How to Build a Pomodoro Timer

<context>
App: Pomodoro Timer
Difficulty: Beginner
Estimated build time: 1 day

Data model:
  Session: id, user_id, task_label, duration_minutes, type (work/short_break/long_break), completed (bool), started_at, ended_at
  Settings: user_id, work_duration (default 25), short_break (default 5), long_break (default 15), sessions_before_long_break (default 4), sound_enabled, notification_enabled

Recommended build order:
  1. Countdown timer core — Store the end time as a timestamp (Date.now() + duration × 60000) when the timer starts. On each tick (useInterval at 1s), calculate remaining = endTime - Date.now(). This works correctly even if the tab is backgrounded.
  2. Work / break cycle — Track session count in state. After each work session, auto-start a short break. After every 4 work sessions, auto-start a long break. Show which phase you're in (Work / Short Break / Long Break).
  3. Sound and notifications — Play a short audio file (new Audio(url).play()) when the timer ends. Request notification permission on first use. Show a browser notification on session end with the Notifications API.
  4. Task label — Add an input above the timer: "What are you working on?" Store the label with each completed session so the history is meaningful.
  5. Session history — Save each completed session to localStorage (or Supabase). Show a history list: task, duration, when. Calculate today's total focus time and display it as a KPI.
  6. Settings panel — Add a settings drawer to customise work/break durations and the number of sessions before a long break. Persist to localStorage. Apply immediately to the next session.
  7. AI weekly focus report — On Monday, aggregate last week's sessions: total focus hours, most productive day, most common task labels. Send to Claude Haiku and get back a 3-sentence coaching comment.

Known pitfalls to avoid:
  - Using setInterval for the countdown — intervals drift and pause in background tabs. Store the target end timestamp and compute remaining time as endTime - Date.now() on each render.
  - Auto-starting breaks without user confirmation — some users want to take control between sessions. Add a setting for "auto-start breaks" and default it to off.
  - Not preserving timer state on refresh — if the user refreshes the page, their 20-minute work session is gone. Store startTime and duration in sessionStorage so it survives a refresh.

Tech stack (intermediate): Next.js + Supabase for session history + Clerk for cross-device sync
</context>

<role>
You are a Senior Full-Stack Engineer and product architect who has shipped production Pomodoro Timers 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>