Vibecode Wholana

You are building a lean indie version of Wholana.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# Wholana indie build

## Goal

Build the smallest trustworthy replacement for the core Wholana workflow for one developer or a tiny team.

## Scope

Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- the cross-creator corpus
- search across videos you never chose to watch
- a curated craft taxonomy instead of labels you invented
- semantic and hybrid search
- subject classification
- creator equity and track-record views
- someone else absorbing the scrape cost and keeping it running

If those capabilities are essential, use TikTokApi instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build me a personal TikTok outlier tracker to replace Wholana. Requirements:

- A nightly Node script (node-cron) that pulls recent videos for up to 25 handles listed in
  handles.txt, using a TikTok scraper actor on Apify, token in .env. Do not scrape TikTok
  directly, you will be blocked inside a day.
- Store videos in SQLite via better-sqlite3: handle, video id, url, caption, posted date,
  views, likes, comments, shares, date first seen. Upsert on video id so a re-scrape
  updates metrics instead of duplicating rows.
- Per creator, keep a rolling median of views over their last 30 videos and score each
  video as views divided by that median. 3x or higher is a breakout. Skip creators under
  10 videos, the median is noise below that.
- Label each breakout with one LLM call (Anthropic or OpenAI, key in .env): caption plus
  the first 15 seconds of subtitles from yt-dlp, returning one hook type from a fixed list
  of 12 in hooks.json. Fixed list, not free text, or nothing groups.
- A page on localhost:3000 (Express, server-rendered HTML, Chart.js): last 7 days of
  breakouts sorted by score, filterable by handle, each row showing score, views, hook
  type, and a link, plus a per-creator sparkline of views over time.
- A save button per row that writes the video into a swipe collection and appends it to
  swipe.md, so my picks survive the database.
- Localhost only. No accounts, no telemetry, everything on my machine except the Apify and
  LLM calls.
- Out of scope: search across creators I am not already tracking, and a shared craft
  taxonomy. Do not build auth, multi-user workspaces, or hosting config.
- README: Apify token and actor id, the cron entry, and the cost per 1,000 videos scraped.
  The scraper bill, not the code, is what makes people quit this build.

## Required capabilities

- TikTok scraper API (Apify or similar, paid per run)
- LLM API key for hook labeling
- SQLite
- a nightly cron job
- a scrape budget that recurs every month

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a lean indie version of Wholana.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# Wholana indie build

## Goal

Build the smallest trustworthy replacement for the core Wholana workflow for one developer or a tiny team.

## Scope

Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- the cross-creator corpus
- search across videos you never chose to watch
- a curated craft taxonomy instead of labels you invented
- semantic and hybrid search
- subject classification
- creator equity and track-record views
- someone else absorbing the scrape cost and keeping it running

If those capabilities are essential, use TikTokApi instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build me a personal TikTok outlier tracker to replace Wholana. Requirements:

- A nightly Node script (node-cron) that pulls recent videos for up to 25 handles listed in
  handles.txt, using a TikTok scraper actor on Apify, token in .env. Do not scrape TikTok
  directly, you will be blocked inside a day.
- Store videos in SQLite via better-sqlite3: handle, video id, url, caption, posted date,
  views, likes, comments, shares, date first seen. Upsert on video id so a re-scrape
  updates metrics instead of duplicating rows.
- Per creator, keep a rolling median of views over their last 30 videos and score each
  video as views divided by that median. 3x or higher is a breakout. Skip creators under
  10 videos, the median is noise below that.
- Label each breakout with one LLM call (Anthropic or OpenAI, key in .env): caption plus
  the first 15 seconds of subtitles from yt-dlp, returning one hook type from a fixed list
  of 12 in hooks.json. Fixed list, not free text, or nothing groups.
- A page on localhost:3000 (Express, server-rendered HTML, Chart.js): last 7 days of
  breakouts sorted by score, filterable by handle, each row showing score, views, hook
  type, and a link, plus a per-creator sparkline of views over time.
- A save button per row that writes the video into a swipe collection and appends it to
  swipe.md, so my picks survive the database.
- Localhost only. No accounts, no telemetry, everything on my machine except the Apify and
  LLM calls.
- Out of scope: search across creators I am not already tracking, and a shared craft
  taxonomy. Do not build auth, multi-user workspaces, or hosting config.
- README: Apify token and actor id, the cron entry, and the cost per 1,000 videos scraped.
  The scraper bill, not the code, is what makes people quit this build.

## Required capabilities

- TikTok scraper API (Apify or similar, paid per run)
- LLM API key for hook labeling
- SQLite
- a nightly cron job
- a scrape budget that recurs every month

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a production product version of Wholana.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== PRODUCT.md =====
# Wholana product brief

## Problem

The core idea is simple arithmetic: a video's views divided by that creator's own median. An agent can build that for a watchlist of creators you pick, over a weekend, on top of a paid scraper API. What it cannot hand you is the corpus, hundreds of thousands of videos already scraped, deduped, and labeled against a curated craft taxonomy, which is what makes search across creators useful instead of a list of your own bookmarks. So: yes for watching 25 creators you already know, no for finding the ones you don't.

## Product outcome

Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- TikTok scraper API (Apify or similar, paid per run)
- LLM API key for hook labeling
- SQLite
- a nightly cron job
- a scrape budget that recurs every month

## Explicit non-goals for v1

- the cross-creator corpus
- search across videos you never chose to watch
- a curated craft taxonomy instead of labels you invented
- semantic and hybrid search
- subject classification
- creator equity and track-record views
- someone else absorbing the scrape cost and keeping it running

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

===== ARCHITECTURE.md =====
# Architecture

## Starting brief

Build me a personal TikTok outlier tracker to replace Wholana. Requirements:

- A nightly Node script (node-cron) that pulls recent videos for up to 25 handles listed in
  handles.txt, using a TikTok scraper actor on Apify, token in .env. Do not scrape TikTok
  directly, you will be blocked inside a day.
- Store videos in SQLite via better-sqlite3: handle, video id, url, caption, posted date,
  views, likes, comments, shares, date first seen. Upsert on video id so a re-scrape
  updates metrics instead of duplicating rows.
- Per creator, keep a rolling median of views over their last 30 videos and score each
  video as views divided by that median. 3x or higher is a breakout. Skip creators under
  10 videos, the median is noise below that.
- Label each breakout with one LLM call (Anthropic or OpenAI, key in .env): caption plus
  the first 15 seconds of subtitles from yt-dlp, returning one hook type from a fixed list
  of 12 in hooks.json. Fixed list, not free text, or nothing groups.
- A page on localhost:3000 (Express, server-rendered HTML, Chart.js): last 7 days of
  breakouts sorted by score, filterable by handle, each row showing score, views, hook
  type, and a link, plus a per-creator sparkline of views over time.
- A save button per row that writes the video into a swipe collection and appends it to
  swipe.md, so my picks survive the database.
- Localhost only. No accounts, no telemetry, everything on my machine except the Apify and
  LLM calls.
- Out of scope: search across creators I am not already tracking, and a shared craft
  taxonomy. Do not build auth, multi-user workspaces, or hosting config.
- README: Apify token and actor id, the cron entry, and the cost per 1,000 videos scraped.
  The scraper bill, not the code, is what makes people quit this build.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

===== AGENTS.md =====
# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

===== MILESTONES.md =====
# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

===== OPERATIONS.md =====
# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted Wholana capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# Wholana indie build

## Goal

Build the smallest trustworthy replacement for the core Wholana workflow for one developer or a tiny team.

## Scope

Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- the cross-creator corpus
- search across videos you never chose to watch
- a curated craft taxonomy instead of labels you invented
- semantic and hybrid search
- subject classification
- creator equity and track-record views
- someone else absorbing the scrape cost and keeping it running

If those capabilities are essential, use TikTokApi instead of pretending the gap is solved.

# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

# Build plan

## Original build brief

Build me a personal TikTok outlier tracker to replace Wholana. Requirements:

- A nightly Node script (node-cron) that pulls recent videos for up to 25 handles listed in
  handles.txt, using a TikTok scraper actor on Apify, token in .env. Do not scrape TikTok
  directly, you will be blocked inside a day.
- Store videos in SQLite via better-sqlite3: handle, video id, url, caption, posted date,
  views, likes, comments, shares, date first seen. Upsert on video id so a re-scrape
  updates metrics instead of duplicating rows.
- Per creator, keep a rolling median of views over their last 30 videos and score each
  video as views divided by that median. 3x or higher is a breakout. Skip creators under
  10 videos, the median is noise below that.
- Label each breakout with one LLM call (Anthropic or OpenAI, key in .env): caption plus
  the first 15 seconds of subtitles from yt-dlp, returning one hook type from a fixed list
  of 12 in hooks.json. Fixed list, not free text, or nothing groups.
- A page on localhost:3000 (Express, server-rendered HTML, Chart.js): last 7 days of
  breakouts sorted by score, filterable by handle, each row showing score, views, hook
  type, and a link, plus a per-creator sparkline of views over time.
- A save button per row that writes the video into a swipe collection and appends it to
  swipe.md, so my picks survive the database.
- Localhost only. No accounts, no telemetry, everything on my machine except the Apify and
  LLM calls.
- Out of scope: search across creators I am not already tracking, and a shared craft
  taxonomy. Do not build auth, multi-user workspaces, or hosting config.
- README: Apify token and actor id, the cron entry, and the cost per 1,000 videos scraped.
  The scraper bill, not the code, is what makes people quit this build.

## Required capabilities

- TikTok scraper API (Apify or similar, paid per run)
- LLM API key for hook labeling
- SQLite
- a nightly cron job
- a scrape budget that recurs every month

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

# Wholana product brief

## Problem

The core idea is simple arithmetic: a video's views divided by that creator's own median. An agent can build that for a watchlist of creators you pick, over a weekend, on top of a paid scraper API. What it cannot hand you is the corpus, hundreds of thousands of videos already scraped, deduped, and labeled against a curated craft taxonomy, which is what makes search across creators useful instead of a list of your own bookmarks. So: yes for watching 25 creators you already know, no for finding the ones you don't.

## Product outcome

Scrape a watchlist of creators nightly, compute each creator's rolling median views, and surface the videos that beat their own baseline.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- TikTok scraper API (Apify or similar, paid per run)
- LLM API key for hook labeling
- SQLite
- a nightly cron job
- a scrape budget that recurs every month

## Explicit non-goals for v1

- the cross-creator corpus
- search across videos you never chose to watch
- a curated craft taxonomy instead of labels you invented
- semantic and hybrid search
- subject classification
- creator equity and track-record views
- someone else absorbing the scrape cost and keeping it running

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

# Architecture

## Starting brief

Build me a personal TikTok outlier tracker to replace Wholana. Requirements:

- A nightly Node script (node-cron) that pulls recent videos for up to 25 handles listed in
  handles.txt, using a TikTok scraper actor on Apify, token in .env. Do not scrape TikTok
  directly, you will be blocked inside a day.
- Store videos in SQLite via better-sqlite3: handle, video id, url, caption, posted date,
  views, likes, comments, shares, date first seen. Upsert on video id so a re-scrape
  updates metrics instead of duplicating rows.
- Per creator, keep a rolling median of views over their last 30 videos and score each
  video as views divided by that median. 3x or higher is a breakout. Skip creators under
  10 videos, the median is noise below that.
- Label each breakout with one LLM call (Anthropic or OpenAI, key in .env): caption plus
  the first 15 seconds of subtitles from yt-dlp, returning one hook type from a fixed list
  of 12 in hooks.json. Fixed list, not free text, or nothing groups.
- A page on localhost:3000 (Express, server-rendered HTML, Chart.js): last 7 days of
  breakouts sorted by score, filterable by handle, each row showing score, views, hook
  type, and a link, plus a per-creator sparkline of views over time.
- A save button per row that writes the video into a swipe collection and appends it to
  swipe.md, so my picks survive the database.
- Localhost only. No accounts, no telemetry, everything on my machine except the Apify and
  LLM calls.
- Out of scope: search across creators I am not already tracking, and a shared craft
  taxonomy. Do not build auth, multi-user workspaces, or hosting config.
- README: Apify token and actor id, the cron entry, and the cost per 1,000 videos scraped.
  The scraper bill, not the code, is what makes people quit this build.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted Wholana capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

$ choose a build depth, inspect the files, then open the complete pack in your agent