Vibecode Mara

You are building a lean indie version of Mara.

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 =====
# Mara indie build

## Goal

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

## Scope

Take product events, draft the next lifecycle email with an LLM in your voice, hold it for approval, and send it on a schedule.

## 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:
- deliverability: warmup, domain reputation, bounce and complaint handling
- the improvement loop: variants written, split across live sends, losers rewritten
- reply handling: inbound classified, answers drafted, suppressions applied
- outcome tracking wired back to the copy that caused it
- the maintenance nobody does, which is the actual reason lifecycle programs rot

If those capabilities are essential, use Mautic 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 self-hosted lifecycle email agent to replace Mara, for one SaaS product. Requirements:

- Node + Express + better-sqlite3 on my VPS, one SQLite file holding contacts,
  events, sequences, drafts, sends, and suppressions. node-cron ticks once a minute,
  no queue service.
- POST /events takes {type, email, properties} with a bearer token from .env. Every
  event upserts a contact and appends a row I can read back later.
- Sequences are JSON files in ./sequences/: an entry event type, then steps with a
  wait ("2d"), an intent in plain words ("nudge them to connect their first
  integration"), and an optional skip-if event type. Ship two: welcome and
  trial-ending.
- Each tick, find contacts due for a step, drop anyone whose skip-if event already
  fired, then draft with the Anthropic API (key in .env): pass ./voice.md plus that
  contact's last 20 events, get back a subject and a plain-text body.
- Drafts land as pending. A localhost-only admin page lists them with subject, body,
  recipient, and the step that produced it, with Approve and Reject buttons. Nothing
  sends without a click.
- Approved mail goes out through Resend or SMTP from .env, one send row per recipient
  with the provider message id. Bounce and complaint webhooks write to a suppression
  table checked before every send. One-click unsubscribe link in every footer, no
  login.
- Cap at 2 emails per contact per 7 days across all sequences, enforced in code
  before drafting.
- Out of scope: A/B variants, reply parsing, open tracking. Do not build multi-user
  accounts or a visual sequence builder, this runs for one product and one operator.
- README with the deliverability homework: SPF, DKIM, and DMARC on a subdomain like
  mail.example.com, a two-week warmup at low volume, and a blunt line that mail from
  a cold domain lands in spam no matter how good the copy is.

## Required capabilities

- Anthropic or OpenAI API key
- email sending API (Resend, Postmark, or SES)
- your own sending subdomain with SPF/DKIM/DMARC
- an always-on host for the scheduler
- product events from your app (webhook or DB)

## 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 Mara.

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 =====
# Mara indie build

## Goal

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

## Scope

Take product events, draft the next lifecycle email with an LLM in your voice, hold it for approval, and send it on a schedule.

## 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:
- deliverability: warmup, domain reputation, bounce and complaint handling
- the improvement loop: variants written, split across live sends, losers rewritten
- reply handling: inbound classified, answers drafted, suppressions applied
- outcome tracking wired back to the copy that caused it
- the maintenance nobody does, which is the actual reason lifecycle programs rot

If those capabilities are essential, use Mautic 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 self-hosted lifecycle email agent to replace Mara, for one SaaS product. Requirements:

- Node + Express + better-sqlite3 on my VPS, one SQLite file holding contacts,
  events, sequences, drafts, sends, and suppressions. node-cron ticks once a minute,
  no queue service.
- POST /events takes {type, email, properties} with a bearer token from .env. Every
  event upserts a contact and appends a row I can read back later.
- Sequences are JSON files in ./sequences/: an entry event type, then steps with a
  wait ("2d"), an intent in plain words ("nudge them to connect their first
  integration"), and an optional skip-if event type. Ship two: welcome and
  trial-ending.
- Each tick, find contacts due for a step, drop anyone whose skip-if event already
  fired, then draft with the Anthropic API (key in .env): pass ./voice.md plus that
  contact's last 20 events, get back a subject and a plain-text body.
- Drafts land as pending. A localhost-only admin page lists them with subject, body,
  recipient, and the step that produced it, with Approve and Reject buttons. Nothing
  sends without a click.
- Approved mail goes out through Resend or SMTP from .env, one send row per recipient
  with the provider message id. Bounce and complaint webhooks write to a suppression
  table checked before every send. One-click unsubscribe link in every footer, no
  login.
- Cap at 2 emails per contact per 7 days across all sequences, enforced in code
  before drafting.
- Out of scope: A/B variants, reply parsing, open tracking. Do not build multi-user
  accounts or a visual sequence builder, this runs for one product and one operator.
- README with the deliverability homework: SPF, DKIM, and DMARC on a subdomain like
  mail.example.com, a two-week warmup at low volume, and a blunt line that mail from
  a cold domain lands in spam no matter how good the copy is.

## Required capabilities

- Anthropic or OpenAI API key
- email sending API (Resend, Postmark, or SES)
- your own sending subdomain with SPF/DKIM/DMARC
- an always-on host for the scheduler
- product events from your app (webhook or DB)

## 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 Mara.

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 =====
# Mara product brief

## Problem

The first send is a weekend. An agent can absolutely wire product events to an LLM draft to an email API with an approval queue, and that covers the visible part of the product. What does not come out of one prompt is the part after the first send: your own domain's reputation, suppression and compliance, variants split across real sends with the results read back, replies classified and answered, and someone still tuning it in month four. Build the sender, then be honest about whether you will keep running it.

## Product outcome

Take product events, draft the next lifecycle email with an LLM in your voice, hold it for approval, and send it on a schedule.

## Target user

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

## Required capabilities

- Anthropic or OpenAI API key
- email sending API (Resend, Postmark, or SES)
- your own sending subdomain with SPF/DKIM/DMARC
- an always-on host for the scheduler
- product events from your app (webhook or DB)

## Explicit non-goals for v1

- deliverability: warmup, domain reputation, bounce and complaint handling
- the improvement loop: variants written, split across live sends, losers rewritten
- reply handling: inbound classified, answers drafted, suppressions applied
- outcome tracking wired back to the copy that caused it
- the maintenance nobody does, which is the actual reason lifecycle programs rot

## 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 self-hosted lifecycle email agent to replace Mara, for one SaaS product. Requirements:

- Node + Express + better-sqlite3 on my VPS, one SQLite file holding contacts,
  events, sequences, drafts, sends, and suppressions. node-cron ticks once a minute,
  no queue service.
- POST /events takes {type, email, properties} with a bearer token from .env. Every
  event upserts a contact and appends a row I can read back later.
- Sequences are JSON files in ./sequences/: an entry event type, then steps with a
  wait ("2d"), an intent in plain words ("nudge them to connect their first
  integration"), and an optional skip-if event type. Ship two: welcome and
  trial-ending.
- Each tick, find contacts due for a step, drop anyone whose skip-if event already
  fired, then draft with the Anthropic API (key in .env): pass ./voice.md plus that
  contact's last 20 events, get back a subject and a plain-text body.
- Drafts land as pending. A localhost-only admin page lists them with subject, body,
  recipient, and the step that produced it, with Approve and Reject buttons. Nothing
  sends without a click.
- Approved mail goes out through Resend or SMTP from .env, one send row per recipient
  with the provider message id. Bounce and complaint webhooks write to a suppression
  table checked before every send. One-click unsubscribe link in every footer, no
  login.
- Cap at 2 emails per contact per 7 days across all sequences, enforced in code
  before drafting.
- Out of scope: A/B variants, reply parsing, open tracking. Do not build multi-user
  accounts or a visual sequence builder, this runs for one product and one operator.
- README with the deliverability homework: SPF, DKIM, and DMARC on a subdomain like
  mail.example.com, a two-week warmup at low volume, and a blunt line that mail from
  a cold domain lands in spam no matter how good the copy is.

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

# Mara indie build

## Goal

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

## Scope

Take product events, draft the next lifecycle email with an LLM in your voice, hold it for approval, and send it on a schedule.

## 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:
- deliverability: warmup, domain reputation, bounce and complaint handling
- the improvement loop: variants written, split across live sends, losers rewritten
- reply handling: inbound classified, answers drafted, suppressions applied
- outcome tracking wired back to the copy that caused it
- the maintenance nobody does, which is the actual reason lifecycle programs rot

If those capabilities are essential, use Mautic 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 self-hosted lifecycle email agent to replace Mara, for one SaaS product. Requirements:

- Node + Express + better-sqlite3 on my VPS, one SQLite file holding contacts,
  events, sequences, drafts, sends, and suppressions. node-cron ticks once a minute,
  no queue service.
- POST /events takes {type, email, properties} with a bearer token from .env. Every
  event upserts a contact and appends a row I can read back later.
- Sequences are JSON files in ./sequences/: an entry event type, then steps with a
  wait ("2d"), an intent in plain words ("nudge them to connect their first
  integration"), and an optional skip-if event type. Ship two: welcome and
  trial-ending.
- Each tick, find contacts due for a step, drop anyone whose skip-if event already
  fired, then draft with the Anthropic API (key in .env): pass ./voice.md plus that
  contact's last 20 events, get back a subject and a plain-text body.
- Drafts land as pending. A localhost-only admin page lists them with subject, body,
  recipient, and the step that produced it, with Approve and Reject buttons. Nothing
  sends without a click.
- Approved mail goes out through Resend or SMTP from .env, one send row per recipient
  with the provider message id. Bounce and complaint webhooks write to a suppression
  table checked before every send. One-click unsubscribe link in every footer, no
  login.
- Cap at 2 emails per contact per 7 days across all sequences, enforced in code
  before drafting.
- Out of scope: A/B variants, reply parsing, open tracking. Do not build multi-user
  accounts or a visual sequence builder, this runs for one product and one operator.
- README with the deliverability homework: SPF, DKIM, and DMARC on a subdomain like
  mail.example.com, a two-week warmup at low volume, and a blunt line that mail from
  a cold domain lands in spam no matter how good the copy is.

## Required capabilities

- Anthropic or OpenAI API key
- email sending API (Resend, Postmark, or SES)
- your own sending subdomain with SPF/DKIM/DMARC
- an always-on host for the scheduler
- product events from your app (webhook or DB)

## 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.

# Mara product brief

## Problem

The first send is a weekend. An agent can absolutely wire product events to an LLM draft to an email API with an approval queue, and that covers the visible part of the product. What does not come out of one prompt is the part after the first send: your own domain's reputation, suppression and compliance, variants split across real sends with the results read back, replies classified and answered, and someone still tuning it in month four. Build the sender, then be honest about whether you will keep running it.

## Product outcome

Take product events, draft the next lifecycle email with an LLM in your voice, hold it for approval, and send it on a schedule.

## Target user

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

## Required capabilities

- Anthropic or OpenAI API key
- email sending API (Resend, Postmark, or SES)
- your own sending subdomain with SPF/DKIM/DMARC
- an always-on host for the scheduler
- product events from your app (webhook or DB)

## Explicit non-goals for v1

- deliverability: warmup, domain reputation, bounce and complaint handling
- the improvement loop: variants written, split across live sends, losers rewritten
- reply handling: inbound classified, answers drafted, suppressions applied
- outcome tracking wired back to the copy that caused it
- the maintenance nobody does, which is the actual reason lifecycle programs rot

## 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 self-hosted lifecycle email agent to replace Mara, for one SaaS product. Requirements:

- Node + Express + better-sqlite3 on my VPS, one SQLite file holding contacts,
  events, sequences, drafts, sends, and suppressions. node-cron ticks once a minute,
  no queue service.
- POST /events takes {type, email, properties} with a bearer token from .env. Every
  event upserts a contact and appends a row I can read back later.
- Sequences are JSON files in ./sequences/: an entry event type, then steps with a
  wait ("2d"), an intent in plain words ("nudge them to connect their first
  integration"), and an optional skip-if event type. Ship two: welcome and
  trial-ending.
- Each tick, find contacts due for a step, drop anyone whose skip-if event already
  fired, then draft with the Anthropic API (key in .env): pass ./voice.md plus that
  contact's last 20 events, get back a subject and a plain-text body.
- Drafts land as pending. A localhost-only admin page lists them with subject, body,
  recipient, and the step that produced it, with Approve and Reject buttons. Nothing
  sends without a click.
- Approved mail goes out through Resend or SMTP from .env, one send row per recipient
  with the provider message id. Bounce and complaint webhooks write to a suppression
  table checked before every send. One-click unsubscribe link in every footer, no
  login.
- Cap at 2 emails per contact per 7 days across all sequences, enforced in code
  before drafting.
- Out of scope: A/B variants, reply parsing, open tracking. Do not build multi-user
  accounts or a visual sequence builder, this runs for one product and one operator.
- README with the deliverability homework: SPF, DKIM, and DMARC on a subdomain like
  mail.example.com, a two-week warmup at low volume, and a blunt line that mail from
  a cold domain lands in spam no matter how good the copy is.

## 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 Mara 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