Vibecode Mymind

You are building a lean indie version of Mymind.

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 =====
# Mymind indie build

## Goal

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

## Scope

Captures URLs, images, highlights and notes into a local SQLite library, auto-extracts text and metadata, asks a model for tags and a one-line summary, then serves a visual masonry grid with semantic plus keyword search.

## 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:
- Real browser extensions and a mobile share sheet, so capture friction goes way up
- Image understanding that recognizes objects, art, color palettes and text in photos at Mymind's quality
- Sync across devices, plus offline capable native apps
- Serendipity features: the everything-search, the surfacing of old cards, spaced resurfacing
- Someone else's ongoing judgment about what a good tag actually is

If those capabilities are essential, use Mymind 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 a local-first personal "everything bucket" web app called Mind. Single user, no accounts, no telemetry, no cloud.

Stack, no substitutions:
- Node 20, TypeScript, Next.js App Router, Tailwind.
- SQLite via better-sqlite3, with sqlite-vec for vector search. One file at ./data/mind.db.
- Playwright (Chromium) for page fetch, readable text extraction and a 1200px-wide screenshot.
- One LLM provider read from .env: MODEL_API_KEY, MODEL_BASE_URL, MODEL_NAME, EMBED_MODEL. Never hardcode keys.

Data model: cards table with id, kind (link | image | note | highlight), url, title, author, siteName, textContent, aiSummary, colorHex, createdAt, favicon path, imagePath, thumbPath. Separate tags table and card_tags join. Separate embeddings virtual table keyed by card id.

Capture:
- POST /api/capture accepts { url } or { text } or a multipart image upload.
- For a URL: fetch with Playwright, extract main text, title, site name, favicon, save screenshot and a thumbnail.
- For an image: store the original, generate a thumbnail, run OCR with tesseract.js if available, and skip silently if it is not.
- After extraction, one model call returns 3 to 6 lowercase tags plus a single sentence summary as strict JSON. Then one embedding call over title + summary + first 2000 chars of text.
- Extract a dominant color from the image or screenshot and store it as colorHex for the card background.

UI:
- Home is a masonry grid of cards, newest first, image-forward, no folders and no manual filing anywhere in the app.
- One search input at the top that does hybrid search: SQLite FTS5 over title/text/tags plus vector similarity, merged and deduped.
- Clicking a card opens a detail sheet with the original link, full text, tags (editable) and a delete button.
- Keyboard: "/" focuses search, "n" opens a quick note composer, Escape closes.

Also ship:
- A bookmarklet and a minimal Chrome MV3 extension in ./extension that POSTs the current tab URL and any selected text to http://localhost:3000/api/capture.
- A CLI: pnpm mind add URL_OR_TEXT.
- A tiny import script that reads a Pocket or browser bookmarks HTML export and queues each URL.

Out of scope, do not build: multi-user auth, sharing, mobile apps, hosted deployment, sync between machines, payments.

Write a README with setup, .env.example, a seed script that captures five sample URLs, and make pnpm dev work on a clean clone.

## Required capabilities

- Node 20 and pnpm, runs locally
- An LLM API key for tagging and embeddings, in .env
- Playwright with Chromium for page snapshots and screenshots
- Local disk for original images and thumbnails
- Optional: Tesseract for OCR on screenshots
- A browser extension loaded unpacked in dev mode

## 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 Mymind.

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 =====
# Mymind indie build

## Goal

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

## Scope

Captures URLs, images, highlights and notes into a local SQLite library, auto-extracts text and metadata, asks a model for tags and a one-line summary, then serves a visual masonry grid with semantic plus keyword search.

## 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:
- Real browser extensions and a mobile share sheet, so capture friction goes way up
- Image understanding that recognizes objects, art, color palettes and text in photos at Mymind's quality
- Sync across devices, plus offline capable native apps
- Serendipity features: the everything-search, the surfacing of old cards, spaced resurfacing
- Someone else's ongoing judgment about what a good tag actually is

If those capabilities are essential, use Mymind 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 a local-first personal "everything bucket" web app called Mind. Single user, no accounts, no telemetry, no cloud.

Stack, no substitutions:
- Node 20, TypeScript, Next.js App Router, Tailwind.
- SQLite via better-sqlite3, with sqlite-vec for vector search. One file at ./data/mind.db.
- Playwright (Chromium) for page fetch, readable text extraction and a 1200px-wide screenshot.
- One LLM provider read from .env: MODEL_API_KEY, MODEL_BASE_URL, MODEL_NAME, EMBED_MODEL. Never hardcode keys.

Data model: cards table with id, kind (link | image | note | highlight), url, title, author, siteName, textContent, aiSummary, colorHex, createdAt, favicon path, imagePath, thumbPath. Separate tags table and card_tags join. Separate embeddings virtual table keyed by card id.

Capture:
- POST /api/capture accepts { url } or { text } or a multipart image upload.
- For a URL: fetch with Playwright, extract main text, title, site name, favicon, save screenshot and a thumbnail.
- For an image: store the original, generate a thumbnail, run OCR with tesseract.js if available, and skip silently if it is not.
- After extraction, one model call returns 3 to 6 lowercase tags plus a single sentence summary as strict JSON. Then one embedding call over title + summary + first 2000 chars of text.
- Extract a dominant color from the image or screenshot and store it as colorHex for the card background.

UI:
- Home is a masonry grid of cards, newest first, image-forward, no folders and no manual filing anywhere in the app.
- One search input at the top that does hybrid search: SQLite FTS5 over title/text/tags plus vector similarity, merged and deduped.
- Clicking a card opens a detail sheet with the original link, full text, tags (editable) and a delete button.
- Keyboard: "/" focuses search, "n" opens a quick note composer, Escape closes.

Also ship:
- A bookmarklet and a minimal Chrome MV3 extension in ./extension that POSTs the current tab URL and any selected text to http://localhost:3000/api/capture.
- A CLI: pnpm mind add URL_OR_TEXT.
- A tiny import script that reads a Pocket or browser bookmarks HTML export and queues each URL.

Out of scope, do not build: multi-user auth, sharing, mobile apps, hosted deployment, sync between machines, payments.

Write a README with setup, .env.example, a seed script that captures five sample URLs, and make pnpm dev work on a clean clone.

## Required capabilities

- Node 20 and pnpm, runs locally
- An LLM API key for tagging and embeddings, in .env
- Playwright with Chromium for page snapshots and screenshots
- Local disk for original images and thumbnails
- Optional: Tesseract for OCR on screenshots
- A browser extension loaded unpacked in dev mode

## 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 Mymind.

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 =====
# Mymind product brief

## Problem

The mechanic is honestly simple: capture a thing, extract text and metadata, ask a model for tags, embed it, then search across everything. An agent can build that in a weekend with SQLite, a headless browser for page snapshots and one model API call per item. What you cannot one-shot is the capture surface, which is the entire product in practice: browser extensions for three browsers, an iOS and Android share sheet, and the reliability that makes you trust it with the thought you had in a queue. The taste also matters more than it should here, because the pitch is that you never organize anything, and a DIY version that mis-tags half your library quietly becomes a junk drawer. Fine build, real gaps.

## Product outcome

Captures URLs, images, highlights and notes into a local SQLite library, auto-extracts text and metadata, asks a model for tags and a one-line summary, then serves a visual masonry grid with semantic plus keyword search.

## Target user

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

## Required capabilities

- Node 20 and pnpm, runs locally
- An LLM API key for tagging and embeddings, in .env
- Playwright with Chromium for page snapshots and screenshots
- Local disk for original images and thumbnails
- Optional: Tesseract for OCR on screenshots
- A browser extension loaded unpacked in dev mode

## Explicit non-goals for v1

- Real browser extensions and a mobile share sheet, so capture friction goes way up
- Image understanding that recognizes objects, art, color palettes and text in photos at Mymind's quality
- Sync across devices, plus offline capable native apps
- Serendipity features: the everything-search, the surfacing of old cards, spaced resurfacing
- Someone else's ongoing judgment about what a good tag actually is

## 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 a local-first personal "everything bucket" web app called Mind. Single user, no accounts, no telemetry, no cloud.

Stack, no substitutions:
- Node 20, TypeScript, Next.js App Router, Tailwind.
- SQLite via better-sqlite3, with sqlite-vec for vector search. One file at ./data/mind.db.
- Playwright (Chromium) for page fetch, readable text extraction and a 1200px-wide screenshot.
- One LLM provider read from .env: MODEL_API_KEY, MODEL_BASE_URL, MODEL_NAME, EMBED_MODEL. Never hardcode keys.

Data model: cards table with id, kind (link | image | note | highlight), url, title, author, siteName, textContent, aiSummary, colorHex, createdAt, favicon path, imagePath, thumbPath. Separate tags table and card_tags join. Separate embeddings virtual table keyed by card id.

Capture:
- POST /api/capture accepts { url } or { text } or a multipart image upload.
- For a URL: fetch with Playwright, extract main text, title, site name, favicon, save screenshot and a thumbnail.
- For an image: store the original, generate a thumbnail, run OCR with tesseract.js if available, and skip silently if it is not.
- After extraction, one model call returns 3 to 6 lowercase tags plus a single sentence summary as strict JSON. Then one embedding call over title + summary + first 2000 chars of text.
- Extract a dominant color from the image or screenshot and store it as colorHex for the card background.

UI:
- Home is a masonry grid of cards, newest first, image-forward, no folders and no manual filing anywhere in the app.
- One search input at the top that does hybrid search: SQLite FTS5 over title/text/tags plus vector similarity, merged and deduped.
- Clicking a card opens a detail sheet with the original link, full text, tags (editable) and a delete button.
- Keyboard: "/" focuses search, "n" opens a quick note composer, Escape closes.

Also ship:
- A bookmarklet and a minimal Chrome MV3 extension in ./extension that POSTs the current tab URL and any selected text to http://localhost:3000/api/capture.
- A CLI: pnpm mind add URL_OR_TEXT.
- A tiny import script that reads a Pocket or browser bookmarks HTML export and queues each URL.

Out of scope, do not build: multi-user auth, sharing, mobile apps, hosted deployment, sync between machines, payments.

Write a README with setup, .env.example, a seed script that captures five sample URLs, and make pnpm dev work on a clean clone.

## 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 Mymind capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# Mymind indie build

## Goal

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

## Scope

Captures URLs, images, highlights and notes into a local SQLite library, auto-extracts text and metadata, asks a model for tags and a one-line summary, then serves a visual masonry grid with semantic plus keyword search.

## 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:
- Real browser extensions and a mobile share sheet, so capture friction goes way up
- Image understanding that recognizes objects, art, color palettes and text in photos at Mymind's quality
- Sync across devices, plus offline capable native apps
- Serendipity features: the everything-search, the surfacing of old cards, spaced resurfacing
- Someone else's ongoing judgment about what a good tag actually is

If those capabilities are essential, use Mymind 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 a local-first personal "everything bucket" web app called Mind. Single user, no accounts, no telemetry, no cloud.

Stack, no substitutions:
- Node 20, TypeScript, Next.js App Router, Tailwind.
- SQLite via better-sqlite3, with sqlite-vec for vector search. One file at ./data/mind.db.
- Playwright (Chromium) for page fetch, readable text extraction and a 1200px-wide screenshot.
- One LLM provider read from .env: MODEL_API_KEY, MODEL_BASE_URL, MODEL_NAME, EMBED_MODEL. Never hardcode keys.

Data model: cards table with id, kind (link | image | note | highlight), url, title, author, siteName, textContent, aiSummary, colorHex, createdAt, favicon path, imagePath, thumbPath. Separate tags table and card_tags join. Separate embeddings virtual table keyed by card id.

Capture:
- POST /api/capture accepts { url } or { text } or a multipart image upload.
- For a URL: fetch with Playwright, extract main text, title, site name, favicon, save screenshot and a thumbnail.
- For an image: store the original, generate a thumbnail, run OCR with tesseract.js if available, and skip silently if it is not.
- After extraction, one model call returns 3 to 6 lowercase tags plus a single sentence summary as strict JSON. Then one embedding call over title + summary + first 2000 chars of text.
- Extract a dominant color from the image or screenshot and store it as colorHex for the card background.

UI:
- Home is a masonry grid of cards, newest first, image-forward, no folders and no manual filing anywhere in the app.
- One search input at the top that does hybrid search: SQLite FTS5 over title/text/tags plus vector similarity, merged and deduped.
- Clicking a card opens a detail sheet with the original link, full text, tags (editable) and a delete button.
- Keyboard: "/" focuses search, "n" opens a quick note composer, Escape closes.

Also ship:
- A bookmarklet and a minimal Chrome MV3 extension in ./extension that POSTs the current tab URL and any selected text to http://localhost:3000/api/capture.
- A CLI: pnpm mind add URL_OR_TEXT.
- A tiny import script that reads a Pocket or browser bookmarks HTML export and queues each URL.

Out of scope, do not build: multi-user auth, sharing, mobile apps, hosted deployment, sync between machines, payments.

Write a README with setup, .env.example, a seed script that captures five sample URLs, and make pnpm dev work on a clean clone.

## Required capabilities

- Node 20 and pnpm, runs locally
- An LLM API key for tagging and embeddings, in .env
- Playwright with Chromium for page snapshots and screenshots
- Local disk for original images and thumbnails
- Optional: Tesseract for OCR on screenshots
- A browser extension loaded unpacked in dev mode

## 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.

# Mymind product brief

## Problem

The mechanic is honestly simple: capture a thing, extract text and metadata, ask a model for tags, embed it, then search across everything. An agent can build that in a weekend with SQLite, a headless browser for page snapshots and one model API call per item. What you cannot one-shot is the capture surface, which is the entire product in practice: browser extensions for three browsers, an iOS and Android share sheet, and the reliability that makes you trust it with the thought you had in a queue. The taste also matters more than it should here, because the pitch is that you never organize anything, and a DIY version that mis-tags half your library quietly becomes a junk drawer. Fine build, real gaps.

## Product outcome

Captures URLs, images, highlights and notes into a local SQLite library, auto-extracts text and metadata, asks a model for tags and a one-line summary, then serves a visual masonry grid with semantic plus keyword search.

## Target user

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

## Required capabilities

- Node 20 and pnpm, runs locally
- An LLM API key for tagging and embeddings, in .env
- Playwright with Chromium for page snapshots and screenshots
- Local disk for original images and thumbnails
- Optional: Tesseract for OCR on screenshots
- A browser extension loaded unpacked in dev mode

## Explicit non-goals for v1

- Real browser extensions and a mobile share sheet, so capture friction goes way up
- Image understanding that recognizes objects, art, color palettes and text in photos at Mymind's quality
- Sync across devices, plus offline capable native apps
- Serendipity features: the everything-search, the surfacing of old cards, spaced resurfacing
- Someone else's ongoing judgment about what a good tag actually is

## 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 a local-first personal "everything bucket" web app called Mind. Single user, no accounts, no telemetry, no cloud.

Stack, no substitutions:
- Node 20, TypeScript, Next.js App Router, Tailwind.
- SQLite via better-sqlite3, with sqlite-vec for vector search. One file at ./data/mind.db.
- Playwright (Chromium) for page fetch, readable text extraction and a 1200px-wide screenshot.
- One LLM provider read from .env: MODEL_API_KEY, MODEL_BASE_URL, MODEL_NAME, EMBED_MODEL. Never hardcode keys.

Data model: cards table with id, kind (link | image | note | highlight), url, title, author, siteName, textContent, aiSummary, colorHex, createdAt, favicon path, imagePath, thumbPath. Separate tags table and card_tags join. Separate embeddings virtual table keyed by card id.

Capture:
- POST /api/capture accepts { url } or { text } or a multipart image upload.
- For a URL: fetch with Playwright, extract main text, title, site name, favicon, save screenshot and a thumbnail.
- For an image: store the original, generate a thumbnail, run OCR with tesseract.js if available, and skip silently if it is not.
- After extraction, one model call returns 3 to 6 lowercase tags plus a single sentence summary as strict JSON. Then one embedding call over title + summary + first 2000 chars of text.
- Extract a dominant color from the image or screenshot and store it as colorHex for the card background.

UI:
- Home is a masonry grid of cards, newest first, image-forward, no folders and no manual filing anywhere in the app.
- One search input at the top that does hybrid search: SQLite FTS5 over title/text/tags plus vector similarity, merged and deduped.
- Clicking a card opens a detail sheet with the original link, full text, tags (editable) and a delete button.
- Keyboard: "/" focuses search, "n" opens a quick note composer, Escape closes.

Also ship:
- A bookmarklet and a minimal Chrome MV3 extension in ./extension that POSTs the current tab URL and any selected text to http://localhost:3000/api/capture.
- A CLI: pnpm mind add URL_OR_TEXT.
- A tiny import script that reads a Pocket or browser bookmarks HTML export and queues each URL.

Out of scope, do not build: multi-user auth, sharing, mobile apps, hosted deployment, sync between machines, payments.

Write a README with setup, .env.example, a seed script that captures five sample URLs, and make pnpm dev work on a clean clone.

## 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 Mymind 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 · this prompt is generated from the build plan · improve it via PR