+
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert(res.body.includes('<h1>Custom Page</h1>'), 'Should contain original content');
+      assert(res.body.includes('WebSocket'), 'Should still inject helper.js');
+      assert(!res.body.includes('indicator-bar'), 'Should NOT wrap in frame template');
+    });
+
+    await test('wraps content fragments in frame template', async () => {
+      const fragment = '<h2>Pick a layout</h2>\n<div class="options"><div class="option" data-choice="a"><div class="letter">A</div></div></div>';
+      fs.writeFileSync(path.join(CONTENT_DIR, 'fragment.html'), fragment);
+      await sleep(300);
+
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert(res.body.includes('indicator-bar'), 'Fragment should get indicator bar');
+      assert(!res.body.includes('<!-- CONTENT -->'), 'Placeholder should be replaced');
+      assert(res.body.includes('Pick a layout'), 'Fragment content should be present');
+      assert(res.body.includes('data-choice="a"'), 'Fragment interactive elements intact');
+    });
+
+    await test('serves newest file by mtime', async () => {
+      fs.writeFileSync(path.join(CONTENT_DIR, 'older.html'), '<h2>Older</h2>');
+      await sleep(100);
+      fs.writeFileSync(path.join(CONTENT_DIR, 'newer.html'), '<h2>Newer</h2>');
+      await sleep(300);
+
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert(res.body.includes('Newer'), 'Should serve newest file');
+    });
+
+    await test('ignores non-html files for serving', async () => {
+      // Write a newer non-HTML file — should still serve newest .html
+      fs.writeFileSync(path.join(CONTENT_DIR, 'data.json'), '{"not": "html"}');
+      await sleep(300);
+
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert(res.body.includes('Newer'), 'Should still serve newest HTML');
+      assert(!res.body.includes('"not"'), 'Should not serve JSON');
+    });
+
+    await test('returns 404 for non-root paths', async () => {
+      const res = await fetch(`http://localhost:${TEST_PORT}/other`);
+      assert.strictEqual(res.status, 404);
+    });
+
+    // ========== WebSocket Communication ==========
+    console.log('\n--- WebSocket Communication ---');
+
+    await test('accepts WebSocket upgrade on /', async () => {
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise((resolve, reject) => {
+        ws.on('open', resolve);
+        ws.on('error', reject);
+      });
+      ws.close();
+    });
+
+    await test('relays user events to stdout with source field', async () => {
+      stdoutAccum = '';
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws.on('open', resolve));
+
+      ws.send(JSON.stringify({ type: 'click', text: 'Test Button' }));
+      await sleep(300);
+
+      assert(stdoutAccum.includes('"source":"user-event"'), 'Should tag with source');
+      assert(stdoutAccum.includes('Test Button'), 'Should include event data');
+      ws.close();
+    });
+
+    await test('writes choice events to state/events', async () => {
+      // Clean up events from prior tests
+      const eventsFile = path.join(STATE_DIR, 'events');
+      if (fs.existsSync(eventsFile)) fs.unlinkSync(eventsFile);
+
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws.on('open', resolve));
+
+      ws.send(JSON.stringify({ type: 'click', choice: 'b', text: 'Option B' }));
+      await sleep(300);
+
+      assert(fs.existsSync(eventsFile), '.events should exist');
+      const lines = fs.readFileSync(eventsFile, 'utf-8').trim().split('\n');
+      const event = JSON.parse(lines[lines.length - 1]);
+      assert.strictEqual(event.choice, 'b');
+      assert.strictEqual(event.text, 'Option B');
+      ws.close();
+    });
+
+    await test('does NOT write non-choice events to state/events', async () => {
+      const eventsFile = path.join(STATE_DIR, 'events');
+      if (fs.existsSync(eventsFile)) fs.unlinkSync(eventsFile);
+
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws.on('open', resolve));
+
+      ws.send(JSON.stringify({ type: 'hover', text: 'Something' }));
+      await sleep(300);
+
+      // Non-choice events should not create .events file
+      assert(!fs.existsSync(eventsFile), '.events should not exist for non-choice events');
+      ws.close();
+    });
+
+    await test('handles multiple concurrent WebSocket clients', async () => {
+      const ws1 = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      const ws2 = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await Promise.all([
+        new Promise(resolve => ws1.on('open', resolve)),
+        new Promise(resolve => ws2.on('open', resolve))
+      ]);
+
+      let ws1Reload = false;
+      let ws2Reload = false;
+      ws1.on('message', (data) => {
+        if (JSON.parse(data.toString()).type === 'reload') ws1Reload = true;
+      });
+      ws2.on('message', (data) => {
+        if (JSON.parse(data.toString()).type === 'reload') ws2Reload = true;
+      });
+
+      fs.writeFileSync(path.join(CONTENT_DIR, 'multi-client.html'), '<h2>Multi</h2>');
+      await sleep(500);
+
+      assert(ws1Reload, 'Client 1 should receive reload');
+      assert(ws2Reload, 'Client 2 should receive reload');
+      ws1.close();
+      ws2.close();
+    });
+
+    await test('cleans up closed clients from broadcast list', async () => {
+      const ws1 = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws1.on('open', resolve));
+      ws1.close();
+      await sleep(100);
+
+      // This should not throw even though ws1 is closed
+      fs.writeFileSync(path.join(CONTENT_DIR, 'after-close.html'), '<h2>After</h2>');
+      await sleep(300);
+      // If we got here without error, the test passes
+    });
+
+    await test('handles malformed JSON from client gracefully', async () => {
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws.on('open', resolve));
+
+      // Send invalid JSON — server should not crash
+      ws.send('not json at all {{{');
+      await sleep(300);
+
+      // Verify server is still responsive
+      const res = await fetch(`http://localhost:${TEST_PORT}/`);
+      assert.strictEqual(res.status, 200, 'Server should still be running');
+      ws.close();
+    });
+
+    // ========== File Watching ==========
+    console.log('\n--- File Watching ---');
+
+    await test('sends reload on new .html file', async () => {
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws.on('open', resolve));
+
+      let gotReload = false;
+      ws.on('message', (data) => {
+        if (JSON.parse(data.toString()).type === 'reload') gotReload = true;
+      });
+
+      fs.writeFileSync(path.join(CONTENT_DIR, 'watch-new.html'), '<h2>New</h2>');
+      await sleep(500);
+
+      assert(gotReload, 'Should send reload on new file');
+      ws.close();
+    });
+
+    await test('sends reload on .html file change', async () => {
+      const filePath = path.join(CONTENT_DIR, 'watch-change.html');
+      fs.writeFileSync(filePath, '<h2>Original</h2>');
+      await sleep(500);
+
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws.on('open', resolve));
+
+      let gotReload = false;
+      ws.on('message', (data) => {
+        if (JSON.parse(data.toString()).type === 'reload') gotReload = true;
+      });
+
+      fs.writeFileSync(filePath, '<h2>Modified</h2>');
+      await sleep(500);
+
+      assert(gotReload, 'Should send reload on file change');
+      ws.close();
+    });
+
+    await test('does NOT send reload for non-.html files', async () => {
+      const ws = new WebSocket(`ws://localhost:${TEST_PORT}`);
+      await new Promise(resolve => ws.on('open', resolve));
+
+      let gotReload = false;
+      ws.on('message', (data) => {
+        if (JSON.parse(data.toString()).type === 'reload') gotReload = true;
+      });
+
+      fs.writeFileSync(path.join(CONTENT_DIR, 'data.txt'), 'not html');
+      await sleep(500);
+
+      assert(!gotReload, 'Should NOT reload for non-HTML files');
+      ws.close();
+    });
+
+    await test('clears state/events on new screen', async () => {
+      // Create an events file
+      const eventsFile = path.join(STATE_DIR, 'events');
+      fs.writeFileSync(eventsFile, '{"choice":"a"}\n');
+      assert(fs.existsSync(eventsFile));
+
+      fs.writeFileSync(path.join(CONTENT_DIR, 'clear-events.html'), '<h2>New screen</h2>');
+      await sleep(500);
+
+      assert(!fs.existsSync(eventsFile), 'state/events should be cleared on new screen');
+    });
+
+    await test('logs screen-added on new file', async () => {
+      stdoutAccum = '';
+      fs.writeFileSync(path.join(CONTENT_DIR, 'log-test.html'), '<h2>Log</h2>');
+      await sleep(500);
+
+      assert(stdoutAccum.includes('screen-added'), 'Should log screen-added');
+    });
+
+    await test('logs screen-updated on file change', async () => {
+      const filePath = path.join(CONTENT_DIR, 'log-update.html');
+      fs.writeFileSync(filePath, '<h2>V1</h2>');
+      await sleep(500);
+
+      stdoutAccum = '';
+      fs.writeFileSync(filePath, '<h2>V2</h2>');
+      await sleep(500);
+
+      assert(stdoutAccum.includes('screen-updated'), 'Should log screen-updated');
+    });
+
+    // ========== Helper.js Content ==========
+    console.log('\n--- Helper.js Verification ---');
+
+    await test('helper.js defines required APIs', () => {
+      const helperContent = fs.readFileSync(
+        path.join(__dirname, '../../skills/brainstorming/scripts/helper.js'), 'utf-8'
+      );
+      assert(helperContent.includes('toggleSelect'), 'Should define toggleSelect');
+      assert(helperContent.includes('sendEvent'), 'Should define sendEvent');
+      assert(helperContent.includes('selectedChoice'), 'Should track selectedChoice');
+      assert(helperContent.includes('brainstorm'), 'Should expose brainstorm API');
+      return Promise.resolve();
+    });
+
+    // ========== Frame Template ==========
+    console.log('\n--- Frame Template Verification ---');
+
+    await test('frame template has required structure', () => {
+      const template = fs.readFileSync(
+        path.join(__dirname, '../../skills/brainstorming/scripts/frame-template.html'), 'utf-8'
+      );
+      assert(template.includes('indicator-bar'), 'Should have indicator bar');
+      assert(template.includes('indicator-text'), 'Should have indicator text');
+      assert(template.includes('<!-- CONTENT -->'), 'Should have content placeholder');
+      assert(template.includes('claude-content'), 'Should have content container');
+      return Promise.resolve();
+    });
+
+    // ========== Summary ==========
+    console.log(`\n--- Results: ${passed} passed, ${failed} failed ---`);
+    if (failed > 0) process.exit(1);
+
+  } finally {
+    server.kill();
+    await sleep(100);
+    cleanup();
+  }
+}
+
+runTests().catch(err => {
+  console.error('Test failed:', err);
+  process.exit(1);
+});

.agent/vendor/superpowers/tests/brainstorm-server/windows-lifecycle.test.sh

@@ -0,0 +1,351 @@
+#!/usr/bin/env bash
+# Windows lifecycle tests for the brainstorm server.
+#
+# Verifies that the brainstorm server survives the 60-second lifecycle
+# check on Windows, where OWNER_PID monitoring is disabled because the
+# MSYS2 PID namespace is invisible to Node.js.
+#
+# Requirements:
+#   - Node.js in PATH
+#   - Run from the repository root, or set SUPERPOWERS_ROOT
+#   - On Windows: Git Bash (OSTYPE=msys*)
+#
+# Usage:
+#   bash tests/brainstorm-server/windows-lifecycle.test.sh
+set -uo pipefail
+
+# ========== Configuration ==========
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="${SUPERPOWERS_ROOT:-$(cd "$SCRIPT_DIR/../.." && pwd)}"
+START_SCRIPT="$REPO_ROOT/skills/brainstorming/scripts/start-server.sh"
+STOP_SCRIPT="$REPO_ROOT/skills/brainstorming/scripts/stop-server.sh"
+SERVER_JS="$REPO_ROOT/skills/brainstorming/scripts/server.js"
+
+TEST_DIR="${TMPDIR:-/tmp}/brainstorm-win-test-$$"
+
+passed=0
+failed=0
+skipped=0
+
+# ========== Helpers ==========
+
+cleanup() {
+  # Kill any server processes we started
+  for pidvar in SERVER_PID CONTROL_PID STOP_TEST_PID; do
+    pid="${!pidvar:-}"
+    if [[ -n "$pid" ]]; then
+      kill "$pid" 2>/dev/null || true
+      wait "$pid" 2>/dev/null || true
+    fi
+  done
+  if [[ -n "${TEST_DIR:-}" && -d "$TEST_DIR" ]]; then
+    rm -rf "$TEST_DIR"
+  fi
+}
+trap cleanup EXIT
+
+pass() {
+  echo "  PASS: $1"
+  passed=$((passed + 1))
+}
+
+fail() {
+  echo "  FAIL: $1"
+  echo "    $2"
+  failed=$((failed + 1))
+}
+
+skip() {
+  echo "  SKIP: $1 ($2)"
+  skipped=$((skipped + 1))
+}
+
+wait_for_server_info() {
+  local dir="$1"
+  for _ in $(seq 1 50); do
+    if [[ -f "$dir/.server-info" ]]; then
+      return 0
+    fi
+    sleep 0.1
+  done
+  return 1
+}
+
+get_port_from_info() {
+  # Read the port from .server-info. Use grep/sed instead of Node.js
+  # to avoid MSYS2-to-Windows path translation issues.
+  grep -o '"port":[0-9]*' "$1/.server-info" | head -1 | sed 's/"port"://'
+}
+
+http_check() {
+  local port="$1"
+  node -e "
+    const http = require('http');
+    http.get('http://localhost:$port/', (res) => {
+      process.exit(res.statusCode === 200 ? 0 : 1);
+    }).on('error', () => process.exit(1));
+  " 2>/dev/null
+}
+
+# ========== Platform Detection ==========
+
+echo ""
+echo "=== Brainstorm Server Windows Lifecycle Tests ==="
+echo "Platform: ${OSTYPE:-unknown}"
+echo "MSYSTEM: ${MSYSTEM:-unset}"
+echo "Node: $(node --version 2>/dev/null || echo 'not found')"
+echo ""
+
+is_windows="false"
+case "${OSTYPE:-}" in
+  msys*|cygwin*|mingw*) is_windows="true" ;;
+esac
+if [[ -n "${MSYSTEM:-}" ]]; then
+  is_windows="true"
+fi
+
+if [[ "$is_windows" != "true" ]]; then
+  echo "NOTE: Not running on Windows/MSYS2 (OSTYPE=${OSTYPE:-unset})."
+  echo "Windows-specific tests will be skipped. Tests 4-6 still run."
+  echo ""
+fi
+
+mkdir -p "$TEST_DIR"
+
+SERVER_PID=""
+CONTROL_PID=""
+STOP_TEST_PID=""
+
+# ========== Test 1: OWNER_PID is empty on Windows ==========
+
+echo "--- Owner PID Resolution ---"
+
+if [[ "$is_windows" == "true" ]]; then
+  # Replicate the PID resolution logic from start-server.sh lines 104-112
+  TEST_OWNER_PID="$(ps -o ppid= -p "$PPID" 2>/dev/null | tr -d ' ' || true)"
+  if [[ -z "$TEST_OWNER_PID" || "$TEST_OWNER_PID" == "1" ]]; then
+    TEST_OWNER_PID="$PPID"
+  fi
+  # The fix: clear on Windows
+  case "${OSTYPE:-}" in
+    msys*|cygwin*|mingw*) TEST_OWNER_PID="" ;;
+  esac
+
+  if [[ -z "$TEST_OWNER_PID" ]]; then
+    pass "OWNER_PID is empty on Windows after fix"
+  else
+    fail "OWNER_PID is empty on Windows after fix" \
+         "Expected empty, got '$TEST_OWNER_PID'"
+  fi
+else
+  skip "OWNER_PID is empty on Windows" "not on Windows"
+fi
+
+# ========== Test 2: start-server.sh passes empty BRAINSTORM_OWNER_PID ==========
+
+if [[ "$is_windows" == "true" ]]; then
+  # Use a fake 'node' that captures the env var and exits
+  FAKE_NODE_DIR="$TEST_DIR/fake-bin"
+  mkdir -p "$FAKE_NODE_DIR"
+  cat > "$FAKE_NODE_DIR/node" <<'FAKENODE'
+#!/usr/bin/env bash
+echo "CAPTURED_OWNER_PID=${BRAINSTORM_OWNER_PID:-__UNSET__}"
+exit 0
+FAKENODE
+  chmod +x "$FAKE_NODE_DIR/node"
+
+  captured=$(PATH="$FAKE_NODE_DIR:$PATH" bash "$START_SCRIPT" --project-dir "$TEST_DIR/session" --foreground 2>/dev/null || true)
+  owner_pid_value=$(echo "$captured" | grep "CAPTURED_OWNER_PID=" | head -1 | sed 's/CAPTURED_OWNER_PID=//')
+
+  if [[ "$owner_pid_value" == "" || "$owner_pid_value" == "__UNSET__" ]]; then
+    pass "start-server.sh passes empty BRAINSTORM_OWNER_PID on Windows"
+  else
+    fail "start-server.sh passes empty BRAINSTORM_OWNER_PID on Windows" \
+         "Expected empty or unset, got '$owner_pid_value'"
+  fi
+
+  rm -rf "$FAKE_NODE_DIR" "$TEST_DIR/session"
+else
+  skip "start-server.sh passes empty BRAINSTORM_OWNER_PID" "not on Windows"
+fi
+
+# ========== Test 3: Auto-foreground detection on Windows ==========
+
+echo ""
+echo "--- Foreground Mode Detection ---"
+
+if [[ "$is_windows" == "true" ]]; then
+  FAKE_NODE_DIR="$TEST_DIR/fake-bin"
+  mkdir -p "$FAKE_NODE_DIR"
+  cat > "$FAKE_NODE_DIR/node" <<'FAKENODE'
+#!/usr/bin/env bash
+echo "FOREGROUND_MODE=true"
+exit 0
+FAKENODE
+  chmod +x "$FAKE_NODE_DIR/node"
+
+  # Run WITHOUT --foreground flag — Windows should auto-detect
+  captured=$(PATH="$FAKE_NODE_DIR:$PATH" bash "$START_SCRIPT" --project-dir "$TEST_DIR/session2" 2>/dev/null || true)
+
+  if echo "$captured" | grep -q "FOREGROUND_MODE=true"; then
+    pass "Windows auto-detects foreground mode"
+  else
+    fail "Windows auto-detects foreground mode" \
+         "Expected foreground code path, output: $captured"
+  fi
+
+  rm -rf "$FAKE_NODE_DIR" "$TEST_DIR/session2"
+else
+  skip "Windows auto-detects foreground mode" "not on Windows"
+fi
+
+# ========== Test 4: Server survives past 60-second lifecycle check ==========
+
+echo ""
+echo "--- Server Survival (lifecycle check) ---"
+
+mkdir -p "$TEST_DIR/survival"
+
+echo "  Starting server (will wait ~75s to verify survival past lifecycle check)..."
+
+BRAINSTORM_DIR="$TEST_DIR/survival" \
+BRAINSTORM_HOST="127.0.0.1" \
+BRAINSTORM_URL_HOST="localhost" \
+BRAINSTORM_OWNER_PID="" \
+BRAINSTORM_PORT=$((49152 + RANDOM % 16383)) \
+  node "$SERVER_JS" > "$TEST_DIR/survival/.server.log" 2>&1 &
+SERVER_PID=$!
+
+if ! wait_for_server_info "$TEST_DIR/survival"; then
+  fail "Server starts successfully" "Server did not write .server-info within 5 seconds"
+  kill "$SERVER_PID" 2>/dev/null || true
+  SERVER_PID=""
+else
+  pass "Server starts successfully with empty OWNER_PID"
+
+  SERVER_PORT=$(get_port_from_info "$TEST_DIR/survival")
+
+  sleep 75
+
+  if kill -0 "$SERVER_PID" 2>/dev/null; then
+    pass "Server is still alive after 75 seconds"
+  else
+    fail "Server is still alive after 75 seconds" \
+         "Server died. Log tail: $(tail -5 "$TEST_DIR/survival/.server.log" 2>/dev/null)"
+  fi
+
+  if http_check "$SERVER_PORT"; then
+    pass "Server responds to HTTP after lifecycle check window"
+  else
+    fail "Server responds to HTTP after lifecycle check window" \
+         "HTTP request to port $SERVER_PORT failed"
+  fi
+
+  if grep -q "owner process exited" "$TEST_DIR/survival/.server.log" 2>/dev/null; then
+    fail "No 'owner process exited' in logs" \
+         "Found spurious owner-exit shutdown in log"
+  else
+    pass "No 'owner process exited' in logs"
+  fi
+
+  kill "$SERVER_PID" 2>/dev/null || true
+  wait "$SERVER_PID" 2>/dev/null || true
+  SERVER_PID=""
+fi
+
+# ========== Test 5: Bad OWNER_PID causes shutdown (control) ==========
+
+echo ""
+echo "--- Control: Bad OWNER_PID causes shutdown ---"
+
+mkdir -p "$TEST_DIR/control"
+
+# Find a PID that does not exist
+BAD_PID=99999
+while kill -0 "$BAD_PID" 2>/dev/null; do
+  BAD_PID=$((BAD_PID + 1))
+done
+
+BRAINSTORM_DIR="$TEST_DIR/control" \
+BRAINSTORM_HOST="127.0.0.1" \
+BRAINSTORM_URL_HOST="localhost" \
+BRAINSTORM_OWNER_PID="$BAD_PID" \
+BRAINSTORM_PORT=$((49152 + RANDOM % 16383)) \
+  node "$SERVER_JS" > "$TEST_DIR/control/.server.log" 2>&1 &
+CONTROL_PID=$!
+
+if ! wait_for_server_info "$TEST_DIR/control"; then
+  fail "Control server starts" "Server did not write .server-info within 5 seconds"
+  kill "$CONTROL_PID" 2>/dev/null || true
+  CONTROL_PID=""
+else
+  pass "Control server starts with bad OWNER_PID=$BAD_PID"
+
+  echo "  Waiting ~75s for lifecycle check to kill server..."
+  sleep 75
+
+  if kill -0 "$CONTROL_PID" 2>/dev/null; then
+    fail "Control server self-terminates with bad OWNER_PID" \
+         "Server is still alive (expected it to die)"
+    kill "$CONTROL_PID" 2>/dev/null || true
+  else
+    pass "Control server self-terminates with bad OWNER_PID"
+  fi
+
+  if grep -q "owner process exited" "$TEST_DIR/control/.server.log" 2>/dev/null; then
+    pass "Control server logs 'owner process exited'"
+  else
+    fail "Control server logs 'owner process exited'" \
+         "Log tail: $(tail -5 "$TEST_DIR/control/.server.log" 2>/dev/null)"
+  fi
+fi
+
+wait "$CONTROL_PID" 2>/dev/null || true
+CONTROL_PID=""
+
+# ========== Test 6: stop-server.sh cleanly stops the server ==========
+
+echo ""
+echo "--- Clean Shutdown ---"
+
+mkdir -p "$TEST_DIR/stop-test"
+
+BRAINSTORM_DIR="$TEST_DIR/stop-test" \
+BRAINSTORM_HOST="127.0.0.1" \
+BRAINSTORM_URL_HOST="localhost" \
+BRAINSTORM_OWNER_PID="" \
+BRAINSTORM_PORT=$((49152 + RANDOM % 16383)) \
+  node "$SERVER_JS" > "$TEST_DIR/stop-test/.server.log" 2>&1 &
+STOP_TEST_PID=$!
+echo "$STOP_TEST_PID" > "$TEST_DIR/stop-test/.server.pid"
+
+if ! wait_for_server_info "$TEST_DIR/stop-test"; then
+  fail "Stop-test server starts" "Server did not start"
+  kill "$STOP_TEST_PID" 2>/dev/null || true
+  STOP_TEST_PID=""
+else
+  bash "$STOP_SCRIPT" "$TEST_DIR/stop-test" >/dev/null 2>&1 || true
+  sleep 1
+
+  if ! kill -0 "$STOP_TEST_PID" 2>/dev/null; then
+    pass "stop-server.sh cleanly stops the server"
+  else
+    fail "stop-server.sh cleanly stops the server" \
+         "Server PID $STOP_TEST_PID is still alive after stop"
+    kill "$STOP_TEST_PID" 2>/dev/null || true
+  fi
+fi
+
+wait "$STOP_TEST_PID" 2>/dev/null || true
+STOP_TEST_PID=""
+
+# ========== Summary ==========
+
+echo ""
+echo "=== Results: $passed passed, $failed failed, $skipped skipped ==="
+
+if [[ $failed -gt 0 ]]; then
+  exit 1
+fi
+exit 0

.agent/vendor/superpowers/tests/brainstorm-server/ws-protocol.test.js

@@ -0,0 +1,392 @@
+/**
+ * Unit tests for the zero-dependency WebSocket protocol implementation.
+ *
+ * Tests the WebSocket frame encoding/decoding, handshake computation,
+ * and protocol-level behavior independent of the HTTP server.
+ *
+ * The module under test exports:
+ *   - computeAcceptKey(clientKey) -> string
+ *   - encodeFrame(opcode, payload) -> Buffer
+ *   - decodeFrame(buffer) -> { opcode, payload, bytesConsumed } | null
+ *   - OPCODES: { TEXT, CLOSE, PING, PONG }
+ */
+
+const assert = require('assert');
+const crypto = require('crypto');
+const path = require('path');
+
+// The module under test — will be the new zero-dep server file
+const SERVER_PATH = path.join(__dirname, '../../skills/brainstorming/scripts/server.cjs');
+let ws;
+
+try {
+  ws = require(SERVER_PATH);
+} catch (e) {
+  // Module doesn't exist yet (TDD — tests written before implementation)
+  console.error(`Cannot load ${SERVER_PATH}: ${e.message}`);
+  console.error('This is expected if running tests before implementation.');
+  process.exit(1);
+}
+
+function runTests() {
+  let passed = 0;
+  let failed = 0;
+
+  function test(name, fn) {
+    try {
+      fn();
+      console.log(`  PASS: ${name}`);
+      passed++;
+    } catch (e) {
+      console.log(`  FAIL: ${name}`);
+      console.log(`    ${e.message}`);
+      failed++;
+    }
+  }
+
+  // ========== Handshake ==========
+  console.log('\n--- WebSocket Handshake ---');
+
+  test('computeAcceptKey produces correct RFC 6455 accept value', () => {
+    // RFC 6455 Section 4.2.2 example
+    // The magic GUID is "258EAFA5-E914-47DA-95CA-C5AB0DC85B11"
+    const clientKey = 'dGhlIHNhbXBsZSBub25jZQ==';
+    const expected = 's3pPLMBiTxaQ9kYGzzhZRbK+xOo=';
+    assert.strictEqual(ws.computeAcceptKey(clientKey), expected);
+  });
+
+  test('computeAcceptKey produces valid base64 for random keys', () => {
+    for (let i = 0; i < 10; i++) {
+      const randomKey = crypto.randomBytes(16).toString('base64');
+      const result = ws.computeAcceptKey(randomKey);
+      // Result should be valid base64
+      assert.strictEqual(Buffer.from(result, 'base64').toString('base64'), result);
+      // SHA-1 output is 20 bytes, base64 encoded = 28 chars
+      assert.strictEqual(result.length, 28);
+    }
+  });
+
+  // ========== Frame Encoding ==========
+  console.log('\n--- Frame Encoding (server -> client) ---');
+
+  test('encodes small text frame (< 126 bytes)', () => {
+    const payload = 'Hello';
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, Buffer.from(payload));
+    // FIN bit + TEXT opcode = 0x81, length = 5
+    assert.strictEqual(frame[0], 0x81);
+    assert.strictEqual(frame[1], 5);
+    assert.strictEqual(frame.slice(2).toString(), 'Hello');
+    assert.strictEqual(frame.length, 7);
+  });
+
+  test('encodes empty text frame', () => {
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, Buffer.alloc(0));
+    assert.strictEqual(frame[0], 0x81);
+    assert.strictEqual(frame[1], 0);
+    assert.strictEqual(frame.length, 2);
+  });
+
+  test('encodes medium text frame (126-65535 bytes)', () => {
+    const payload = Buffer.alloc(200, 0x41); // 200 'A's
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, payload);
+    assert.strictEqual(frame[0], 0x81);
+    assert.strictEqual(frame[1], 126); // extended length marker
+    assert.strictEqual(frame.readUInt16BE(2), 200);
+    assert.strictEqual(frame.slice(4).toString(), payload.toString());
+    assert.strictEqual(frame.length, 204);
+  });
+
+  test('encodes frame at exactly 126 bytes (boundary)', () => {
+    const payload = Buffer.alloc(126, 0x42);
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, payload);
+    assert.strictEqual(frame[1], 126); // extended length marker
+    assert.strictEqual(frame.readUInt16BE(2), 126);
+    assert.strictEqual(frame.length, 130);
+  });
+
+  test('encodes frame at exactly 125 bytes (max small)', () => {
+    const payload = Buffer.alloc(125, 0x43);
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, payload);
+    assert.strictEqual(frame[1], 125);
+    assert.strictEqual(frame.length, 127);
+  });
+
+  test('encodes large frame (> 65535 bytes)', () => {
+    const payload = Buffer.alloc(70000, 0x44);
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, payload);
+    assert.strictEqual(frame[0], 0x81);
+    assert.strictEqual(frame[1], 127); // 64-bit length marker
+    // 8-byte extended length at offset 2
+    const len = Number(frame.readBigUInt64BE(2));
+    assert.strictEqual(len, 70000);
+    assert.strictEqual(frame.length, 10 + 70000);
+  });
+
+  test('encodes close frame', () => {
+    const frame = ws.encodeFrame(ws.OPCODES.CLOSE, Buffer.alloc(0));
+    assert.strictEqual(frame[0], 0x88); // FIN + CLOSE
+    assert.strictEqual(frame[1], 0);
+  });
+
+  test('encodes pong frame with payload', () => {
+    const payload = Buffer.from('ping-data');
+    const frame = ws.encodeFrame(ws.OPCODES.PONG, payload);
+    assert.strictEqual(frame[0], 0x8A); // FIN + PONG
+    assert.strictEqual(frame[1], payload.length);
+    assert.strictEqual(frame.slice(2).toString(), 'ping-data');
+  });
+
+  test('server frames are never masked (per RFC 6455)', () => {
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, Buffer.from('test'));
+    // Bit 7 of byte 1 is the mask bit — must be 0 for server frames
+    assert.strictEqual(frame[1] & 0x80, 0);
+  });
+
+  // ========== Frame Decoding ==========
+  console.log('\n--- Frame Decoding (client -> server) ---');
+
+  // Helper: create a masked client frame
+  function makeClientFrame(opcode, payload, fin = true) {
+    const buf = Buffer.from(payload);
+    const mask = crypto.randomBytes(4);
+    const masked = Buffer.alloc(buf.length);
+    for (let i = 0; i < buf.length; i++) {
+      masked[i] = buf[i] ^ mask[i % 4];
+    }
+
+    let header;
+    const finBit = fin ? 0x80 : 0x00;
+    if (buf.length < 126) {
+      header = Buffer.alloc(6);
+      header[0] = finBit | opcode;
+      header[1] = 0x80 | buf.length; // mask bit set
+      mask.copy(header, 2);
+    } else if (buf.length < 65536) {
+      header = Buffer.alloc(8);
+      header[0] = finBit | opcode;
+      header[1] = 0x80 | 126;
+      header.writeUInt16BE(buf.length, 2);
+      mask.copy(header, 4);
+    } else {
+      header = Buffer.alloc(14);
+      header[0] = finBit | opcode;
+      header[1] = 0x80 | 127;
+      header.writeBigUInt64BE(BigInt(buf.length), 2);
+      mask.copy(header, 10);
+    }
+
+    return Buffer.concat([header, masked]);
+  }
+
+  test('decodes small masked text frame', () => {
+    const frame = makeClientFrame(0x01, 'Hello');
+    const result = ws.decodeFrame(frame);
+    assert(result, 'Should return a result');
+    assert.strictEqual(result.opcode, ws.OPCODES.TEXT);
+    assert.strictEqual(result.payload.toString(), 'Hello');
+    assert.strictEqual(result.bytesConsumed, frame.length);
+  });
+
+  test('decodes empty masked text frame', () => {
+    const frame = makeClientFrame(0x01, '');
+    const result = ws.decodeFrame(frame);
+    assert(result, 'Should return a result');
+    assert.strictEqual(result.opcode, ws.OPCODES.TEXT);
+    assert.strictEqual(result.payload.length, 0);
+  });
+
+  test('decodes medium masked text frame (126-65535 bytes)', () => {
+    const payload = 'A'.repeat(200);
+    const frame = makeClientFrame(0x01, payload);
+    const result = ws.decodeFrame(frame);
+    assert(result, 'Should return a result');
+    assert.strictEqual(result.payload.toString(), payload);
+  });
+
+  test('decodes large masked text frame (> 65535 bytes)', () => {
+    const payload = 'B'.repeat(70000);
+    const frame = makeClientFrame(0x01, payload);
+    const result = ws.decodeFrame(frame);
+    assert(result, 'Should return a result');
+    assert.strictEqual(result.payload.length, 70000);
+    assert.strictEqual(result.payload.toString(), payload);
+  });
+
+  test('decodes masked close frame', () => {
+    const frame = makeClientFrame(0x08, '');
+    const result = ws.decodeFrame(frame);
+    assert(result, 'Should return a result');
+    assert.strictEqual(result.opcode, ws.OPCODES.CLOSE);
+  });
+
+  test('decodes masked ping frame', () => {
+    const frame = makeClientFrame(0x09, 'ping!');
+    const result = ws.decodeFrame(frame);
+    assert(result, 'Should return a result');
+    assert.strictEqual(result.opcode, ws.OPCODES.PING);
+    assert.strictEqual(result.payload.toString(), 'ping!');
+  });
+
+  test('returns null for incomplete frame (not enough header bytes)', () => {
+    const result = ws.decodeFrame(Buffer.from([0x81]));
+    assert.strictEqual(result, null, 'Should return null for 1-byte buffer');
+  });
+
+  test('returns null for incomplete frame (header ok, payload truncated)', () => {
+    // Create a valid frame then truncate it
+    const frame = makeClientFrame(0x01, 'Hello World');
+    const truncated = frame.slice(0, frame.length - 3);
+    const result = ws.decodeFrame(truncated);
+    assert.strictEqual(result, null, 'Should return null for truncated frame');
+  });
+
+  test('returns null for incomplete extended-length header', () => {
+    // Frame claiming 16-bit length but only 3 bytes total
+    const buf = Buffer.alloc(3);
+    buf[0] = 0x81;
+    buf[1] = 0x80 | 126; // masked, 16-bit extended
+    // Missing the 2 length bytes + mask
+    const result = ws.decodeFrame(buf);
+    assert.strictEqual(result, null);
+  });
+
+  test('rejects unmasked client frame', () => {
+    // Server MUST reject unmasked client frames per RFC 6455 Section 5.1
+    const buf = Buffer.alloc(7);
+    buf[0] = 0x81; // FIN + TEXT
+    buf[1] = 5;    // length 5, NO mask bit
+    Buffer.from('Hello').copy(buf, 2);
+    assert.throws(() => ws.decodeFrame(buf), /mask/i, 'Should reject unmasked client frame');
+  });
+
+  test('handles multiple frames in a single buffer', () => {
+    const frame1 = makeClientFrame(0x01, 'first');
+    const frame2 = makeClientFrame(0x01, 'second');
+    const combined = Buffer.concat([frame1, frame2]);
+
+    const result1 = ws.decodeFrame(combined);
+    assert(result1, 'Should decode first frame');
+    assert.strictEqual(result1.payload.toString(), 'first');
+    assert.strictEqual(result1.bytesConsumed, frame1.length);
+
+    const result2 = ws.decodeFrame(combined.slice(result1.bytesConsumed));
+    assert(result2, 'Should decode second frame');
+    assert.strictEqual(result2.payload.toString(), 'second');
+  });
+
+  test('correctly unmasks with all mask byte values', () => {
+    // Use a known mask to verify unmasking arithmetic
+    const payload = Buffer.from('ABCDEFGH');
+    const mask = Buffer.from([0xFF, 0x00, 0xAA, 0x55]);
+    const masked = Buffer.alloc(payload.length);
+    for (let i = 0; i < payload.length; i++) {
+      masked[i] = payload[i] ^ mask[i % 4];
+    }
+
+    // Build frame manually
+    const header = Buffer.alloc(6);
+    header[0] = 0x81; // FIN + TEXT
+    header[1] = 0x80 | payload.length;
+    mask.copy(header, 2);
+    const frame = Buffer.concat([header, masked]);
+
+    const result = ws.decodeFrame(frame);
+    assert.strictEqual(result.payload.toString(), 'ABCDEFGH');
+  });
+
+  // ========== Frame Encoding Boundary at 65535/65536 ==========
+  console.log('\n--- Frame Size Boundaries ---');
+
+  test('encodes frame at exactly 65535 bytes (max 16-bit)', () => {
+    const payload = Buffer.alloc(65535, 0x45);
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, payload);
+    assert.strictEqual(frame[1], 126);
+    assert.strictEqual(frame.readUInt16BE(2), 65535);
+    assert.strictEqual(frame.length, 4 + 65535);
+  });
+
+  test('encodes frame at exactly 65536 bytes (min 64-bit)', () => {
+    const payload = Buffer.alloc(65536, 0x46);
+    const frame = ws.encodeFrame(ws.OPCODES.TEXT, payload);
+    assert.strictEqual(frame[1], 127);
+    assert.strictEqual(Number(frame.readBigUInt64BE(2)), 65536);
+    assert.strictEqual(frame.length, 10 + 65536);
+  });
+
+  test('decodes frame at 65535 bytes boundary', () => {
+    const payload = 'X'.repeat(65535);
+    const frame = makeClientFrame(0x01, payload);
+    const result = ws.decodeFrame(frame);
+    assert(result);
+    assert.strictEqual(result.payload.length, 65535);
+  });
+
+  test('decodes frame at 65536 bytes boundary', () => {
+    const payload = 'Y'.repeat(65536);
+    const frame = makeClientFrame(0x01, payload);
+    const result = ws.decodeFrame(frame);
+    assert(result);
+    assert.strictEqual(result.payload.length, 65536);
+  });
+
+  // ========== Close Frame with Status Code ==========
+  console.log('\n--- Close Frame Details ---');
+
+  test('decodes close frame with status code', () => {
+    // Close frame payload: 2-byte status code + optional reason
+    const statusBuf = Buffer.alloc(2);
+    statusBuf.writeUInt16BE(1000); // Normal closure
+    const frame = makeClientFrame(0x08, statusBuf);
+    const result = ws.decodeFrame(frame);
+    assert.strictEqual(result.opcode, ws.OPCODES.CLOSE);
+    assert.strictEqual(result.payload.readUInt16BE(0), 1000);
+  });
+
+  test('decodes close frame with status code and reason', () => {
+    const reason = 'Normal shutdown';
+    const payload = Buffer.alloc(2 + reason.length);
+    payload.writeUInt16BE(1000);
+    payload.write(reason, 2);
+    const frame = makeClientFrame(0x08, payload);
+    const result = ws.decodeFrame(frame);
+    assert.strictEqual(result.opcode, ws.OPCODES.CLOSE);
+    assert.strictEqual(result.payload.slice(2).toString(), reason);
+  });
+
+  // ========== JSON Roundtrip ==========
+  console.log('\n--- JSON Message Roundtrip ---');
+
+  test('roundtrip encode/decode of JSON message', () => {
+    const msg = { type: 'reload' };
+    const payload = Buffer.from(JSON.stringify(msg));
+    const serverFrame = ws.encodeFrame(ws.OPCODES.TEXT, payload);
+
+    // Verify we can read what we encoded (unmasked server frame)
+    // Server frames don't go through decodeFrame (that expects masked),
+    // so just verify the payload bytes directly
+    let offset;
+    if (serverFrame[1] < 126) {
+      offset = 2;
+    } else if (serverFrame[1] === 126) {
+      offset = 4;
+    } else {
+      offset = 10;
+    }
+    const decoded = JSON.parse(serverFrame.slice(offset).toString());
+    assert.deepStrictEqual(decoded, msg);
+  });
+
+  test('roundtrip masked client JSON message', () => {
+    const msg = { type: 'click', choice: 'a', text: 'Option A', timestamp: 1706000101 };
+    const frame = makeClientFrame(0x01, JSON.stringify(msg));
+    const result = ws.decodeFrame(frame);
+    const decoded = JSON.parse(result.payload.toString());
+    assert.deepStrictEqual(decoded, msg);
+  });
+
+  // ========== Summary ==========
+  console.log(`\n--- Results: ${passed} passed, ${failed} failed ---`);
+  if (failed > 0) process.exit(1);
+}
+
+runTests();

.agent/vendor/superpowers/tests/claude-code/README.md

@@ -0,0 +1,158 @@
+# Claude Code Skills Tests
+
+Automated tests for superpowers skills using Claude Code CLI.
+
+## Overview
+
+This test suite verifies that skills are loaded correctly and Claude follows them as expected. Tests invoke Claude Code in headless mode (`claude -p`) and verify the behavior.
+
+## Requirements
+
+- Claude Code CLI installed and in PATH (`claude --version` should work)
+- Local superpowers plugin installed (see main README for installation)
+
+## Running Tests
+
+### Run all fast tests (recommended):
+```bash
+./run-skill-tests.sh
+```
+
+### Run integration tests (slow, 10-30 minutes):
+```bash
+./run-skill-tests.sh --integration
+```
+
+### Run specific test:
+```bash
+./run-skill-tests.sh --test test-subagent-driven-development.sh
+```
+
+### Run with verbose output:
+```bash
+./run-skill-tests.sh --verbose
+```
+
+### Set custom timeout:
+```bash
+./run-skill-tests.sh --timeout 1800  # 30 minutes for integration tests
+```
+
+## Test Structure
+
+### test-helpers.sh
+Common functions for skills testing:
+- `run_claude "prompt" [timeout]` - Run Claude with prompt
+- `assert_contains output pattern name` - Verify pattern exists
+- `assert_not_contains output pattern name` - Verify pattern absent
+- `assert_count output pattern count name` - Verify exact count
+- `assert_order output pattern_a pattern_b name` - Verify order
+- `create_test_project` - Create temp test directory
+- `create_test_plan project_dir` - Create sample plan file
+
+### Test Files
+
+Each test file:
+1. Sources `test-helpers.sh`
+2. Runs Claude Code with specific prompts
+3. Verifies expected behavior using assertions
+4. Returns 0 on success, non-zero on failure
+
+## Example Test
+
+```bash
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+source "$SCRIPT_DIR/test-helpers.sh"
+
+echo "=== Test: My Skill ==="
+
+# Ask Claude about the skill
+output=$(run_claude "What does the my-skill skill do?" 30)
+
+# Verify response
+assert_contains "$output" "expected behavior" "Skill describes behavior"
+
+echo "=== All tests passed ==="
+```
+
+## Current Tests
+
+### Fast Tests (run by default)
+
+#### test-subagent-driven-development.sh
+Tests skill content and requirements (~2 minutes):
+- Skill loading and accessibility
+- Workflow ordering (spec compliance before code quality)
+- Self-review requirements documented
+- Plan reading efficiency documented
+- Spec compliance reviewer skepticism documented
+- Review loops documented
+- Task context provision documented
+
+### Integration Tests (use --integration flag)
+
+#### test-subagent-driven-development-integration.sh
+Full workflow execution test (~10-30 minutes):
+- Creates real test project with Node.js setup
+- Creates implementation plan with 2 tasks
+- Executes plan using subagent-driven-development
+- Verifies actual behaviors:
+  - Plan read once at start (not per task)
+  - Full task text provided in subagent prompts
+  - Subagents perform self-review before reporting
+  - Spec compliance review happens before code quality
+  - Spec reviewer reads code independently
+  - Working implementation is produced
+  - Tests pass
+  - Proper git commits created
+
+**What it tests:**
+- The workflow actually works end-to-end
+- Our improvements are actually applied
+- Subagents follow the skill correctly
+- Final code is functional and tested
+
+## Adding New Tests
+
+1. Create new test file: `test-<skill-name>.sh`
+2. Source test-helpers.sh
+3. Write tests using `run_claude` and assertions
+4. Add to test list in `run-skill-tests.sh`
+5. Make executable: `chmod +x test-<skill-name>.sh`
+
+## Timeout Considerations
+
+- Default timeout: 5 minutes per test
+- Claude Code may take time to respond
+- Adjust with `--timeout` if needed
+- Tests should be focused to avoid long runs
+
+## Debugging Failed Tests
+
+With `--verbose`, you'll see full Claude output:
+```bash
+./run-skill-tests.sh --verbose --test test-subagent-driven-development.sh
+```
+
+Without verbose, only failures show output.
+
+## CI/CD Integration
+
+To run in CI:
+```bash
+# Run with explicit timeout for CI environments
+./run-skill-tests.sh --timeout 900
+
+# Exit code 0 = success, non-zero = failure
+```
+
+## Notes
+
+- Tests verify skill *instructions*, not full execution
+- Full workflow tests would be very slow
+- Focus on verifying key skill requirements
+- Tests should be deterministic
+- Avoid testing implementation details

.agent/vendor/superpowers/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()

.agent/vendor/superpowers/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

.agent/vendor/superpowers/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

.agent/vendor/superpowers/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

.agent/vendor/superpowers/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

.agent/vendor/superpowers/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 ==="

.agent/vendor/superpowers/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.

.agent/vendor/superpowers/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

.agent/vendor/superpowers/tests/explicit-skill-requests/prompts/claude-suggested-it.txt

@@ -0,0 +1,11 @@
+[Previous assistant message]:
+Plan complete and saved to docs/superpowers/plans/auth-system.md.
+
+Two execution options:
+1. Subagent-Driven (this session) - I dispatch a fresh subagent per task, review between tasks, fast iteration within this conversation
+2. Parallel Session (separate) - Open a new Claude Code session with the execute-plan skill, batch execution with review checkpoints
+
+Which approach do you want to use for implementation?
+
+[Your response]:
+subagent-driven-development, please

.agent/vendor/superpowers/tests/explicit-skill-requests/prompts/i-know-what-sdd-means.txt

@@ -0,0 +1,8 @@
+I have my implementation plan ready at docs/superpowers/plans/auth-system.md.
+
+I want to use subagent-driven-development to execute it. That means:
+- Dispatch a fresh subagent for each task in the plan
+- Review the output between tasks
+- Keep iteration fast within this conversation
+
+Let's start - please read the plan and begin dispatching subagents for each task.

.agent/vendor/superpowers/tests/explicit-skill-requests/prompts/mid-conversation-execute-plan.txt

@@ -0,0 +1,3 @@
+I have a plan at docs/superpowers/plans/auth-system.md that's ready to implement.
+
+subagent-driven-development, please

.agent/vendor/superpowers/tests/explicit-skill-requests/prompts/please-use-brainstorming.txt

@@ -0,0 +1 @@
+please use the brainstorming skill to help me think through this feature

.agent/vendor/superpowers/tests/explicit-skill-requests/prompts/skip-formalities.txt

@@ -0,0 +1,3 @@
+Plan is at docs/superpowers/plans/auth-system.md.
+
+subagent-driven-development, please. Don't waste time - just read the plan and start dispatching subagents immediately.

.agent/vendor/superpowers/tests/explicit-skill-requests/prompts/subagent-driven-development-please.txt

@@ -0,0 +1 @@
+subagent-driven-development, please

.agent/vendor/superpowers/tests/explicit-skill-requests/prompts/use-systematic-debugging.txt

@@ -0,0 +1 @@
+use systematic-debugging to figure out what's wrong

.agent/vendor/superpowers/tests/explicit-skill-requests/run-all.sh

@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+# Run all explicit skill request tests
+# Usage: ./run-all.sh
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROMPTS_DIR="$SCRIPT_DIR/prompts"
+
+echo "=== Running All Explicit Skill Request Tests ==="
+echo ""
+
+PASSED=0
+FAILED=0
+RESULTS=""
+
+# Test: subagent-driven-development, please
+echo ">>> Test 1: subagent-driven-development-please"
+if "$SCRIPT_DIR/run-test.sh" "subagent-driven-development" "$PROMPTS_DIR/subagent-driven-development-please.txt"; then
+    PASSED=$((PASSED + 1))
+    RESULTS="$RESULTS\nPASS: subagent-driven-development-please"
+else
+    FAILED=$((FAILED + 1))
+    RESULTS="$RESULTS\nFAIL: subagent-driven-development-please"
+fi
+echo ""
+
+# Test: use systematic-debugging
+echo ">>> Test 2: use-systematic-debugging"
+if "$SCRIPT_DIR/run-test.sh" "systematic-debugging" "$PROMPTS_DIR/use-systematic-debugging.txt"; then
+    PASSED=$((PASSED + 1))
+    RESULTS="$RESULTS\nPASS: use-systematic-debugging"
+else
+    FAILED=$((FAILED + 1))
+    RESULTS="$RESULTS\nFAIL: use-systematic-debugging"
+fi
+echo ""
+
+# Test: please use brainstorming
+echo ">>> Test 3: please-use-brainstorming"
+if "$SCRIPT_DIR/run-test.sh" "brainstorming" "$PROMPTS_DIR/please-use-brainstorming.txt"; then
+    PASSED=$((PASSED + 1))
+    RESULTS="$RESULTS\nPASS: please-use-brainstorming"
+else
+    FAILED=$((FAILED + 1))
+    RESULTS="$RESULTS\nFAIL: please-use-brainstorming"
+fi
+echo ""
+
+# Test: mid-conversation execute plan
+echo ">>> Test 4: mid-conversation-execute-plan"
+if "$SCRIPT_DIR/run-test.sh" "subagent-driven-development" "$PROMPTS_DIR/mid-conversation-execute-plan.txt"; then
+    PASSED=$((PASSED + 1))
+    RESULTS="$RESULTS\nPASS: mid-conversation-execute-plan"
+else
+    FAILED=$((FAILED + 1))
+    RESULTS="$RESULTS\nFAIL: mid-conversation-execute-plan"
+fi
+echo ""
+
+echo "=== Summary ==="
+echo -e "$RESULTS"
+echo ""
+echo "Passed: $PASSED"
+echo "Failed: $FAILED"
+echo "Total: $((PASSED + FAILED))"
+
+if [ "$FAILED" -gt 0 ]; then
+    exit 1
+fi

.agent/vendor/superpowers/tests/explicit-skill-requests/run-claude-describes-sdd.sh

@@ -0,0 +1,100 @@
+#!/usr/bin/env bash
+# Test where Claude explicitly describes subagent-driven-development before user requests it
+# This mimics the original failure scenario
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/claude-describes"
+mkdir -p "$OUTPUT_DIR"
+
+PROJECT_DIR="$OUTPUT_DIR/project"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
+
+echo "=== Test: Claude Describes SDD First ==="
+echo "Output dir: $OUTPUT_DIR"
+echo ""
+
+cd "$PROJECT_DIR"
+
+# Create a plan
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
+# Auth System Implementation Plan
+
+## Task 1: Add User Model
+Create user model with email and password fields.
+
+## Task 2: Add Auth Routes
+Create login and register endpoints.
+
+## Task 3: Add JWT Middleware
+Protect routes with JWT validation.
+EOF
+
+# Turn 1: Have Claude describe execution options including SDD
+echo ">>> Turn 1: Ask Claude to describe execution options..."
+claude -p "I have a plan at docs/superpowers/plans/auth-system.md. Tell me about my options for executing it, including what subagent-driven-development means and how it works." \
+    --model haiku \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 3 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn1.json" 2>&1 || true
+echo "Done."
+
+# Turn 2: THE CRITICAL TEST - now that Claude has explained it
+echo ">>> Turn 2: Request subagent-driven-development..."
+FINAL_LOG="$OUTPUT_DIR/turn2.json"
+claude -p "subagent-driven-development, please" \
+    --continue \
+    --model haiku \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$FINAL_LOG" 2>&1 || true
+echo "Done."
+echo ""
+
+echo "=== Results ==="
+
+# Check Turn 1 to see if Claude described SDD
+echo "Turn 1 - Claude's description of options (excerpt):"
+grep '"type":"assistant"' "$OUTPUT_DIR/turn1.json" | head -1 | jq -r '.message.content[0].text // .message.content' 2>/dev/null | head -c 800 || echo "  (could not extract)"
+echo ""
+echo "---"
+echo ""
+
+# Check final turn
+SKILL_PATTERN='"skill":"([^"]*:)?subagent-driven-development"'
+if grep -q '"name":"Skill"' "$FINAL_LOG" && grep -qE "$SKILL_PATTERN" "$FINAL_LOG"; then
+    echo "PASS: Skill was triggered after Claude described it"
+    TRIGGERED=true
+else
+    echo "FAIL: Skill was NOT triggered (Claude may have thought it already knew)"
+    TRIGGERED=false
+
+    echo ""
+    echo "Tools invoked in final turn:"
+    grep '"type":"tool_use"' "$FINAL_LOG" | grep -o '"name":"[^"]*"' | sort -u | head -10 || echo "  (none)"
+
+    echo ""
+    echo "Final turn response:"
+    grep '"type":"assistant"' "$FINAL_LOG" | head -1 | jq -r '.message.content[0].text // .message.content' 2>/dev/null | head -c 800 || echo "  (could not extract)"
+fi
+
+echo ""
+echo "Skills triggered in final turn:"
+grep -o '"skill":"[^"]*"' "$FINAL_LOG" 2>/dev/null | sort -u || echo "  (none)"
+
+echo ""
+echo "Logs in: $OUTPUT_DIR"
+
+if [ "$TRIGGERED" = "true" ]; then
+    exit 0
+else
+    exit 1
+fi

.agent/vendor/superpowers/tests/explicit-skill-requests/run-extended-multiturn-test.sh

@@ -0,0 +1,113 @@
+#!/usr/bin/env bash
+# Extended multi-turn test with more conversation history
+# This tries to reproduce the failure by building more context
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/extended-multiturn"
+mkdir -p "$OUTPUT_DIR"
+
+PROJECT_DIR="$OUTPUT_DIR/project"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
+
+echo "=== Extended Multi-Turn Test ==="
+echo "Output dir: $OUTPUT_DIR"
+echo "Plugin dir: $PLUGIN_DIR"
+echo ""
+
+cd "$PROJECT_DIR"
+
+# Turn 1: Start brainstorming
+echo ">>> Turn 1: Brainstorming request..."
+claude -p "I want to add user authentication to my app. Help me think through this." \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 3 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn1.json" 2>&1 || true
+echo "Done."
+
+# Turn 2: Answer a brainstorming question
+echo ">>> Turn 2: Answering questions..."
+claude -p "Let's use JWT tokens with 24-hour expiry. Email/password registration." \
+    --continue \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 3 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn2.json" 2>&1 || true
+echo "Done."
+
+# Turn 3: Ask to write a plan
+echo ">>> Turn 3: Requesting plan..."
+claude -p "Great, write this up as an implementation plan." \
+    --continue \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 3 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn3.json" 2>&1 || true
+echo "Done."
+
+# Turn 4: Confirm plan looks good
+echo ">>> Turn 4: Confirming plan..."
+claude -p "The plan looks good. What are my options for executing it?" \
+    --continue \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn4.json" 2>&1 || true
+echo "Done."
+
+# Turn 5: THE CRITICAL TEST
+echo ">>> Turn 5: Requesting subagent-driven-development..."
+FINAL_LOG="$OUTPUT_DIR/turn5.json"
+claude -p "subagent-driven-development, please" \
+    --continue \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$FINAL_LOG" 2>&1 || true
+echo "Done."
+echo ""
+
+echo "=== Results ==="
+
+# Check final turn
+SKILL_PATTERN='"skill":"([^"]*:)?subagent-driven-development"'
+if grep -q '"name":"Skill"' "$FINAL_LOG" && grep -qE "$SKILL_PATTERN" "$FINAL_LOG"; then
+    echo "PASS: Skill was triggered"
+    TRIGGERED=true
+else
+    echo "FAIL: Skill was NOT triggered"
+    TRIGGERED=false
+
+    # Show what was invoked instead
+    echo ""
+    echo "Tools invoked in final turn:"
+    grep '"type":"tool_use"' "$FINAL_LOG" | jq -r '.content[] | select(.type=="tool_use") | .name' 2>/dev/null | head -10 || \
+    grep -o '"name":"[^"]*"' "$FINAL_LOG" | head -10 || echo "  (none found)"
+fi
+
+echo ""
+echo "Skills triggered:"
+grep -o '"skill":"[^"]*"' "$FINAL_LOG" 2>/dev/null | sort -u || echo "  (none)"
+
+echo ""
+echo "Final turn response (first 500 chars):"
+grep '"type":"assistant"' "$FINAL_LOG" | head -1 | jq -r '.message.content[0].text // .message.content' 2>/dev/null | head -c 500 || echo "  (could not extract)"
+
+echo ""
+echo "Logs in: $OUTPUT_DIR"
+
+if [ "$TRIGGERED" = "true" ]; then
+    exit 0
+else
+    exit 1
+fi

.agent/vendor/superpowers/tests/explicit-skill-requests/run-haiku-test.sh

@@ -0,0 +1,144 @@
+#!/usr/bin/env bash
+# Test with haiku model and user's CLAUDE.md
+# This tests whether a cheaper/faster model fails more easily
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/haiku"
+mkdir -p "$OUTPUT_DIR"
+
+PROJECT_DIR="$OUTPUT_DIR/project"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
+mkdir -p "$PROJECT_DIR/.claude"
+
+echo "=== Haiku Model Test with User CLAUDE.md ==="
+echo "Output dir: $OUTPUT_DIR"
+echo "Plugin dir: $PLUGIN_DIR"
+echo ""
+
+cd "$PROJECT_DIR"
+
+# Copy user's CLAUDE.md to simulate real environment
+if [ -f "$HOME/.claude/CLAUDE.md" ]; then
+    cp "$HOME/.claude/CLAUDE.md" "$PROJECT_DIR/.claude/CLAUDE.md"
+    echo "Copied user CLAUDE.md"
+else
+    echo "No user CLAUDE.md found, proceeding without"
+fi
+
+# Create a dummy plan file
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
+# Auth System Implementation Plan
+
+## Task 1: Add User Model
+Create user model with email and password fields.
+
+## Task 2: Add Auth Routes
+Create login and register endpoints.
+
+## Task 3: Add JWT Middleware
+Protect routes with JWT validation.
+
+## Task 4: Write Tests
+Add comprehensive test coverage.
+EOF
+
+echo ""
+
+# Turn 1: Start brainstorming
+echo ">>> Turn 1: Brainstorming request..."
+claude -p "I want to add user authentication to my app. Help me think through this." \
+    --model haiku \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 3 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn1.json" 2>&1 || true
+echo "Done."
+
+# Turn 2: Answer questions
+echo ">>> Turn 2: Answering questions..."
+claude -p "Let's use JWT tokens with 24-hour expiry. Email/password registration." \
+    --continue \
+    --model haiku \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 3 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn2.json" 2>&1 || true
+echo "Done."
+
+# Turn 3: Ask to write a plan
+echo ">>> Turn 3: Requesting plan..."
+claude -p "Great, write this up as an implementation plan." \
+    --continue \
+    --model haiku \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 3 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn3.json" 2>&1 || true
+echo "Done."
+
+# Turn 4: Confirm plan looks good
+echo ">>> Turn 4: Confirming plan..."
+claude -p "The plan looks good. What are my options for executing it?" \
+    --continue \
+    --model haiku \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$OUTPUT_DIR/turn4.json" 2>&1 || true
+echo "Done."
+
+# Turn 5: THE CRITICAL TEST
+echo ">>> Turn 5: Requesting subagent-driven-development..."
+FINAL_LOG="$OUTPUT_DIR/turn5.json"
+claude -p "subagent-driven-development, please" \
+    --continue \
+    --model haiku \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$FINAL_LOG" 2>&1 || true
+echo "Done."
+echo ""
+
+echo "=== Results (Haiku) ==="
+
+# Check final turn
+SKILL_PATTERN='"skill":"([^"]*:)?subagent-driven-development"'
+if grep -q '"name":"Skill"' "$FINAL_LOG" && grep -qE "$SKILL_PATTERN" "$FINAL_LOG"; then
+    echo "PASS: Skill was triggered"
+    TRIGGERED=true
+else
+    echo "FAIL: Skill was NOT triggered"
+    TRIGGERED=false
+
+    echo ""
+    echo "Tools invoked in final turn:"
+    grep '"type":"tool_use"' "$FINAL_LOG" | grep -o '"name":"[^"]*"' | head -10 || echo "  (none)"
+fi
+
+echo ""
+echo "Skills triggered:"
+grep -o '"skill":"[^"]*"' "$FINAL_LOG" 2>/dev/null | sort -u || echo "  (none)"
+
+echo ""
+echo "Final turn response (first 500 chars):"
+grep '"type":"assistant"' "$FINAL_LOG" | head -1 | jq -r '.message.content[0].text // .message.content' 2>/dev/null | head -c 500 || echo "  (could not extract)"
+
+echo ""
+echo "Logs in: $OUTPUT_DIR"
+
+if [ "$TRIGGERED" = "true" ]; then
+    exit 0
+else
+    exit 1
+fi

.agent/vendor/superpowers/tests/explicit-skill-requests/run-multiturn-test.sh

@@ -0,0 +1,143 @@
+#!/usr/bin/env bash
+# Test explicit skill requests in multi-turn conversations
+# Usage: ./run-multiturn-test.sh
+#
+# This test builds actual conversation history to reproduce the failure mode
+# where Claude skips skill invocation after extended conversation
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/multiturn"
+mkdir -p "$OUTPUT_DIR"
+
+# Create project directory (conversation is cwd-based)
+PROJECT_DIR="$OUTPUT_DIR/project"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
+
+echo "=== Multi-Turn Explicit Skill Request Test ==="
+echo "Output dir: $OUTPUT_DIR"
+echo "Project dir: $PROJECT_DIR"
+echo "Plugin dir: $PLUGIN_DIR"
+echo ""
+
+cd "$PROJECT_DIR"
+
+# Create a dummy plan file
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
+# Auth System Implementation Plan
+
+## Task 1: Add User Model
+Create user model with email and password fields.
+
+## Task 2: Add Auth Routes
+Create login and register endpoints.
+
+## Task 3: Add JWT Middleware
+Protect routes with JWT validation.
+
+## Task 4: Write Tests
+Add comprehensive test coverage.
+EOF
+
+# Turn 1: Start a planning conversation
+echo ">>> Turn 1: Starting planning conversation..."
+TURN1_LOG="$OUTPUT_DIR/turn1.json"
+claude -p "I need to implement an authentication system. Let's plan this out. The requirements are: user registration with email/password, JWT tokens, and protected routes." \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$TURN1_LOG" 2>&1 || true
+
+echo "Turn 1 complete."
+echo ""
+
+# Turn 2: Continue with more planning detail
+echo ">>> Turn 2: Continuing planning..."
+TURN2_LOG="$OUTPUT_DIR/turn2.json"
+claude -p "Good analysis. I've already written the plan to docs/superpowers/plans/auth-system.md. Now I'm ready to implement. What are my options for execution?" \
+    --continue \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$TURN2_LOG" 2>&1 || true
+
+echo "Turn 2 complete."
+echo ""
+
+# Turn 3: The critical test - ask for subagent-driven-development
+echo ">>> Turn 3: Requesting subagent-driven-development..."
+TURN3_LOG="$OUTPUT_DIR/turn3.json"
+claude -p "subagent-driven-development, please" \
+    --continue \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 2 \
+    --output-format stream-json \
+    > "$TURN3_LOG" 2>&1 || true
+
+echo "Turn 3 complete."
+echo ""
+
+echo "=== Results ==="
+
+# Check if skill was triggered in Turn 3
+SKILL_PATTERN='"skill":"([^"]*:)?subagent-driven-development"'
+if grep -q '"name":"Skill"' "$TURN3_LOG" && grep -qE "$SKILL_PATTERN" "$TURN3_LOG"; then
+    echo "PASS: Skill 'subagent-driven-development' was triggered in Turn 3"
+    TRIGGERED=true
+else
+    echo "FAIL: Skill 'subagent-driven-development' was NOT triggered in Turn 3"
+    TRIGGERED=false
+fi
+
+# Show what skills were triggered
+echo ""
+echo "Skills triggered in Turn 3:"
+grep -o '"skill":"[^"]*"' "$TURN3_LOG" 2>/dev/null | sort -u || echo "  (none)"
+
+# Check for premature action in Turn 3
+echo ""
+echo "Checking for premature action in Turn 3..."
+FIRST_SKILL_LINE=$(grep -n '"name":"Skill"' "$TURN3_LOG" | head -1 | cut -d: -f1)
+if [ -n "$FIRST_SKILL_LINE" ]; then
+    PREMATURE_TOOLS=$(head -n "$FIRST_SKILL_LINE" "$TURN3_LOG" | \
+        grep '"type":"tool_use"' | \
+        grep -v '"name":"Skill"' | \
+        grep -v '"name":"TodoWrite"' || true)
+    if [ -n "$PREMATURE_TOOLS" ]; then
+        echo "WARNING: Tools invoked BEFORE Skill tool in Turn 3:"
+        echo "$PREMATURE_TOOLS" | head -5
+    else
+        echo "OK: No premature tool invocations detected"
+    fi
+else
+    echo "WARNING: No Skill invocation found in Turn 3"
+    # Show what WAS invoked
+    echo ""
+    echo "Tools invoked in Turn 3:"
+    grep '"type":"tool_use"' "$TURN3_LOG" | grep -o '"name":"[^"]*"' | head -10 || echo "  (none)"
+fi
+
+# Show Turn 3 assistant response
+echo ""
+echo "Turn 3 first assistant response (truncated):"
+grep '"type":"assistant"' "$TURN3_LOG" | head -1 | jq -r '.message.content[0].text // .message.content' 2>/dev/null | head -c 500 || echo "  (could not extract)"
+
+echo ""
+echo "Logs:"
+echo "  Turn 1: $TURN1_LOG"
+echo "  Turn 2: $TURN2_LOG"
+echo "  Turn 3: $TURN3_LOG"
+echo "Timestamp: $TIMESTAMP"
+
+if [ "$TRIGGERED" = "true" ]; then
+    exit 0
+else
+    exit 1
+fi

.agent/vendor/superpowers/tests/explicit-skill-requests/run-test.sh

@@ -0,0 +1,136 @@
+#!/usr/bin/env bash
+# Test explicit skill requests (user names a skill directly)
+# Usage: ./run-test.sh <skill-name> <prompt-file>
+#
+# Tests whether Claude invokes a skill when the user explicitly requests it by name
+# (without using the plugin namespace prefix)
+#
+# Uses isolated HOME to avoid user context interference
+
+set -e
+
+SKILL_NAME="$1"
+PROMPT_FILE="$2"
+MAX_TURNS="${3:-3}"
+
+if [ -z "$SKILL_NAME" ] || [ -z "$PROMPT_FILE" ]; then
+    echo "Usage: $0 <skill-name> <prompt-file> [max-turns]"
+    echo "Example: $0 subagent-driven-development ./prompts/subagent-driven-development-please.txt"
+    exit 1
+fi
+
+# Get the directory where this script lives
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+# Get the superpowers plugin root (two levels up)
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/${SKILL_NAME}"
+mkdir -p "$OUTPUT_DIR"
+
+# Read prompt from file
+PROMPT=$(cat "$PROMPT_FILE")
+
+echo "=== Explicit Skill Request Test ==="
+echo "Skill: $SKILL_NAME"
+echo "Prompt file: $PROMPT_FILE"
+echo "Max turns: $MAX_TURNS"
+echo "Output dir: $OUTPUT_DIR"
+echo ""
+
+# Copy prompt for reference
+cp "$PROMPT_FILE" "$OUTPUT_DIR/prompt.txt"
+
+# Create a minimal project directory for the test
+PROJECT_DIR="$OUTPUT_DIR/project"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
+
+# Create a dummy plan file for mid-conversation tests
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
+# Auth System Implementation Plan
+
+## Task 1: Add User Model
+Create user model with email and password fields.
+
+## Task 2: Add Auth Routes
+Create login and register endpoints.
+
+## Task 3: Add JWT Middleware
+Protect routes with JWT validation.
+EOF
+
+# Run Claude with isolated environment
+LOG_FILE="$OUTPUT_DIR/claude-output.json"
+cd "$PROJECT_DIR"
+
+echo "Plugin dir: $PLUGIN_DIR"
+echo "Running claude -p with explicit skill request..."
+echo "Prompt: $PROMPT"
+echo ""
+
+timeout 300 claude -p "$PROMPT" \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns "$MAX_TURNS" \
+    --output-format stream-json \
+    > "$LOG_FILE" 2>&1 || true
+
+echo ""
+echo "=== Results ==="
+
+# Check if skill was triggered (look for Skill tool invocation)
+# Match either "skill":"skillname" or "skill":"namespace:skillname"
+SKILL_PATTERN='"skill":"([^"]*:)?'"${SKILL_NAME}"'"'
+if grep -q '"name":"Skill"' "$LOG_FILE" && grep -qE "$SKILL_PATTERN" "$LOG_FILE"; then
+    echo "PASS: Skill '$SKILL_NAME' was triggered"
+    TRIGGERED=true
+else
+    echo "FAIL: Skill '$SKILL_NAME' was NOT triggered"
+    TRIGGERED=false
+fi
+
+# Show what skills WERE triggered
+echo ""
+echo "Skills triggered in this run:"
+grep -o '"skill":"[^"]*"' "$LOG_FILE" 2>/dev/null | sort -u || echo "  (none)"
+
+# Check if Claude took action BEFORE invoking the skill (the failure mode)
+echo ""
+echo "Checking for premature action..."
+
+# Look for tool invocations before the Skill invocation
+# This detects the failure mode where Claude starts doing work without loading the skill
+FIRST_SKILL_LINE=$(grep -n '"name":"Skill"' "$LOG_FILE" | head -1 | cut -d: -f1)
+if [ -n "$FIRST_SKILL_LINE" ]; then
+    # Check if any non-Skill, non-system tools were invoked before the first Skill invocation
+    # Filter out system messages, TodoWrite (planning is ok), and other non-action tools
+    PREMATURE_TOOLS=$(head -n "$FIRST_SKILL_LINE" "$LOG_FILE" | \
+        grep '"type":"tool_use"' | \
+        grep -v '"name":"Skill"' | \
+        grep -v '"name":"TodoWrite"' || true)
+    if [ -n "$PREMATURE_TOOLS" ]; then
+        echo "WARNING: Tools invoked BEFORE Skill tool:"
+        echo "$PREMATURE_TOOLS" | head -5
+        echo ""
+        echo "This indicates Claude started working before loading the requested skill."
+    else
+        echo "OK: No premature tool invocations detected"
+    fi
+else
+    echo "WARNING: No Skill invocation found at all"
+fi
+
+# Show first assistant message
+echo ""
+echo "First assistant response (truncated):"
+grep '"type":"assistant"' "$LOG_FILE" | head -1 | jq -r '.message.content[0].text // .message.content' 2>/dev/null | head -c 500 || echo "  (could not extract)"
+
+echo ""
+echo "Full log: $LOG_FILE"
+echo "Timestamp: $TIMESTAMP"
+
+if [ "$TRIGGERED" = "true" ]; then
+    exit 0
+else
+    exit 1
+fi

.agent/vendor/superpowers/tests/opencode/run-tests.sh

@@ -0,0 +1,163 @@
+#!/usr/bin/env bash
+# Main test runner for OpenCode plugin test suite
+# Runs all tests and reports results
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+cd "$SCRIPT_DIR"
+
+echo "========================================"
+echo " OpenCode Plugin Test Suite"
+echo "========================================"
+echo ""
+echo "Repository: $(cd ../.. && pwd)"
+echo "Test time: $(date)"
+echo ""
+
+# Parse command line arguments
+RUN_INTEGRATION=false
+VERBOSE=false
+SPECIFIC_TEST=""
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --integration|-i)
+            RUN_INTEGRATION=true
+            shift
+            ;;
+        --verbose|-v)
+            VERBOSE=true
+            shift
+            ;;
+        --test|-t)
+            SPECIFIC_TEST="$2"
+            shift 2
+            ;;
+        --help|-h)
+            echo "Usage: $0 [options]"
+            echo ""
+            echo "Options:"
+            echo "  --integration, -i  Run integration tests (requires OpenCode)"
+            echo "  --verbose, -v      Show verbose output"
+            echo "  --test, -t NAME    Run only the specified test"
+            echo "  --help, -h         Show this help"
+            echo ""
+            echo "Tests:"
+            echo "  test-plugin-loading.sh  Verify plugin installation and structure"
+            echo "  test-tools.sh           Test use_skill and find_skills tools (integration)"
+            echo "  test-priority.sh        Test skill priority resolution (integration)"
+            exit 0
+            ;;
+        *)
+            echo "Unknown option: $1"
+            echo "Use --help for usage information"
+            exit 1
+            ;;
+    esac
+done
+
+# List of tests to run (no external dependencies)
+tests=(
+    "test-plugin-loading.sh"
+)
+
+# Integration tests (require OpenCode)
+integration_tests=(
+    "test-tools.sh"
+    "test-priority.sh"
+)
+
+# Add integration tests if requested
+if [ "$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 bash "$test_path"; then
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            echo ""
+            echo "  [PASS] $test (${duration}s)"
+            passed=$((passed + 1))
+        else
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            echo ""
+            echo "  [FAIL] $test (${duration}s)"
+            failed=$((failed + 1))
+        fi
+    else
+        # Capture output for non-verbose mode
+        if output=$(bash "$test_path" 2>&1); then
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            echo "  [PASS] (${duration}s)"
+            passed=$((passed + 1))
+        else
+            end_time=$(date +%s)
+            duration=$((end_time - start_time))
+            echo "  [FAIL] (${duration}s)"
+            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."
+    echo "Use --integration flag to run tests that require OpenCode."
+    echo ""
+fi
+
+if [ $failed -gt 0 ]; then
+    echo "STATUS: FAILED"
+    exit 1
+else
+    echo "STATUS: PASSED"
+    exit 0
+fi

.agent/vendor/superpowers/tests/opencode/setup.sh

@@ -0,0 +1,73 @@
+#!/usr/bin/env bash
+# Setup script for OpenCode plugin tests
+# Creates an isolated test environment with proper plugin installation
+set -euo pipefail
+
+# Get the repository root (two levels up from tests/opencode/)
+REPO_ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
+
+# Create temp home directory for isolation
+export TEST_HOME=$(mktemp -d)
+export HOME="$TEST_HOME"
+export XDG_CONFIG_HOME="$TEST_HOME/.config"
+export OPENCODE_CONFIG_DIR="$TEST_HOME/.config/opencode"
+
+# Install plugin to test location
+mkdir -p "$HOME/.config/opencode/superpowers"
+cp -r "$REPO_ROOT/lib" "$HOME/.config/opencode/superpowers/"
+cp -r "$REPO_ROOT/skills" "$HOME/.config/opencode/superpowers/"
+
+# Copy plugin directory
+mkdir -p "$HOME/.config/opencode/superpowers/.opencode/plugins"
+cp "$REPO_ROOT/.opencode/plugins/superpowers.js" "$HOME/.config/opencode/superpowers/.opencode/plugins/"
+
+# Register plugin via symlink
+mkdir -p "$HOME/.config/opencode/plugins"
+ln -sf "$HOME/.config/opencode/superpowers/.opencode/plugins/superpowers.js" \
+       "$HOME/.config/opencode/plugins/superpowers.js"
+
+# Create test skills in different locations for testing
+
+# Personal test skill
+mkdir -p "$HOME/.config/opencode/skills/personal-test"
+cat > "$HOME/.config/opencode/skills/personal-test/SKILL.md" <<'EOF'
+---
+name: personal-test
+description: Test personal skill for verification
+---
+# Personal Test Skill
+
+This is a personal skill used for testing.
+
+PERSONAL_SKILL_MARKER_12345
+EOF
+
+# Create a project directory for project-level skill tests
+mkdir -p "$TEST_HOME/test-project/.opencode/skills/project-test"
+cat > "$TEST_HOME/test-project/.opencode/skills/project-test/SKILL.md" <<'EOF'
+---
+name: project-test
+description: Test project skill for verification
+---
+# Project Test Skill
+
+This is a project skill used for testing.
+
+PROJECT_SKILL_MARKER_67890
+EOF
+
+echo "Setup complete: $TEST_HOME"
+echo "Plugin installed to: $HOME/.config/opencode/superpowers/.opencode/plugins/superpowers.js"
+echo "Plugin registered at: $HOME/.config/opencode/plugins/superpowers.js"
+echo "Test project at: $TEST_HOME/test-project"
+
+# Helper function for cleanup (call from tests or trap)
+cleanup_test_env() {
+    if [ -n "${TEST_HOME:-}" ] && [ -d "$TEST_HOME" ]; then
+        rm -rf "$TEST_HOME"
+    fi
+}
+
+# Export for use in tests
+export -f cleanup_test_env
+export REPO_ROOT

.agent/vendor/superpowers/tests/opencode/test-plugin-loading.sh

@@ -0,0 +1,72 @@
+#!/usr/bin/env bash
+# Test: Plugin Loading
+# Verifies that the superpowers plugin loads correctly in OpenCode
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+echo "=== Test: Plugin Loading ==="
+
+# Source setup to create isolated environment
+source "$SCRIPT_DIR/setup.sh"
+
+# Trap to cleanup on exit
+trap cleanup_test_env EXIT
+
+# Test 1: Verify plugin file exists and is registered
+echo "Test 1: Checking plugin registration..."
+if [ -L "$HOME/.config/opencode/plugins/superpowers.js" ]; then
+    echo "  [PASS] Plugin symlink exists"
+else
+    echo "  [FAIL] Plugin symlink not found at $HOME/.config/opencode/plugins/superpowers.js"
+    exit 1
+fi
+
+# Verify symlink target exists
+if [ -f "$(readlink -f "$HOME/.config/opencode/plugins/superpowers.js")" ]; then
+    echo "  [PASS] Plugin symlink target exists"
+else
+    echo "  [FAIL] Plugin symlink target does not exist"
+    exit 1
+fi
+
+# Test 2: Verify skills directory is populated
+echo "Test 2: Checking skills directory..."
+skill_count=$(find "$HOME/.config/opencode/superpowers/skills" -name "SKILL.md" | wc -l)
+if [ "$skill_count" -gt 0 ]; then
+    echo "  [PASS] Found $skill_count skills installed"
+else
+    echo "  [FAIL] No skills found in installed location"
+    exit 1
+fi
+
+# Test 4: Check using-superpowers skill exists (critical for bootstrap)
+echo "Test 4: Checking using-superpowers skill (required for bootstrap)..."
+if [ -f "$HOME/.config/opencode/superpowers/skills/using-superpowers/SKILL.md" ]; then
+    echo "  [PASS] using-superpowers skill exists"
+else
+    echo "  [FAIL] using-superpowers skill not found (required for bootstrap)"
+    exit 1
+fi
+
+# Test 5: Verify plugin JavaScript syntax (basic check)
+echo "Test 5: Checking plugin JavaScript syntax..."
+plugin_file="$HOME/.config/opencode/superpowers/.opencode/plugins/superpowers.js"
+if node --check "$plugin_file" 2>/dev/null; then
+    echo "  [PASS] Plugin JavaScript syntax is valid"
+else
+    echo "  [FAIL] Plugin has JavaScript syntax errors"
+    exit 1
+fi
+
+# Test 6: Verify personal test skill was created
+echo "Test 6: Checking test fixtures..."
+if [ -f "$HOME/.config/opencode/skills/personal-test/SKILL.md" ]; then
+    echo "  [PASS] Personal test skill fixture created"
+else
+    echo "  [FAIL] Personal test skill fixture not found"
+    exit 1
+fi
+
+echo ""
+echo "=== All plugin loading tests passed ==="

.agent/vendor/superpowers/tests/opencode/test-priority.sh

@@ -0,0 +1,198 @@
+#!/usr/bin/env bash
+# Test: Skill Priority Resolution
+# Verifies that skills are resolved with correct priority: project > personal > superpowers
+# NOTE: These tests require OpenCode to be installed and configured
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+echo "=== Test: Skill Priority Resolution ==="
+
+# Source setup to create isolated environment
+source "$SCRIPT_DIR/setup.sh"
+
+# Trap to cleanup on exit
+trap cleanup_test_env EXIT
+
+# Create same skill "priority-test" in all three locations with different markers
+echo "Setting up priority test fixtures..."
+
+# 1. Create in superpowers location (lowest priority)
+mkdir -p "$HOME/.config/opencode/superpowers/skills/priority-test"
+cat > "$HOME/.config/opencode/superpowers/skills/priority-test/SKILL.md" <<'EOF'
+---
+name: priority-test
+description: Superpowers version of priority test skill
+---
+# Priority Test Skill (Superpowers Version)
+
+This is the SUPERPOWERS version of the priority test skill.
+
+PRIORITY_MARKER_SUPERPOWERS_VERSION
+EOF
+
+# 2. Create in personal location (medium priority)
+mkdir -p "$HOME/.config/opencode/skills/priority-test"
+cat > "$HOME/.config/opencode/skills/priority-test/SKILL.md" <<'EOF'
+---
+name: priority-test
+description: Personal version of priority test skill
+---
+# Priority Test Skill (Personal Version)
+
+This is the PERSONAL version of the priority test skill.
+
+PRIORITY_MARKER_PERSONAL_VERSION
+EOF
+
+# 3. Create in project location (highest priority)
+mkdir -p "$TEST_HOME/test-project/.opencode/skills/priority-test"
+cat > "$TEST_HOME/test-project/.opencode/skills/priority-test/SKILL.md" <<'EOF'
+---
+name: priority-test
+description: Project version of priority test skill
+---
+# Priority Test Skill (Project Version)
+
+This is the PROJECT version of the priority test skill.
+
+PRIORITY_MARKER_PROJECT_VERSION
+EOF
+
+echo "  Created priority-test skill in all three locations"
+
+# Test 1: Verify fixture setup
+echo ""
+echo "Test 1: Verifying test fixtures..."
+
+if [ -f "$HOME/.config/opencode/superpowers/skills/priority-test/SKILL.md" ]; then
+    echo "  [PASS] Superpowers version exists"
+else
+    echo "  [FAIL] Superpowers version missing"
+    exit 1
+fi
+
+if [ -f "$HOME/.config/opencode/skills/priority-test/SKILL.md" ]; then
+    echo "  [PASS] Personal version exists"
+else
+    echo "  [FAIL] Personal version missing"
+    exit 1
+fi
+
+if [ -f "$TEST_HOME/test-project/.opencode/skills/priority-test/SKILL.md" ]; then
+    echo "  [PASS] Project version exists"
+else
+    echo "  [FAIL] Project version missing"
+    exit 1
+fi
+
+# Check if opencode is available for integration tests
+if ! command -v opencode &> /dev/null; then
+    echo ""
+    echo "  [SKIP] OpenCode not installed - skipping integration tests"
+    echo "  To run these tests, install OpenCode: https://opencode.ai"
+    echo ""
+    echo "=== Priority fixture tests passed (integration tests skipped) ==="
+    exit 0
+fi
+
+# Test 2: Test that personal overrides superpowers
+echo ""
+echo "Test 2: Testing personal > superpowers priority..."
+echo "  Running from outside project directory..."
+
+# Run from HOME (not in project) - should get personal version
+cd "$HOME"
+output=$(timeout 60s opencode run --print-logs "Use the use_skill tool to load the priority-test skill. Show me the exact content including any PRIORITY_MARKER text." 2>&1) || {
+    exit_code=$?
+    if [ $exit_code -eq 124 ]; then
+        echo "  [FAIL] OpenCode timed out after 60s"
+        exit 1
+    fi
+}
+
+if echo "$output" | grep -qi "PRIORITY_MARKER_PERSONAL_VERSION"; then
+    echo "  [PASS] Personal version loaded (overrides superpowers)"
+elif echo "$output" | grep -qi "PRIORITY_MARKER_SUPERPOWERS_VERSION"; then
+    echo "  [FAIL] Superpowers version loaded instead of personal"
+    exit 1
+else
+    echo "  [WARN] Could not verify priority marker in output"
+    echo "  Output snippet:"
+    echo "$output" | grep -i "priority\|personal\|superpowers" | head -10
+fi
+
+# Test 3: Test that project overrides both personal and superpowers
+echo ""
+echo "Test 3: Testing project > personal > superpowers priority..."
+echo "  Running from project directory..."
+
+# Run from project directory - should get project version
+cd "$TEST_HOME/test-project"
+output=$(timeout 60s opencode run --print-logs "Use the use_skill tool to load the priority-test skill. Show me the exact content including any PRIORITY_MARKER text." 2>&1) || {
+    exit_code=$?
+    if [ $exit_code -eq 124 ]; then
+        echo "  [FAIL] OpenCode timed out after 60s"
+        exit 1
+    fi
+}
+
+if echo "$output" | grep -qi "PRIORITY_MARKER_PROJECT_VERSION"; then
+    echo "  [PASS] Project version loaded (highest priority)"
+elif echo "$output" | grep -qi "PRIORITY_MARKER_PERSONAL_VERSION"; then
+    echo "  [FAIL] Personal version loaded instead of project"
+    exit 1
+elif echo "$output" | grep -qi "PRIORITY_MARKER_SUPERPOWERS_VERSION"; then
+    echo "  [FAIL] Superpowers version loaded instead of project"
+    exit 1
+else
+    echo "  [WARN] Could not verify priority marker in output"
+    echo "  Output snippet:"
+    echo "$output" | grep -i "priority\|project\|personal" | head -10
+fi
+
+# Test 4: Test explicit superpowers: prefix bypasses priority
+echo ""
+echo "Test 4: Testing superpowers: prefix forces superpowers version..."
+
+cd "$TEST_HOME/test-project"
+output=$(timeout 60s opencode run --print-logs "Use the use_skill tool to load superpowers:priority-test specifically. Show me the exact content including any PRIORITY_MARKER text." 2>&1) || {
+    exit_code=$?
+    if [ $exit_code -eq 124 ]; then
+        echo "  [FAIL] OpenCode timed out after 60s"
+        exit 1
+    fi
+}
+
+if echo "$output" | grep -qi "PRIORITY_MARKER_SUPERPOWERS_VERSION"; then
+    echo "  [PASS] superpowers: prefix correctly forces superpowers version"
+elif echo "$output" | grep -qi "PRIORITY_MARKER_PROJECT_VERSION\|PRIORITY_MARKER_PERSONAL_VERSION"; then
+    echo "  [FAIL] superpowers: prefix did not force superpowers version"
+    exit 1
+else
+    echo "  [WARN] Could not verify priority marker in output"
+fi
+
+# Test 5: Test explicit project: prefix
+echo ""
+echo "Test 5: Testing project: prefix forces project version..."
+
+cd "$HOME"  # Run from outside project but with project: prefix
+output=$(timeout 60s opencode run --print-logs "Use the use_skill tool to load project:priority-test specifically. Show me the exact content." 2>&1) || {
+    exit_code=$?
+    if [ $exit_code -eq 124 ]; then
+        echo "  [FAIL] OpenCode timed out after 60s"
+        exit 1
+    fi
+}
+
+# Note: This may fail since we're not in the project directory
+# The project: prefix only works when in a project context
+if echo "$output" | grep -qi "not found\|error"; then
+    echo "  [PASS] project: prefix correctly fails when not in project context"
+else
+    echo "  [INFO] project: prefix behavior outside project context may vary"
+fi
+
+echo ""
+echo "=== All priority tests passed ==="

.agent/vendor/superpowers/tests/opencode/test-tools.sh

@@ -0,0 +1,104 @@
+#!/usr/bin/env bash
+# Test: Tools Functionality
+# Verifies that use_skill and find_skills tools work correctly
+# NOTE: These tests require OpenCode to be installed and configured
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+echo "=== Test: Tools Functionality ==="
+
+# Source setup to create isolated environment
+source "$SCRIPT_DIR/setup.sh"
+
+# Trap to cleanup on exit
+trap cleanup_test_env EXIT
+
+# Check if opencode is available
+if ! command -v opencode &> /dev/null; then
+    echo "  [SKIP] OpenCode not installed - skipping integration tests"
+    echo "  To run these tests, install OpenCode: https://opencode.ai"
+    exit 0
+fi
+
+# Test 1: Test find_skills tool via direct invocation
+echo "Test 1: Testing find_skills tool..."
+echo "  Running opencode with find_skills request..."
+
+# Use timeout to prevent hanging, capture both stdout and stderr
+output=$(timeout 60s opencode run --print-logs "Use the find_skills tool to list available skills. Just call the tool and show me the raw output." 2>&1) || {
+    exit_code=$?
+    if [ $exit_code -eq 124 ]; then
+        echo "  [FAIL] OpenCode timed out after 60s"
+        exit 1
+    fi
+    echo "  [WARN] OpenCode returned non-zero exit code: $exit_code"
+}
+
+# Check for expected patterns in output
+if echo "$output" | grep -qi "superpowers:brainstorming\|superpowers:using-superpowers\|Available skills"; then
+    echo "  [PASS] find_skills tool discovered superpowers skills"
+else
+    echo "  [FAIL] find_skills did not return expected skills"
+    echo "  Output was:"
+    echo "$output" | head -50
+    exit 1
+fi
+
+# Check if personal test skill was found
+if echo "$output" | grep -qi "personal-test"; then
+    echo "  [PASS] find_skills found personal test skill"
+else
+    echo "  [WARN] personal test skill not found in output (may be ok if tool returned subset)"
+fi
+
+# Test 2: Test use_skill tool
+echo ""
+echo "Test 2: Testing use_skill tool..."
+echo "  Running opencode with use_skill request..."
+
+output=$(timeout 60s opencode run --print-logs "Use the use_skill tool to load the personal-test skill and show me what you get." 2>&1) || {
+    exit_code=$?
+    if [ $exit_code -eq 124 ]; then
+        echo "  [FAIL] OpenCode timed out after 60s"
+        exit 1
+    fi
+    echo "  [WARN] OpenCode returned non-zero exit code: $exit_code"
+}
+
+# Check for the skill marker we embedded
+if echo "$output" | grep -qi "PERSONAL_SKILL_MARKER_12345\|Personal Test Skill\|Launching skill"; then
+    echo "  [PASS] use_skill loaded personal-test skill content"
+else
+    echo "  [FAIL] use_skill did not load personal-test skill correctly"
+    echo "  Output was:"
+    echo "$output" | head -50
+    exit 1
+fi
+
+# Test 3: Test use_skill with superpowers: prefix
+echo ""
+echo "Test 3: Testing use_skill with superpowers: prefix..."
+echo "  Running opencode with superpowers:brainstorming skill..."
+
+output=$(timeout 60s opencode run --print-logs "Use the use_skill tool to load superpowers:brainstorming and tell me the first few lines of what you received." 2>&1) || {
+    exit_code=$?
+    if [ $exit_code -eq 124 ]; then
+        echo "  [FAIL] OpenCode timed out after 60s"
+        exit 1
+    fi
+    echo "  [WARN] OpenCode returned non-zero exit code: $exit_code"
+}
+
+# Check for expected content from brainstorming skill
+if echo "$output" | grep -qi "brainstorming\|Launching skill\|skill.*loaded"; then
+    echo "  [PASS] use_skill loaded superpowers:brainstorming skill"
+else
+    echo "  [FAIL] use_skill did not load superpowers:brainstorming correctly"
+    echo "  Output was:"
+    echo "$output" | head -50
+    exit 1
+fi
+
+echo ""
+echo "=== All tools tests passed ==="

.agent/vendor/superpowers/tests/skill-triggering/prompts/dispatching-parallel-agents.txt

@@ -0,0 +1,8 @@
+I have 4 independent test failures happening in different modules:
+
+1. tests/auth/login.test.ts - "should redirect after login" is failing
+2. tests/api/users.test.ts - "should return user list" returns 500
+3. tests/components/Button.test.tsx - snapshot mismatch
+4. tests/utils/date.test.ts - timezone handling broken
+
+These are unrelated issues in different parts of the codebase. Can you investigate all of them?

.agent/vendor/superpowers/tests/skill-triggering/prompts/executing-plans.txt

@@ -0,0 +1 @@
+I have a plan document at docs/superpowers/plans/2024-01-15-auth-system.md that needs to be executed. Please implement it.

.agent/vendor/superpowers/tests/skill-triggering/prompts/requesting-code-review.txt

@@ -0,0 +1,3 @@
+I just finished implementing the user authentication feature. All the code is committed. Can you review the changes before I merge to main?
+
+The commits are between abc123 and def456.

.agent/vendor/superpowers/tests/skill-triggering/prompts/systematic-debugging.txt

@@ -0,0 +1,11 @@
+The tests are failing with this error:
+
+```
+FAIL src/utils/parser.test.ts
+  ● Parser › should handle nested objects
+    TypeError: Cannot read property 'value' of undefined
+      at parse (src/utils/parser.ts:42:18)
+      at Object.<anonymous> (src/utils/parser.test.ts:28:20)
+```
+
+Can you figure out what's going wrong and fix it?

.agent/vendor/superpowers/tests/skill-triggering/prompts/test-driven-development.txt

@@ -0,0 +1,7 @@
+I need to add a new feature to validate email addresses. It should:
+- Check that there's an @ symbol
+- Check that there's at least one character before the @
+- Check that there's a dot in the domain part
+- Return true/false
+
+Can you implement this?

.agent/vendor/superpowers/tests/skill-triggering/prompts/writing-plans.txt

@@ -0,0 +1,10 @@
+Here's the spec for our new authentication system:
+
+Requirements:
+- Users can register with email/password
+- Users can log in and receive a JWT token
+- Protected routes require valid JWT
+- Tokens expire after 24 hours
+- Support password reset via email
+
+We need to implement this. There are multiple steps involved - user model, auth routes, middleware, email service integration.

.agent/vendor/superpowers/tests/skill-triggering/run-all.sh

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+# Run all skill triggering tests
+# Usage: ./run-all.sh
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROMPTS_DIR="$SCRIPT_DIR/prompts"
+
+SKILLS=(
+    "systematic-debugging"
+    "test-driven-development"
+    "writing-plans"
+    "dispatching-parallel-agents"
+    "executing-plans"
+    "requesting-code-review"
+)
+
+echo "=== Running Skill Triggering Tests ==="
+echo ""
+
+PASSED=0
+FAILED=0
+RESULTS=()
+
+for skill in "${SKILLS[@]}"; do
+    prompt_file="$PROMPTS_DIR/${skill}.txt"
+
+    if [ ! -f "$prompt_file" ]; then
+        echo "⚠️  SKIP: No prompt file for $skill"
+        continue
+    fi
+
+    echo "Testing: $skill"
+
+    if "$SCRIPT_DIR/run-test.sh" "$skill" "$prompt_file" 3 2>&1 | tee /tmp/skill-test-$skill.log; then
+        PASSED=$((PASSED + 1))
+        RESULTS+=("✅ $skill")
+    else
+        FAILED=$((FAILED + 1))
+        RESULTS+=("❌ $skill")
+    fi
+
+    echo ""
+    echo "---"
+    echo ""
+done
+
+echo ""
+echo "=== Summary ==="
+for result in "${RESULTS[@]}"; do
+    echo "  $result"
+done
+echo ""
+echo "Passed: $PASSED"
+echo "Failed: $FAILED"
+
+if [ $FAILED -gt 0 ]; then
+    exit 1
+fi

.agent/vendor/superpowers/tests/skill-triggering/run-test.sh

@@ -0,0 +1,88 @@
+#!/usr/bin/env bash
+# Test skill triggering with naive prompts
+# Usage: ./run-test.sh <skill-name> <prompt-file>
+#
+# Tests whether Claude triggers a skill based on a natural prompt
+# (without explicitly mentioning the skill)
+
+set -e
+
+SKILL_NAME="$1"
+PROMPT_FILE="$2"
+MAX_TURNS="${3:-3}"
+
+if [ -z "$SKILL_NAME" ] || [ -z "$PROMPT_FILE" ]; then
+    echo "Usage: $0 <skill-name> <prompt-file> [max-turns]"
+    echo "Example: $0 systematic-debugging ./test-prompts/debugging.txt"
+    exit 1
+fi
+
+# Get the directory where this script lives (should be tests/skill-triggering)
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+# Get the superpowers plugin root (two levels up from tests/skill-triggering)
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/skill-triggering/${SKILL_NAME}"
+mkdir -p "$OUTPUT_DIR"
+
+# Read prompt from file
+PROMPT=$(cat "$PROMPT_FILE")
+
+echo "=== Skill Triggering Test ==="
+echo "Skill: $SKILL_NAME"
+echo "Prompt file: $PROMPT_FILE"
+echo "Max turns: $MAX_TURNS"
+echo "Output dir: $OUTPUT_DIR"
+echo ""
+
+# Copy prompt for reference
+cp "$PROMPT_FILE" "$OUTPUT_DIR/prompt.txt"
+
+# Run Claude
+LOG_FILE="$OUTPUT_DIR/claude-output.json"
+cd "$OUTPUT_DIR"
+
+echo "Plugin dir: $PLUGIN_DIR"
+echo "Running claude -p with naive prompt..."
+timeout 300 claude -p "$PROMPT" \
+    --plugin-dir "$PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns "$MAX_TURNS" \
+    --output-format stream-json \
+    > "$LOG_FILE" 2>&1 || true
+
+echo ""
+echo "=== Results ==="
+
+# Check if skill was triggered (look for Skill tool invocation)
+# In stream-json, tool invocations have "name":"Skill" (not "tool":"Skill")
+# Match either "skill":"skillname" or "skill":"namespace:skillname"
+SKILL_PATTERN='"skill":"([^"]*:)?'"${SKILL_NAME}"'"'
+if grep -q '"name":"Skill"' "$LOG_FILE" && grep -qE "$SKILL_PATTERN" "$LOG_FILE"; then
+    echo "✅ PASS: Skill '$SKILL_NAME' was triggered"
+    TRIGGERED=true
+else
+    echo "❌ FAIL: Skill '$SKILL_NAME' was NOT triggered"
+    TRIGGERED=false
+fi
+
+# Show what skills WERE triggered
+echo ""
+echo "Skills triggered in this run:"
+grep -o '"skill":"[^"]*"' "$LOG_FILE" 2>/dev/null | sort -u || echo "  (none)"
+
+# Show first assistant message
+echo ""
+echo "First assistant response (truncated):"
+grep '"type":"assistant"' "$LOG_FILE" | head -1 | jq -r '.message.content[0].text // .message.content' 2>/dev/null | head -c 500 || echo "  (could not extract)"
+
+echo ""
+echo "Full log: $LOG_FILE"
+echo "Timestamp: $TIMESTAMP"
+
+if [ "$TRIGGERED" = "true" ]; then
+    exit 0
+else
+    exit 1
+fi

.agent/vendor/superpowers/tests/subagent-driven-dev/go-fractals/design.md

@@ -0,0 +1,81 @@
+# Go Fractals CLI - Design
+
+## Overview
+
+A command-line tool that generates ASCII art fractals. Supports two fractal types with configurable output.
+
+## Usage
+
+```bash
+# Sierpinski triangle
+fractals sierpinski --size 32 --depth 5
+
+# Mandelbrot set
+fractals mandelbrot --width 80 --height 24 --iterations 100
+
+# Custom character
+fractals sierpinski --size 16 --char '#'
+
+# Help
+fractals --help
+fractals sierpinski --help
+```
+
+## Commands
+
+### `sierpinski`
+
+Generates a Sierpinski triangle using recursive subdivision.
+
+Flags:
+- `--size` (default: 32) - Width of the triangle base in characters
+- `--depth` (default: 5) - Recursion depth
+- `--char` (default: '*') - Character to use for filled points
+
+Output: Triangle printed to stdout, one line per row.
+
+### `mandelbrot`
+
+Renders the Mandelbrot set as ASCII art. Maps iteration count to characters.
+
+Flags:
+- `--width` (default: 80) - Output width in characters
+- `--height` (default: 24) - Output height in characters
+- `--iterations` (default: 100) - Maximum iterations for escape calculation
+- `--char` (default: gradient) - Single character, or omit for gradient " .:-=+*#%@"
+
+Output: Rectangle printed to stdout.
+
+## Architecture
+
+```
+cmd/
+  fractals/
+    main.go           # Entry point, CLI setup
+internal/
+  sierpinski/
+    sierpinski.go     # Algorithm
+    sierpinski_test.go
+  mandelbrot/
+    mandelbrot.go     # Algorithm
+    mandelbrot_test.go
+  cli/
+    root.go           # Root command, help
+    sierpinski.go     # Sierpinski subcommand
+    mandelbrot.go     # Mandelbrot subcommand
+```
+
+## Dependencies
+
+- Go 1.21+
+- `github.com/spf13/cobra` for CLI
+
+## Acceptance Criteria
+
+1. `fractals --help` shows usage
+2. `fractals sierpinski` outputs a recognizable triangle
+3. `fractals mandelbrot` outputs a recognizable Mandelbrot set
+4. `--size`, `--width`, `--height`, `--depth`, `--iterations` flags work
+5. `--char` customizes output character
+6. Invalid inputs produce clear error messages
+7. All tests pass

.agent/vendor/superpowers/tests/subagent-driven-dev/go-fractals/plan.md

@@ -0,0 +1,172 @@
+# Go Fractals CLI - Implementation Plan
+
+Execute this plan using the `superpowers:subagent-driven-development` skill.
+
+## Context
+
+Building a CLI tool that generates ASCII fractals. See `design.md` for full specification.
+
+## Tasks
+
+### Task 1: Project Setup
+
+Create the Go module and directory structure.
+
+**Do:**
+- Initialize `go.mod` with module name `github.com/superpowers-test/fractals`
+- Create directory structure: `cmd/fractals/`, `internal/sierpinski/`, `internal/mandelbrot/`, `internal/cli/`
+- Create minimal `cmd/fractals/main.go` that prints "fractals cli"
+- Add `github.com/spf13/cobra` dependency
+
+**Verify:**
+- `go build ./cmd/fractals` succeeds
+- `./fractals` prints "fractals cli"
+
+---
+
+### Task 2: CLI Framework with Help
+
+Set up Cobra root command with help output.
+
+**Do:**
+- Create `internal/cli/root.go` with root command
+- Configure help text showing available subcommands
+- Wire root command into `main.go`
+
+**Verify:**
+- `./fractals --help` shows usage with "sierpinski" and "mandelbrot" listed as available commands
+- `./fractals` (no args) shows help
+
+---
+
+### Task 3: Sierpinski Algorithm
+
+Implement the Sierpinski triangle generation algorithm.
+
+**Do:**
+- Create `internal/sierpinski/sierpinski.go`
+- Implement `Generate(size, depth int, char rune) []string` that returns lines of the triangle
+- Use recursive midpoint subdivision algorithm
+- Create `internal/sierpinski/sierpinski_test.go` with tests:
+  - Small triangle (size=4, depth=2) matches expected output
+  - Size=1 returns single character
+  - Depth=0 returns filled triangle
+
+**Verify:**
+- `go test ./internal/sierpinski/...` passes
+
+---
+
+### Task 4: Sierpinski CLI Integration
+
+Wire the Sierpinski algorithm to a CLI subcommand.
+
+**Do:**
+- Create `internal/cli/sierpinski.go` with `sierpinski` subcommand
+- Add flags: `--size` (default 32), `--depth` (default 5), `--char` (default '*')
+- Call `sierpinski.Generate()` and print result to stdout
+
+**Verify:**
+- `./fractals sierpinski` outputs a triangle
+- `./fractals sierpinski --size 16 --depth 3` outputs smaller triangle
+- `./fractals sierpinski --help` shows flag documentation
+
+---
+
+### Task 5: Mandelbrot Algorithm
+
+Implement the Mandelbrot set ASCII renderer.
+
+**Do:**
+- Create `internal/mandelbrot/mandelbrot.go`
+- Implement `Render(width, height, maxIter int, char string) []string`
+- Map complex plane region (-2.5 to 1.0 real, -1.0 to 1.0 imaginary) to output dimensions
+- Map iteration count to character gradient " .:-=+*#%@" (or single char if provided)
+- Create `internal/mandelbrot/mandelbrot_test.go` with tests:
+  - Output dimensions match requested width/height
+  - Known point inside set (0,0) maps to max-iteration character
+  - Known point outside set (2,0) maps to low-iteration character
+
+**Verify:**
+- `go test ./internal/mandelbrot/...` passes
+
+---
+
+### Task 6: Mandelbrot CLI Integration
+
+Wire the Mandelbrot algorithm to a CLI subcommand.
+
+**Do:**
+- Create `internal/cli/mandelbrot.go` with `mandelbrot` subcommand
+- Add flags: `--width` (default 80), `--height` (default 24), `--iterations` (default 100), `--char` (default "")
+- Call `mandelbrot.Render()` and print result to stdout
+
+**Verify:**
+- `./fractals mandelbrot` outputs recognizable Mandelbrot set
+- `./fractals mandelbrot --width 40 --height 12` outputs smaller version
+- `./fractals mandelbrot --help` shows flag documentation
+
+---
+
+### Task 7: Character Set Configuration
+
+Ensure `--char` flag works consistently across both commands.
+
+**Do:**
+- Verify Sierpinski `--char` flag passes character to algorithm
+- For Mandelbrot, `--char` should use single character instead of gradient
+- Add tests for custom character output
+
+**Verify:**
+- `./fractals sierpinski --char '#'` uses '#' character
+- `./fractals mandelbrot --char '.'` uses '.' for all filled points
+- Tests pass
+
+---
+
+### Task 8: Input Validation and Error Handling
+
+Add validation for invalid inputs.
+
+**Do:**
+- Sierpinski: size must be > 0, depth must be >= 0
+- Mandelbrot: width/height must be > 0, iterations must be > 0
+- Return clear error messages for invalid inputs
+- Add tests for error cases
+
+**Verify:**
+- `./fractals sierpinski --size 0` prints error, exits non-zero
+- `./fractals mandelbrot --width -1` prints error, exits non-zero
+- Error messages are clear and helpful
+
+---
+
+### Task 9: Integration Tests
+
+Add integration tests that invoke the CLI.
+
+**Do:**
+- Create `cmd/fractals/main_test.go` or `test/integration_test.go`
+- Test full CLI invocation for both commands
+- Verify output format and exit codes
+- Test error cases return non-zero exit
+
+**Verify:**
+- `go test ./...` passes all tests including integration tests
+
+---
+
+### Task 10: README
+
+Document usage and examples.
+
+**Do:**
+- Create `README.md` with:
+  - Project description
+  - Installation: `go install ./cmd/fractals`
+  - Usage examples for both commands
+  - Example output (small samples)
+
+**Verify:**
+- README accurately describes the tool
+- Examples in README actually work

.agent/vendor/superpowers/tests/subagent-driven-dev/go-fractals/scaffold.sh

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+# Scaffold the Go Fractals test project
+# Usage: ./scaffold.sh /path/to/target/directory
+
+set -e
+
+TARGET_DIR="${1:?Usage: $0 <target-directory>}"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+# Create target directory
+mkdir -p "$TARGET_DIR"
+cd "$TARGET_DIR"
+
+# Initialize git repo
+git init
+
+# Copy design and plan
+cp "$SCRIPT_DIR/design.md" .
+cp "$SCRIPT_DIR/plan.md" .
+
+# Create .claude settings to allow reads/writes in this directory
+mkdir -p .claude
+cat > .claude/settings.local.json << 'SETTINGS'
+{
+  "permissions": {
+    "allow": [
+      "Read(**)",
+      "Edit(**)",
+      "Write(**)",
+      "Bash(go:*)",
+      "Bash(mkdir:*)",
+      "Bash(git:*)"
+    ]
+  }
+}
+SETTINGS
+
+# Create initial commit
+git add .
+git commit -m "Initial project setup with design and plan"
+
+echo "Scaffolded Go Fractals project at: $TARGET_DIR"
+echo ""
+echo "To run the test:"
+echo "  claude -p \"Execute this plan using superpowers:subagent-driven-development. Plan: $TARGET_DIR/plan.md\" --plugin-dir /path/to/superpowers"

.agent/vendor/superpowers/tests/subagent-driven-dev/run-test.sh

@@ -0,0 +1,106 @@
+#!/usr/bin/env bash
+# Run a subagent-driven-development test
+# Usage: ./run-test.sh <test-name> [--plugin-dir <path>]
+#
+# Example:
+#   ./run-test.sh go-fractals
+#   ./run-test.sh svelte-todo --plugin-dir /path/to/superpowers
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+TEST_NAME="${1:?Usage: $0 <test-name> [--plugin-dir <path>]}"
+shift
+
+# Parse optional arguments
+PLUGIN_DIR=""
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    --plugin-dir)
+      PLUGIN_DIR="$2"
+      shift 2
+      ;;
+    *)
+      echo "Unknown option: $1"
+      exit 1
+      ;;
+  esac
+done
+
+# Default plugin dir to parent of tests directory
+if [[ -z "$PLUGIN_DIR" ]]; then
+  PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+fi
+
+# Verify test exists
+TEST_DIR="$SCRIPT_DIR/$TEST_NAME"
+if [[ ! -d "$TEST_DIR" ]]; then
+  echo "Error: Test '$TEST_NAME' not found at $TEST_DIR"
+  echo "Available tests:"
+  ls -1 "$SCRIPT_DIR" | grep -v '\.sh$' | grep -v '\.md$'
+  exit 1
+fi
+
+# Create timestamped output directory
+TIMESTAMP=$(date +%s)
+OUTPUT_BASE="/tmp/superpowers-tests/$TIMESTAMP/subagent-driven-development"
+OUTPUT_DIR="$OUTPUT_BASE/$TEST_NAME"
+mkdir -p "$OUTPUT_DIR"
+
+echo "=== Subagent-Driven Development Test ==="
+echo "Test: $TEST_NAME"
+echo "Output: $OUTPUT_DIR"
+echo "Plugin: $PLUGIN_DIR"
+echo ""
+
+# Scaffold the project
+echo ">>> Scaffolding project..."
+"$TEST_DIR/scaffold.sh" "$OUTPUT_DIR/project"
+echo ""
+
+# Prepare the prompt
+PLAN_PATH="$OUTPUT_DIR/project/plan.md"
+PROMPT="Execute this plan using superpowers:subagent-driven-development. The plan is at: $PLAN_PATH"
+
+# Run Claude with JSON output for token tracking
+LOG_FILE="$OUTPUT_DIR/claude-output.json"
+echo ">>> Running Claude..."
+echo "Prompt: $PROMPT"
+echo "Log file: $LOG_FILE"
+echo ""
+
+# Run claude and capture output
+# Using stream-json to get token usage stats
+# --dangerously-skip-permissions for automated testing (subagents don't inherit parent settings)
+cd "$OUTPUT_DIR/project"
+claude -p "$PROMPT" \
+  --plugin-dir "$PLUGIN_DIR" \
+  --dangerously-skip-permissions \
+  --output-format stream-json \
+  --verbose \
+  > "$LOG_FILE" 2>&1 || true
+
+# Extract final stats
+echo ""
+echo ">>> Test complete"
+echo "Project directory: $OUTPUT_DIR/project"
+echo "Claude log: $LOG_FILE"
+echo ""
+
+# Show token usage if available
+if command -v jq &> /dev/null; then
+  echo ">>> Token usage:"
+  # Extract usage from the last message with usage info
+  jq -s '[.[] | select(.type == "result")] | last | .usage' "$LOG_FILE" 2>/dev/null || echo "(could not parse usage)"
+  echo ""
+fi
+
+echo ">>> Next steps:"
+echo "1. Review the project: cd $OUTPUT_DIR/project"
+echo "2. Review Claude's log: less $LOG_FILE"
+echo "3. Check if tests pass:"
+if [[ "$TEST_NAME" == "go-fractals" ]]; then
+  echo "   cd $OUTPUT_DIR/project && go test ./..."
+elif [[ "$TEST_NAME" == "svelte-todo" ]]; then
+  echo "   cd $OUTPUT_DIR/project && npm test && npx playwright test"
+fi

.agent/vendor/superpowers/tests/subagent-driven-dev/svelte-todo/design.md

@@ -0,0 +1,70 @@
+# Svelte Todo List - Design
+
+## Overview
+
+A simple todo list application built with Svelte. Supports creating, completing, and deleting todos with localStorage persistence.
+
+## Features
+
+- Add new todos
+- Mark todos as complete/incomplete
+- Delete todos
+- Filter by: All / Active / Completed
+- Clear all completed todos
+- Persist to localStorage
+- Show count of remaining items
+
+## User Interface
+
+```
+┌─────────────────────────────────────────┐
+│  Svelte Todos                           │
+├─────────────────────────────────────────┤
+│  [________________________] [Add]       │
+├─────────────────────────────────────────┤
+│  [ ] Buy groceries                  [x] │
+│  [✓] Walk the dog                   [x] │
+│  [ ] Write code                     [x] │
+├─────────────────────────────────────────┤
+│  2 items left                           │
+│  [All] [Active] [Completed]  [Clear ✓]  │
+└─────────────────────────────────────────┘
+```
+
+## Components
+
+```
+src/
+  App.svelte           # Main app, state management
+  lib/
+    TodoInput.svelte   # Text input + Add button
+    TodoList.svelte    # List container
+    TodoItem.svelte    # Single todo with checkbox, text, delete
+    FilterBar.svelte   # Filter buttons + clear completed
+    store.ts           # Svelte store for todos
+    storage.ts         # localStorage persistence
+```
+
+## Data Model
+
+```typescript
+interface Todo {
+  id: string;        // UUID
+  text: string;      // Todo text
+  completed: boolean;
+}
+
+type Filter = 'all' | 'active' | 'completed';
+```
+
+## Acceptance Criteria
+
+1. Can add a todo by typing and pressing Enter or clicking Add
+2. Can toggle todo completion by clicking checkbox
+3. Can delete a todo by clicking X button
+4. Filter buttons show correct subset of todos
+5. "X items left" shows count of incomplete todos
+6. "Clear completed" removes all completed todos
+7. Todos persist across page refresh (localStorage)
+8. Empty state shows helpful message
+9. All tests pass

.agent/vendor/superpowers/tests/subagent-driven-dev/svelte-todo/plan.md

@@ -0,0 +1,222 @@
+# Svelte Todo List - Implementation Plan
+
+Execute this plan using the `superpowers:subagent-driven-development` skill.
+
+## Context
+
+Building a todo list app with Svelte. See `design.md` for full specification.
+
+## Tasks
+
+### Task 1: Project Setup
+
+Create the Svelte project with Vite.
+
+**Do:**
+- Run `npm create vite@latest . -- --template svelte-ts`
+- Install dependencies with `npm install`
+- Verify dev server works
+- Clean up default Vite template content from App.svelte
+
+**Verify:**
+- `npm run dev` starts server
+- App shows minimal "Svelte Todos" heading
+- `npm run build` succeeds
+
+---
+
+### Task 2: Todo Store
+
+Create the Svelte store for todo state management.
+
+**Do:**
+- Create `src/lib/store.ts`
+- Define `Todo` interface with id, text, completed
+- Create writable store with initial empty array
+- Export functions: `addTodo(text)`, `toggleTodo(id)`, `deleteTodo(id)`, `clearCompleted()`
+- Create `src/lib/store.test.ts` with tests for each function
+
+**Verify:**
+- Tests pass: `npm run test` (install vitest if needed)
+
+---
+
+### Task 3: localStorage Persistence
+
+Add persistence layer for todos.
+
+**Do:**
+- Create `src/lib/storage.ts`
+- Implement `loadTodos(): Todo[]` and `saveTodos(todos: Todo[])`
+- Handle JSON parse errors gracefully (return empty array)
+- Integrate with store: load on init, save on change
+- Add tests for load/save/error handling
+
+**Verify:**
+- Tests pass
+- Manual test: add todo, refresh page, todo persists
+
+---
+
+### Task 4: TodoInput Component
+
+Create the input component for adding todos.
+
+**Do:**
+- Create `src/lib/TodoInput.svelte`
+- Text input bound to local state
+- Add button calls `addTodo()` and clears input
+- Enter key also submits
+- Disable Add button when input is empty
+- Add component tests
+
+**Verify:**
+- Tests pass
+- Component renders input and button
+
+---
+
+### Task 5: TodoItem Component
+
+Create the single todo item component.
+
+**Do:**
+- Create `src/lib/TodoItem.svelte`
+- Props: `todo: Todo`
+- Checkbox toggles completion (calls `toggleTodo`)
+- Text with strikethrough when completed
+- Delete button (X) calls `deleteTodo`
+- Add component tests
+
+**Verify:**
+- Tests pass
+- Component renders checkbox, text, delete button
+
+---
+
+### Task 6: TodoList Component
+
+Create the list container component.
+
+**Do:**
+- Create `src/lib/TodoList.svelte`
+- Props: `todos: Todo[]`
+- Renders TodoItem for each todo
+- Shows "No todos yet" when empty
+- Add component tests
+
+**Verify:**
+- Tests pass
+- Component renders list of TodoItems
+
+---
+
+### Task 7: FilterBar Component
+
+Create the filter and status bar component.
+
+**Do:**
+- Create `src/lib/FilterBar.svelte`
+- Props: `todos: Todo[]`, `filter: Filter`, `onFilterChange: (f: Filter) => void`
+- Show count: "X items left" (incomplete count)
+- Three filter buttons: All, Active, Completed
+- Active filter is visually highlighted
+- "Clear completed" button (hidden when no completed todos)
+- Add component tests
+
+**Verify:**
+- Tests pass
+- Component renders count, filters, clear button
+
+---
+
+### Task 8: App Integration
+
+Wire all components together in App.svelte.
+
+**Do:**
+- Import all components and store
+- Add filter state (default: 'all')
+- Compute filtered todos based on filter state
+- Render: heading, TodoInput, TodoList, FilterBar
+- Pass appropriate props to each component
+
+**Verify:**
+- App renders all components
+- Adding todos works
+- Toggling works
+- Deleting works
+
+---
+
+### Task 9: Filter Functionality
+
+Ensure filtering works end-to-end.
+
+**Do:**
+- Verify filter buttons change displayed todos
+- 'all' shows all todos
+- 'active' shows only incomplete todos
+- 'completed' shows only completed todos
+- Clear completed removes completed todos and resets filter if needed
+- Add integration tests
+
+**Verify:**
+- Filter tests pass
+- Manual verification of all filter states
+
+---
+
+### Task 10: Styling and Polish
+
+Add CSS styling for usability.
+
+**Do:**
+- Style the app to match the design mockup
+- Completed todos have strikethrough and muted color
+- Active filter button is highlighted
+- Input has focus styles
+- Delete button appears on hover (or always on mobile)
+- Responsive layout
+
+**Verify:**
+- App is visually usable
+- Styles don't break functionality
+
+---
+
+### Task 11: End-to-End Tests
+
+Add Playwright tests for full user flows.
+
+**Do:**
+- Install Playwright: `npm init playwright@latest`
+- Create `tests/todo.spec.ts`
+- Test flows:
+  - Add a todo
+  - Complete a todo
+  - Delete a todo
+  - Filter todos
+  - Clear completed
+  - Persistence (add, reload, verify)
+
+**Verify:**
+- `npx playwright test` passes
+
+---
+
+### Task 12: README
+
+Document the project.
+
+**Do:**
+- Create `README.md` with:
+  - Project description
+  - Setup: `npm install`
+  - Development: `npm run dev`
+  - Testing: `npm test` and `npx playwright test`
+  - Build: `npm run build`
+
+**Verify:**
+- README accurately describes the project
+- Instructions work

.agent/vendor/superpowers/tests/subagent-driven-dev/svelte-todo/scaffold.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+# Scaffold the Svelte Todo test project
+# Usage: ./scaffold.sh /path/to/target/directory
+
+set -e
+
+TARGET_DIR="${1:?Usage: $0 <target-directory>}"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+# Create target directory
+mkdir -p "$TARGET_DIR"
+cd "$TARGET_DIR"
+
+# Initialize git repo
+git init
+
+# Copy design and plan
+cp "$SCRIPT_DIR/design.md" .
+cp "$SCRIPT_DIR/plan.md" .
+
+# Create .claude settings to allow reads/writes in this directory
+mkdir -p .claude
+cat > .claude/settings.local.json << 'SETTINGS'
+{
+  "permissions": {
+    "allow": [
+      "Read(**)",
+      "Edit(**)",
+      "Write(**)",
+      "Bash(npm:*)",
+      "Bash(npx:*)",
+      "Bash(mkdir:*)",
+      "Bash(git:*)"
+    ]
+  }
+}
+SETTINGS
+
+# Create initial commit
+git add .
+git commit -m "Initial project setup with design and plan"
+
+echo "Scaffolded Svelte Todo project at: $TARGET_DIR"
+echo ""
+echo "To run the test:"
+echo "  claude -p \"Execute this plan using superpowers:subagent-driven-development. Plan: $TARGET_DIR/plan.md\" --plugin-dir /path/to/superpowers"