How to Build a Habit Tracker

<context>
App: Habit Tracker
Difficulty: Beginner
Estimated build time: 2–4 days

Data model:
  User: id, email, timezone, notification_time
  Habit: id, user_id, name, icon, color, frequency (daily/weekdays/custom), target_per_day, created_at
  HabitLog: id, habit_id, date (YYYY-MM-DD), value (1 for bool, n for quantity), created_at

Recommended build order:
  1. Habit list and daily check-in — Show a list of habits for today. Each has a checkbox. On check, write a HabitLog for today's date. If unchecked, delete today's log. Keep it simple — no streaks yet.
  2. Streak calculation — Write a function that takes an array of log dates and returns the current streak. Walk backwards from today: if yesterday has a log, increment streak. Stop at the first missing day.
  3. Streak recovery (grace period) — Add a grace_period field to habits (default: 1 day). If the user missed one day but the habit has a grace period, don't break the streak — show a "recover streak" button that logs yesterday.
  4. Progress charts — Build a 7-day heatmap row showing which days had a check-in. Add a monthly calendar view where completed days are highlighted. Use a simple CSS grid — no chart library needed for this.
  5. Habit templates — Seed 8–10 common habits (drink water, read, exercise, meditate) with icons and suggested targets. Show these as one-click templates on the add-habit screen.
  6. Daily reminder notifications — On web, use the Web Notifications API + a service worker to schedule a daily notification. On mobile (Expo), use expo-notifications with a daily trigger at the user's preferred time.
  7. AI weekly summary — Every Monday, generate a summary: fetch last week's logs, calculate hit rate per habit, send to Claude Haiku, get back a 2-sentence coaching comment per habit. Email or show in-app.

Known pitfalls to avoid:
  - Calculating streaks in local time without knowing the user's timezone — a check-in at 11pm in New York is the next day in UTC. Always store dates as YYYY-MM-DD strings in the user's timezone, not as UTC timestamps.
  - Breaking streaks on the first missed day — this is the #1 reason users abandon habit apps. Add a 1-day grace period and a "I forgot yesterday" recovery option before you punish missed days.
  - Storing one HabitLog per check action instead of one per day — if the user checks and unchecks, you'll have multiple logs per day. Use upsert on (habit_id, date) as a unique key.

Tech stack (intermediate): Next.js + Supabase + Clerk + React Native Web for cross-platform
</context>

<role>
You are a Senior Full-Stack Engineer and product architect who has shipped production Habit Trackers before. You know exactly where developers get stuck and how to structure the project to avoid rewrites.
</role>

<task id="step-1-clarify">
Before writing any code or spec, ask me 3–5 clarifying questions that will meaningfully change the architecture. Focus on: scale expectations, auth requirements, platform (web / mobile / both), must-have vs nice-to-have features for the MVP, and any hard constraints (budget, deadline, existing infrastructure).

<example>
BAD: "What tech stack do you want to use?" — too broad, doesn't change architecture decisions.
GOOD: "Do you need real-time sync across devices, or is single-device with periodic refresh acceptable? This decides whether we use WebSockets or simple REST polling and significantly affects infrastructure complexity."
</example>
</task>

<task id="step-2-architect">
After I answer your questions, generate a complete project specification including:

1. Final tech stack with version numbers
2. Full file and folder structure
3. Complete database schema — every table, column, type, index, and foreign key
4. All API routes with request/response shapes and auth requirements
5. Component tree with TypeScript props interfaces
6. Auth and authorisation flow (who can do what)
7. Step-by-step implementation plan in the exact build order from <context> above
8. All environment variables with descriptions

<self_check>
Before presenting the spec, verify:
□ Every answer I gave in step 1 is reflected in the spec
□ The database schema matches the data model in <context>
□ The implementation plan follows the build order from <context>
□ No circular dependencies in the component tree
□ Auth is wired up before any protected routes are built
□ All known pitfalls from <context> are addressed in the spec
</self_check>
</task>

<task id="step-2.5-agents-md">
Generate an AGENTS.md file at the project root. This file is read automatically by Claude Code, Cursor, Windsurf, Sourcegraph Cody, and all major AI coding tools at the start of every session.

Include:
- Project overview (2–3 sentences)
- Tech stack with version numbers
- Folder structure with one-line descriptions
- Key architectural decisions and why they were made
- Coding conventions: naming (camelCase components, kebab-case files), max 200 lines per file, one concern per file
- Available commands: dev, build, test, lint, db:migrate, db:seed

Note in the file: "Cursor users can symlink .cursorrules → AGENTS.md. Claude Code users can symlink CLAUDE.md → AGENTS.md."
</task>

<task id="step-3-implement">
Implement the full project following the spec from step 2, in the exact order defined. For each step:
- Write the complete code (no placeholders or TODOs)
- Confirm the step is working before moving to the next
- Note any deviations from the spec with an explanation

<constraints>
- Max 200 lines per file. WHY: every file must fit in one AI context window for easy review and editing.
- One concern per file. WHY: mixing auth logic into API routes makes it impossible to reuse — extract to lib/auth.ts.
- TypeScript strict mode, no `any` types. WHY: catches data shape mismatches at compile time, not in production at 2am.
- All database queries in server components or API routes only. WHY: keeps credentials server-side, prevents accidental client-side exposure.
- All environment variables documented in .env.example. WHY: the next developer (or your future self) should be able to set up the project in under 5 minutes.
- Comment every non-obvious decision. WHY: AI tools read your comments to understand intent — without them, the next edit will break the pattern you established.
</constraints>
</task>