qualia-framework-v2 2.10.0 → 3.0.0

package/skills/qualia-polish/SKILL.md

@@ -1,11 +1,24 @@
 ---
 name: qualia-polish
-description: "Design and UX pass — critique, polish, harden. Run after all phases are verified."
+description: "Design and UX pass — anti-AI-slop, genuine craft, responsive, accessible. Run after all phases are verified."
 ---
 
 # /qualia-polish — Design Pass
 
-Run after all feature phases are verified. Makes it look production-ready.
+Makes it look like a human designer built it. Kills AI slop. Run after all feature phases are verified.
+
+## The Standard
+
+Every site Qualia ships must feel **designed, not generated.** AI-generated sites have tells:
+- Identical card grids with rounded corners and soft shadows
+- Blue-purple gradients on everything
+- Inter/system-ui font with no hierarchy
+- Generic hero with centered text and a stock gradient background
+- Fixed-width containers leaving dead space on wide screens
+- No motion, no personality, no opinion
+- Perfect symmetry everywhere (real design has tension)
+
+**Kill all of these.** A Qualia site should make someone ask "who designed this?" — not "which template is this?"
 
 ## Process
 
@@ -19,139 +32,163 @@ node ~/.claude/bin/qualia-ui.js banner polish
 cat .planning/DESIGN.md 2>/dev/null || echo "NO_DESIGN"
 ```
 
-If DESIGN.md exists → use it as the standard. If not → use Qualia defaults from `rules/frontend.md`.
+If DESIGN.md exists → it's the standard. If not → use `rules/frontend.md` defaults.
 
 Read EVERY frontend file before modifying. No blind edits.
 
-### 1. Critique (Structured Audit)
-
-Review the entire UI against this checklist. Check each item, note violations with file:line.
-
-**Typography:**
-- [ ] No generic fonts (Inter, Roboto, Arial, system-ui, Space Grotesk)
-- [ ] Proper type scale with clear hierarchy (display → heading → body → caption)
-- [ ] Body text: 16px+, line-height 1.5–1.7
-- [ ] Headings: tighter line-height (1.1–1.3), negative letter-spacing for large sizes
-- [ ] Prose max-width: 65ch
-- [ ] Font weights used for hierarchy (Regular, Medium, Semibold, Bold)
-
-**Color & Contrast:**
-- [ ] Cohesive palette via CSS variables (not scattered hex values)
-- [ ] All text passes WCAG AA contrast (4.5:1 normal, 3:1 large)
-- [ ] CTA buttons use accent color — stand out from the page
-- [ ] No blue-purple gradients, no rainbow palettes
-- [ ] Dark mode: rethought surfaces (not just inverted)
-- [ ] Semantic colors used consistently (success=green, error=red, warning=amber)
-
-**Layout & Spacing:**
-- [ ] Full-width fluid layouts — no hardcoded max-width caps
-- [ ] 8px spacing grid followed consistently
-- [ ] Tight spacing within groups, generous between sections
-- [ ] Fluid padding: `clamp(1rem, 5vw, 4rem)` horizontal
-- [ ] No identical card grids — varied visual hierarchy
-- [ ] No generic heroes — purposeful, distinctive
-
-**Interactive States:**
-- [ ] Every button/link: hover (color shift, 150ms), focus (visible ring), active (press feedback), disabled
-- [ ] Loading: skeleton or spinner on all async operations
-- [ ] Empty: helpful message + action on empty lists/data
-- [ ] Error: user-friendly message + recovery action on failed fetches
-- [ ] Form validation: inline errors with `aria-describedby`
-
-**Motion:**
-- [ ] Hover/focus: 150–200ms transitions
-- [ ] Page load: staggered entrance animations (50–80ms delay)
-- [ ] Expand/collapse: 250ms ease-in-out
-- [ ] `prefers-reduced-motion` respected (no animation for users who opt out)
-- [ ] No jank: transforms and opacity only for animated properties
-
-**Accessibility:**
-- [ ] Semantic HTML: `nav`, `main`, `section`, `article`, `header`, `footer`
-- [ ] One `h1` per page, sequential heading hierarchy
-- [ ] All images: descriptive `alt` (or `alt=""` + `aria-hidden` if decorative)
-- [ ] All form inputs: visible `<label>` with `htmlFor` — not placeholder-only
-- [ ] All interactive elements: keyboard accessible (Tab/Enter/Escape)
-- [ ] Touch targets: 44px minimum
-- [ ] Skip link: `<a href="#main">` as first focusable element
-- [ ] No `outline: none` without focus replacement
-- [ ] `<html lang="en">` set
-- [ ] Color not sole information carrier — icons/text as supplements
-
-**Responsive:**
-- [ ] Mobile-first approach (base styles for mobile, min-width breakpoints for larger)
-- [ ] No horizontal scroll at 320px
-- [ ] Navigation: hamburger on mobile, expanded on desktop
-- [ ] Touch targets adequate on mobile (44px min)
-- [ ] Fluid typography with `clamp()`
-- [ ] Images: `max-width: 100%`, responsive srcset where needed
-- [ ] Tables: card view or horizontal scroll on mobile
-
-**Performance:**
-- [ ] Server Components by default — `'use client'` only when needed
-- [ ] Images via `next/image` with width/height
-- [ ] No barrel file imports — direct imports from source
-- [ ] Heavy components lazy-loaded with `next/dynamic`
-- [ ] Data fetched in parallel, not sequentially
-
-### 2. Fix Everything
-
-Work through violations from the critique. Fix each category:
-
-1. Typography first (sets the visual foundation)
-2. Color & contrast (palette coherence)
-3. Layout & spacing (structural fixes)
-4. Interactive states (loading, empty, error, hover, focus)
-5. Motion (transitions, entrance animations, reduced-motion)
-6. Accessibility (semantic HTML, ARIA, keyboard, labels)
-7. Responsive (mobile breakpoints, fluid sizing)
-8. Performance (quick wins — image optimization, dynamic imports)
-
-### 3. Harden
-
-After polish, stress-test edge cases:
-- Long text content (overflow, truncation, word-break)
-- Extremely long usernames or email addresses
-- Empty data everywhere simultaneously
-- Error state on every fetch simultaneously
-- 320px viewport width
-- Keyboard-only navigation through entire flow
-- Screen reader landmarks check (semantic HTML)
-- Right-to-left text (if i18n is planned)
-- Slow network (loading states visible, no flash of empty content)
-
-### 4. Verify
+### 1. AI Slop Detector
+
+Run these checks first. Any hits = mandatory fixes.
 
 ```bash
-npx tsc --noEmit 2>&1 | head -20
+# Generic fonts (the #1 AI tell)
+grep -rn "Inter\|Roboto\|Arial\|Helvetica\|system-ui\|Space.Grotesk" --include="*.tsx" --include="*.css" --include="*.scss" --include="tailwind*" app/ components/ src/ 2>/dev/null | grep -v node_modules
+
+# Hardcoded max-width containers (screams template)
+grep -rn "max-w-7xl\|max-w-\[1200\|max-w-\[1280\|max-width.*1200\|max-width.*1280" --include="*.tsx" --include="*.css" app/ components/ src/ 2>/dev/null
+
+# Blue-purple gradients
+grep -rn "from-blue.*to-purple\|from-purple.*to-blue\|linear-gradient.*blue.*purple\|linear-gradient.*purple.*blue\|from-indigo.*to-violet" --include="*.tsx" --include="*.css" app/ components/ src/ 2>/dev/null
+
+# Card grid monotony (same card component repeated in a grid)
+grep -rn "grid-cols-3\|grid-cols-4" --include="*.tsx" app/ components/ src/ 2>/dev/null | head -5
+
+# Generic hero patterns
+grep -rn "text-center.*mx-auto\|Hero\|hero" --include="*.tsx" app/ components/ src/ 2>/dev/null | head -5
+
+# Scattered hardcoded colors (no design system)
+grep -rn "text-\[#\|bg-\[#\|border-\[#\|color:.*#\|background:.*#" --include="*.tsx" app/ components/ src/ 2>/dev/null | wc -l
 ```
 
-Fix any TypeScript errors before committing.
+**Every hit gets fixed.** Not flagged — fixed.
+
+### 2. Typography Pass
+
+**Goal:** A reader should feel the type was chosen, not defaulted.
+
+- Pick a distinctive display font. Not Inter, not Roboto, not system. Something with character: Clash Display, Cabinet Grotesk, General Sans, Satoshi, Plus Jakarta Sans, Outfit, Sora, Manrope. Pair with a clean body font.
+- Establish clear hierarchy: display (hero text) → h1 → h2 → h3 → body → caption
+- Body: 16px minimum, line-height 1.5-1.7
+- Headings: tighter line-height (1.1-1.3), negative letter-spacing (-0.02em) for display sizes
+- Weight hierarchy: Regular (400) for body, Medium (500) for labels, Semibold (600) for headings, Bold (700) for display
+- Prose content: `max-width: 65ch`. Everything else: fluid full-width.
+- Use `clamp()` for fluid sizing: `clamp(2rem, 1rem + 3vw, 3.75rem)` for h1
+
+### 3. Color & Surfaces
+
+**Goal:** A palette that looks intentional, not random.
+
+- Define all colors as CSS variables or Tailwind config — zero scattered hex values
+- One dominant brand color. One sharp accent for CTAs that pops against the page.
+- Surfaces: layer them. Background → card → elevated card. Use subtle shade differences, not just white-on-white.
+- Dark mode (if present): rethink surfaces, don't just invert. Slightly reduce contrast. Use darker brand colors, not just white→black swap.
+- Semantic colors with non-color indicators: success (green + checkmark), error (red + icon), warning (amber + triangle)
+- Verify WCAG AA: 4.5:1 for normal text, 3:1 for large text (18px+ bold or 24px+)
+
+### 4. Layout & Spacing
+
+**Goal:** Full-width, fluid, generous. No dead space gutters.
+
+- Full-width layouts with fluid padding: `clamp(1rem, 5vw, 4rem)` horizontal
+- 8px spacing grid: 4, 8, 12, 16, 24, 32, 48, 64, 96
+- Tight spacing within groups (related items). Generous spacing between sections.
+- Break symmetry where it serves the design — offset grids, overlapping elements, diagonal flow
+- Varied layouts: not every section should be a centered-text-with-cards-below. Use side-by-side, staggered, asymmetric, full-bleed.
+- Section spacing: `clamp(2rem, 8vw, 6rem)` vertical padding
+
+### 5. Interactive States
 
-### 5. Commit & Transition
+**Goal:** Every clickable thing responds. Every async operation shows progress.
+
+- **Hover:** color shift or underline within 150ms ease-out. `cursor: pointer` on ALL clickables.
+- **Focus:** visible ring (2px+ offset, contrasting color). Never `outline: none` without replacement.
+- **Active/pressed:** subtle scale down (`transform: scale(0.98)`) or color shift.
+- **Disabled:** opacity 0.5 + `cursor: not-allowed` + `aria-disabled="true"`
+- **Loading:** skeleton shimmer or spinner on every async operation. Never a blank void.
+- **Empty:** helpful message + CTA on empty lists/tables. Not just "No results."
+- **Error:** user-friendly message + recovery action. Not raw error text. Use `aria-live="assertive"`.
+
+### 6. Motion & Personality
+
+**Goal:** The site feels alive, not static. But tasteful — not a circus.
+
+- Page load: stagger children entrance (50-80ms delay between items, `fadeUp` animation, 300ms)
+- Hover transitions: 150-200ms ease-out
+- Section transitions: 300-500ms with `cubic-bezier(0.4, 0, 0.2, 1)`
+- One signature motion that gives the site personality (parallax, scroll-triggered reveal, magnetic buttons, morphing shapes)
+- **Always** `prefers-reduced-motion: reduce` — disable non-essential animation
+- CSS-only for static sites, `motion/react` (formerly Framer Motion) for React
+
+### 7. Accessibility (Non-Negotiable)
+
+- Semantic HTML: `nav`, `main`, `section`, `article`, `header`, `footer` — not div soup
+- One `h1` per page, sequential heading order (no h1 → h3 skip)
+- All images: descriptive `alt` (or `alt=""` + `aria-hidden` if decorative)
+- All form inputs: visible `<label>` with `htmlFor` — not placeholder-only
+- All interactive elements: keyboard accessible (Tab, Enter, Escape, Arrow keys)
+- Touch targets: 44x44px minimum
+- Skip link: `<a href="#main" class="sr-only focus:not-sr-only">` as first focusable element
+- `<html lang="en">` set
+- Color never the sole information carrier — icons, text, patterns as supplements
+- `aria-live="polite"` for toast notifications and dynamic content updates
+
+### 8. Responsive (Mobile-First)
+
+- Base styles for mobile (320px), scale up with `min-width` breakpoints
+- Test at: 320px (small phone), 375px (iPhone), 768px (iPad), 1024px (laptop), 1440px (desktop)
+- No horizontal scroll at any viewport
+- Navigation: hamburger/drawer on mobile, full horizontal on desktop
+- Stack on mobile, expand on desktop
+- Fluid typography with `clamp()`
+- Images: `max-width: 100%`, responsive `srcset`, `next/image` with width/height
+- Tables: card layout or horizontal scroll on mobile
+
+### 9. Harden (Edge Cases)
+
+After all visual work, stress-test:
+- Long text: does a 200-character username break the layout?
+- Empty everywhere: all lists empty, all data missing — does it still make sense?
+- Error everywhere: every fetch fails — are error states visible and helpful?
+- 320px viewport: nothing overflows, nothing clips, nothing overlaps
+- Keyboard only: Tab through the entire app — can you reach everything? Is focus visible?
+- Slow network: are loading states visible? Does content stream in or flash?
+
+### 10. Verify & Ship
+
+```bash
+npx tsc --noEmit 2>&1 | head -20
+```
+
+Fix any TypeScript errors.
 
 ```bash
 git add {changed files}
-git commit -m "polish: design and UX pass — typography, accessibility, responsive, states"
+git commit -m "polish: design pass — typography, color, states, motion, responsive, a11y"
 ```
 
 ```bash
 node ~/.claude/bin/state.js transition --to polished
 ```
-Do NOT manually edit STATE.md or tracking.json — state.js handles both.
-
-### 6. Report
 
 ```bash
 node ~/.claude/bin/qualia-ui.js divider
-node ~/.claude/bin/qualia-ui.js info "Files modified: {N}"
-node ~/.claude/bin/qualia-ui.js ok "Typography — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "Color — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "Layout — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "States — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "Motion — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "Accessibility — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "Responsive — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "Performance — {brief}"
-node ~/.claude/bin/qualia-ui.js ok "Hardening — {brief}"
+node ~/.claude/bin/qualia-ui.js ok "AI slop: killed"
+node ~/.claude/bin/qualia-ui.js ok "Typography: {brief}"
+node ~/.claude/bin/qualia-ui.js ok "Color: {brief}"
+node ~/.claude/bin/qualia-ui.js ok "Layout: {brief}"
+node ~/.claude/bin/qualia-ui.js ok "States: {brief}"
+node ~/.claude/bin/qualia-ui.js ok "Motion: {brief}"
+node ~/.claude/bin/qualia-ui.js ok "Accessibility: {brief}"
+node ~/.claude/bin/qualia-ui.js ok "Responsive: {brief}"
+node ~/.claude/bin/qualia-ui.js ok "Hardened: {brief}"
 node ~/.claude/bin/qualia-ui.js end "POLISHED" "/qualia-ship"
 ```
+
+## Rules
+
+1. **Read before write.** Understand every file before changing it.
+2. **DESIGN.md is law.** If it exists, follow it. Don't override client decisions.
+3. **Don't break functionality.** Only change styling, never logic.
+4. **AI slop is a bug.** Generic fonts, card grids, blue-purple gradients, centered-everything — treat these as defects, not preferences.
+5. **TypeScript must pass** after every change.
+6. **One commit** at the end — not per category.

package/skills/qualia-report/SKILL.md

@@ -73,26 +73,35 @@ git commit -m "report: session {YYYY-MM-DD}"
 git push
 ```
 
-### 5. Upload to ERP
+### 5. Upload to ERP (if enabled)
 
-**This step is MANDATORY** — the clock-out modal requires the report to be uploaded.
+Read `~/.claude/.qualia-config.json` and check the `erp` object:
+- If `erp.enabled` is `false`, skip this step and print: "ERP upload skipped (disabled in config)."
+- If `erp.enabled` is `true` (default) or the `erp` field is missing (backward compatibility), proceed with the upload.
 
 ```bash
-ERP_URL="https://portal.qualiasolutions.net"
+# Read ERP config
+ERP_URL=$(node -e "try{const c=JSON.parse(require('fs').readFileSync(require('os').homedir()+'/.claude/.qualia-config.json','utf8'));console.log(c.erp?.url||'https://portal.qualiasolutions.net')}catch{console.log('https://portal.qualiasolutions.net')}")
+ERP_ENABLED=$(node -e "try{const c=JSON.parse(require('fs').readFileSync(require('os').homedir()+'/.claude/.qualia-config.json','utf8'));console.log(c.erp?.enabled!==false)}catch{console.log('true')}")
+
 API_KEY=$(cat ~/.claude/.erp-api-key 2>/dev/null)
 REPORT_FILE=".planning/reports/report-{date}.md"
 EMAIL=$(git config user.email)
 PROJECT=$(basename $(pwd))
 
-curl -s -X POST "$ERP_URL/api/claude/report-upload" \
-  -H "X-API-Key: $API_KEY" \
-  -F "file=@$REPORT_FILE" \
-  -F "employee_email=$EMAIL" \
-  -F "project_name=$PROJECT"
+# Only upload if ERP is enabled
+if [ "$ERP_ENABLED" = "true" ]; then
+  curl -s -X POST "$ERP_URL/api/claude/report-upload" \
+    -H "X-API-Key: $API_KEY" \
+    -F "file=@$REPORT_FILE" \
+    -F "employee_email=$EMAIL" \
+    -F "project_name=$PROJECT"
+fi
 ```
 
 If the upload succeeds, print: "Report uploaded to ERP. You can now clock out."
 If it fails (no API key, network error), print the error and tell the employee to ask Fawzi.
+If ERP is disabled, print: "ERP upload skipped (disabled in config)."
 
 ### 6. Update State
 

package/skills/qualia-review/SKILL.md

@@ -1,76 +1,161 @@
 ---
 name: qualia-review
-description: "Production audit and code review. General review, --web for web app audit, --ai for AI/voice agent audit. Trigger on 'review', 'audit', 'code review', 'security check', 'production check'."
+description: "Production audit with scored diagnostics. Runs real commands, scores findings by severity. Trigger on 'review', 'audit', 'code review', 'security check', 'production check'."
 ---
 
 # /qualia-review — Production Audit
 
-Deep review with severity-scored findings. Different from `/qualia-verify` (which checks phase goals). This checks production readiness.
+Runs real diagnostic commands and scores every finding. Not a checklist — an executable audit.
 
 ## Usage
 
-- `/qualia-review` — General code review
-- `/qualia-review --web` — Web app production audit
-- `/qualia-review --ai` — AI/voice agent audit
+- `/qualia-review` — Full audit (security + quality + performance)
+- `/qualia-review --web` — Adds web-specific checks (headers, CORS, vitals)
+- `/qualia-review --ai` — Adds AI/voice agent checks (prompt safety, latency)
 
-## General Review (default)
+## Process
 
 ```bash
 node ~/.claude/bin/qualia-ui.js banner review
 ```
 
-Spawn parallel agents analyzing:
+### 0. Load Context
 
-1. **Code Quality** — Clean code, TypeScript strictness, naming, readability
-2. **Security** — OWASP top 10, auth server-side, RLS policies, secrets scan
-3. **Architecture** — Component boundaries, coupling, API contracts
-4. **Performance** — N+1 queries, bundle size, caching, render performance
-5. **Test Coverage** — Gaps, edge cases, test quality
+```bash
+cat ~/.claude/knowledge/common-fixes.md 2>/dev/null
+cat ~/.claude/knowledge/learned-patterns.md 2>/dev/null
+```
 
-## --web (Web App Audit)
+Detect project shape:
+```bash
+ls package.json next.config.* tsconfig.json supabase/ app/ src/ 2>/dev/null
+```
 
-Full production readiness for Next.js + Supabase + Vercel:
+### 1. Security Scan
 
-**Security:** No secrets in code, HTTPS, CORS restricted, CSP headers, rate limiting, npm audit clean.
+Run every command. Record each finding with severity.
 
-**Performance:** Core Web Vitals (LCP < 2.5s, CLS < 0.1), image optimization, bundle analysis, query performance.
+```bash
+# CRITICAL: service_role in client code
+grep -rn "service_role" --include="*.ts" --include="*.tsx" --include="*.js" app/ components/ src/ lib/ 2>/dev/null | grep -v node_modules | grep -v "\.server\.\|[\\/]server[\\/]\|[\\/]app[\\/]api[\\/]\|route\.\|middleware\."
 
-**Reliability:** Error boundaries, API error handling, graceful degradation, health check endpoint.
+# CRITICAL: hardcoded secrets
+grep -rn "sk_live\|sk_test\|SUPABASE_SERVICE_ROLE\|eyJhbGciOi" --include="*.ts" --include="*.tsx" --include="*.js" app/ components/ src/ lib/ 2>/dev/null | grep -v node_modules | grep -v "\.env"
 
-**Observability:** Error tracking (Sentry), structured logging, uptime monitoring, analytics.
+# CRITICAL: dangerous patterns
+grep -rn "dangerouslySetInnerHTML\|eval(" --include="*.ts" --include="*.tsx" --include="*.js" app/ components/ src/ 2>/dev/null | grep -v node_modules
 
-## --ai (AI/Voice Agent Audit)
+# CRITICAL: .env files tracked in git
+git ls-files | grep -i "\.env" | grep -v "\.example\|\.template\|\.sample"
 
-Auto-detect stack (VAPI, ElevenLabs, Retell, OpenAI, Anthropic, pgvector).
+# HIGH: API routes without auth
+for f in $(find app/api -name "route.ts" -o -name "route.js" 2>/dev/null); do
+  grep -qL "getUser\|getSession\|auth()\|createClient" "$f" && echo "UNPROTECTED: $f"
+done
 
-**Prompt Safety:** System prompts not exposed, injection defenses, no eval() on AI output, token limits.
+# HIGH: API routes without input validation
+for f in $(find app/api -name "route.ts" -o -name "route.js" 2>/dev/null); do
+  grep -L "z\.\|zod\|Zod\|parse\|safeParse" "$f" 2>/dev/null
+done
 
-**Conversation Flow:** Off-topic handling, context window management, error recovery, human handoff.
+# HIGH: client-side database mutations
+grep -rn "\.insert\|\.update\|\.delete\|\.upsert" --include="*.tsx" --include="*.jsx" app/ components/ 2>/dev/null | grep -v "use server" | grep -v "\.server\."
 
-**Voice (if detected):** Latency < 500ms, interruption handling, silence timeout, webhook security.
+# MEDIUM: npm vulnerabilities
+npm audit --json 2>/dev/null | node -e "try{const d=JSON.parse(require('fs').readFileSync(0,'utf8'));const v=d.metadata?.vulnerabilities||{};console.log('critical:',v.critical||0,'high:',v.high||0,'moderate:',v.moderate||0)}catch{console.log('audit unavailable')}"
+```
 
-**RAG (if detected):** Embedding consistency, chunk size, retrieval relevance, index refresh.
+### 2. Code Quality Scan
 
-**Resilience:** Provider failover, timeout handling, cost monitoring, streaming error recovery.
+```bash
+# TypeScript errors (HIGH if >0)
+npx tsc --noEmit 2>&1 | grep -c "error TS"
 
-## Output
+# 'any' type usage (MEDIUM — count)
+grep -rn ": any\| as any" --include="*.ts" --include="*.tsx" app/ components/ src/ lib/ 2>/dev/null | grep -v node_modules | wc -l
 
-Every finding:
-- **What** — description
-- **Where** — `file:line`
-- **Fix** — concrete suggestion
-- **Severity** — CRITICAL / HIGH / MEDIUM / LOW
+# Empty catch blocks (HIGH)
+grep -rn "catch\s*{}\|catch\s*(.*)\s*{\s*}" --include="*.ts" --include="*.tsx" app/ components/ src/ lib/ 2>/dev/null | grep -v node_modules | head -10
 
-Write to `.planning/REVIEW.md`. CRITICAL or HIGH findings are deploy blockers — `/qualia-ship` checks for them.
+# TODO/FIXME left in code (LOW — count)
+grep -rn "TODO\|FIXME\|HACK\|XXX" --include="*.ts" --include="*.tsx" app/ components/ src/ lib/ 2>/dev/null | grep -v node_modules | wc -l
 
+# console.log in production code (LOW — count)
+grep -rn "console\.log" --include="*.ts" --include="*.tsx" app/ components/ src/ 2>/dev/null | grep -v node_modules | wc -l
 ```
-⬢ Review Complete
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-  Critical:  {N}
-  High:      {N}
-  Medium:    {N}
-  Low:       {N}
-
-  {If blockers: Fix CRITICAL/HIGH before /qualia-ship}
-  {If clean: Ready to ship}
+
+### 3. Performance Scan
+
+```bash
+# Build output — route sizes and first load JS
+npx next build 2>&1 | grep -E "Route|First Load|shared by all|○|●|ƒ|λ" | tail -25
+
+# Heavy files (>300 lines often means split needed)
+find app/ components/ src/ -name "*.tsx" -o -name "*.ts" 2>/dev/null | xargs wc -l 2>/dev/null | sort -rn | head -10
+
+# Missing next/image (MEDIUM)
+grep -rn "<img " --include="*.tsx" --include="*.jsx" app/ components/ src/ 2>/dev/null | grep -v "next/image" | wc -l
+
+# Client component ratio
+echo "use client: $(grep -rl "'use client'" --include="*.tsx" app/ components/ src/ 2>/dev/null | wc -l)"
+echo "total tsx: $(find app/ components/ src/ -name '*.tsx' 2>/dev/null | wc -l)"
+
+# Sequential data fetching (HIGH)
+grep -rn "const.*=.*await" --include="*.tsx" --include="*.ts" app/ src/ 2>/dev/null | grep -v "Promise.all\|Promise.allSettled" | head -10
 ```
+
+### 4. Score and Report
+
+Write to `.planning/REVIEW.md`:
+
+```markdown
+# Production Review — {YYYY-MM-DD}
+
+## Summary
+| Category | Critical | High | Medium | Low | Score |
+|----------|----------|------|--------|-----|-------|
+| Security | {n} | {n} | {n} | {n} | {1-5} |
+| Quality  | {n} | {n} | {n} | {n} | {1-5} |
+| Perf     | {n} | {n} | {n} | {n} | {1-5} |
+| **Total** | {n} | {n} | {n} | {n} | **{avg}/5** |
+
+## Findings
+
+### CRITICAL
+- **{title}** — `{file}:{line}` — {what's wrong} — Fix: {how}
+
+### HIGH
+- ...
+
+### MEDIUM
+- ...
+
+### LOW
+- ...
+
+## Verdict
+{PASS: no critical/high | FAIL: N blockers — fix before /qualia-ship}
+```
+
+**Scoring:**
+- 5 = zero high/critical, fewer than 3 medium
+- 4 = zero critical, 1 high or fewer than 5 medium
+- 3 = zero critical, 2-3 high
+- 2 = 1 critical or 4+ high
+- 1 = multiple critical
+
+```bash
+node ~/.claude/bin/qualia-ui.js divider
+node ~/.claude/bin/qualia-ui.js info "Security: {score}/5 ({n} findings)"
+node ~/.claude/bin/qualia-ui.js info "Quality:  {score}/5 ({n} findings)"
+node ~/.claude/bin/qualia-ui.js info "Perf:     {score}/5 ({n} findings)"
+node ~/.claude/bin/qualia-ui.js end "REVIEW: {PASS|FAIL}" "{next command}"
+```
+
+## Rules
+
+1. **Run every command.** Don't skip scans because "the code looks clean."
+2. **Every finding gets a severity.** No prose — CRITICAL/HIGH/MEDIUM/LOW.
+3. **Every finding gets a fix suggestion.** Not just "this is bad" — say what to do.
+4. **Review detects. It does NOT fix.** This is an audit, not a refactor. Tell the user what to fix.
+5. **CRITICAL or HIGH = deploy blocker.** `/qualia-ship` checks for these.