Vibecode posterly

You are building a lean indie version of posterly.

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 =====
# posterly indie build

## Goal

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

## Scope

A local API and compose queue that publishes to open-API networks on a schedule, with a caption endpoint an agent can call directly instead of a UI-only AI button.

## 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:
- 18 maintained platform integrations, including approval-gated ones (Instagram, LinkedIn, TikTok, Facebook, Google Business Profile)
- a voice model trained on your actual post history and what performed well, not a static prompt template
- Google Business Profile review replies and photo management
- client approval portal and content-plan review for agencies managing multiple brands
- per-platform video/image transcoding tuned to each network's limits
- a hosted MCP server + REST API built for agents, not bolted on after the fact

If those capabilities are essential, use Postiz 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 social scheduler an AI agent can drive, to replace posterly. Requirements:

- Node + Express + better-sqlite3, with both a localhost compose page and
  a small local HTTP API (list_slots, create_post, get_recent_posts) so a
  coding agent can call it directly instead of only a human using the UI.
- Three open-API targets: Mastodon (access token), Bluesky (app password
  via @atproto/api), and a Telegram channel (bot token). One adapter file
  per network so a fourth is addable later.
- A /caption endpoint: given a topic, call an LLM API (key in .env) with
  my last ~20 published posts as style examples, so drafts sound like me
  instead of a generic AI voice. Cache the examples so it's not refetching
  the DB on every call.
- Slot-based queue: posting times per weekday in my timezone, new posts
  fill the next free slot, or pin an exact datetime; duplicate a post
  across networks with per-network text.
- A node-cron tick every minute publishes due posts, marks each row sent
  or failed before sending (no double-posts), retries failures 3 times.
- Attached images in media/ next to the database, resized per network
  with sharp; a history page of the last 100 sent posts linking out.
- Runs on my always-on box; localhost only, no accounts, no telemetry.
- Out of scope: Instagram, LinkedIn, TikTok, Facebook, and Google Business
  Profile (approval-gated APIs, say so in the README), review management,
  client approvals, video transcoding, and analytics.
- README: getting a Mastodon token, a Bluesky app password, a Telegram
  bot token, and pointing a coding agent at the local API.

## Required capabilities

- OAuth/API access per social network
- always-on box for the scheduler
- database
- media storage
- LLM API key for caption generation

## 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 posterly.

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 =====
# posterly indie build

## Goal

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

## Scope

A local API and compose queue that publishes to open-API networks on a schedule, with a caption endpoint an agent can call directly instead of a UI-only AI button.

## 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:
- 18 maintained platform integrations, including approval-gated ones (Instagram, LinkedIn, TikTok, Facebook, Google Business Profile)
- a voice model trained on your actual post history and what performed well, not a static prompt template
- Google Business Profile review replies and photo management
- client approval portal and content-plan review for agencies managing multiple brands
- per-platform video/image transcoding tuned to each network's limits
- a hosted MCP server + REST API built for agents, not bolted on after the fact

If those capabilities are essential, use Postiz 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 social scheduler an AI agent can drive, to replace posterly. Requirements:

- Node + Express + better-sqlite3, with both a localhost compose page and
  a small local HTTP API (list_slots, create_post, get_recent_posts) so a
  coding agent can call it directly instead of only a human using the UI.
- Three open-API targets: Mastodon (access token), Bluesky (app password
  via @atproto/api), and a Telegram channel (bot token). One adapter file
  per network so a fourth is addable later.
- A /caption endpoint: given a topic, call an LLM API (key in .env) with
  my last ~20 published posts as style examples, so drafts sound like me
  instead of a generic AI voice. Cache the examples so it's not refetching
  the DB on every call.
- Slot-based queue: posting times per weekday in my timezone, new posts
  fill the next free slot, or pin an exact datetime; duplicate a post
  across networks with per-network text.
- A node-cron tick every minute publishes due posts, marks each row sent
  or failed before sending (no double-posts), retries failures 3 times.
- Attached images in media/ next to the database, resized per network
  with sharp; a history page of the last 100 sent posts linking out.
- Runs on my always-on box; localhost only, no accounts, no telemetry.
- Out of scope: Instagram, LinkedIn, TikTok, Facebook, and Google Business
  Profile (approval-gated APIs, say so in the README), review management,
  client approvals, video transcoding, and analytics.
- README: getting a Mastodon token, a Bluesky app password, a Telegram
  bot token, and pointing a coding agent at the local API.

## Required capabilities

- OAuth/API access per social network
- always-on box for the scheduler
- database
- media storage
- LLM API key for caption generation

## 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 posterly.

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 =====
# posterly product brief

## Problem

A basic compose-queue-publish loop against open-API networks (Mastodon, Bluesky, Telegram) is a weekend build, same as any scheduler. What's specific to posterly and harder to fake is the agent-native layer: an MCP server exposing tools like generate_captions, get_learned_voice, and find_available_slot so a coding agent can draft and post on your behalf, plus a voice model that's actually learned from your posting history and its own performance data rather than a one-off few-shot prompt. Add Google Business Profile review management, per-platform video transcoding, and client approval workflows for agencies, and the moat is upkeep and depth, not the initial compose/publish loop.

## Product outcome

A local API and compose queue that publishes to open-API networks on a schedule, with a caption endpoint an agent can call directly instead of a UI-only AI button.

## Target user

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

## Required capabilities

- OAuth/API access per social network
- always-on box for the scheduler
- database
- media storage
- LLM API key for caption generation

## Explicit non-goals for v1

- 18 maintained platform integrations, including approval-gated ones (Instagram, LinkedIn, TikTok, Facebook, Google Business Profile)
- a voice model trained on your actual post history and what performed well, not a static prompt template
- Google Business Profile review replies and photo management
- client approval portal and content-plan review for agencies managing multiple brands
- per-platform video/image transcoding tuned to each network's limits
- a hosted MCP server + REST API built for agents, not bolted on after the fact

## 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 social scheduler an AI agent can drive, to replace posterly. Requirements:

- Node + Express + better-sqlite3, with both a localhost compose page and
  a small local HTTP API (list_slots, create_post, get_recent_posts) so a
  coding agent can call it directly instead of only a human using the UI.
- Three open-API targets: Mastodon (access token), Bluesky (app password
  via @atproto/api), and a Telegram channel (bot token). One adapter file
  per network so a fourth is addable later.
- A /caption endpoint: given a topic, call an LLM API (key in .env) with
  my last ~20 published posts as style examples, so drafts sound like me
  instead of a generic AI voice. Cache the examples so it's not refetching
  the DB on every call.
- Slot-based queue: posting times per weekday in my timezone, new posts
  fill the next free slot, or pin an exact datetime; duplicate a post
  across networks with per-network text.
- A node-cron tick every minute publishes due posts, marks each row sent
  or failed before sending (no double-posts), retries failures 3 times.
- Attached images in media/ next to the database, resized per network
  with sharp; a history page of the last 100 sent posts linking out.
- Runs on my always-on box; localhost only, no accounts, no telemetry.
- Out of scope: Instagram, LinkedIn, TikTok, Facebook, and Google Business
  Profile (approval-gated APIs, say so in the README), review management,
  client approvals, video transcoding, and analytics.
- README: getting a Mastodon token, a Bluesky app password, a Telegram
  bot token, and pointing a coding agent at the local API.

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

# posterly indie build

## Goal

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

## Scope

A local API and compose queue that publishes to open-API networks on a schedule, with a caption endpoint an agent can call directly instead of a UI-only AI button.

## 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:
- 18 maintained platform integrations, including approval-gated ones (Instagram, LinkedIn, TikTok, Facebook, Google Business Profile)
- a voice model trained on your actual post history and what performed well, not a static prompt template
- Google Business Profile review replies and photo management
- client approval portal and content-plan review for agencies managing multiple brands
- per-platform video/image transcoding tuned to each network's limits
- a hosted MCP server + REST API built for agents, not bolted on after the fact

If those capabilities are essential, use Postiz 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 social scheduler an AI agent can drive, to replace posterly. Requirements:

- Node + Express + better-sqlite3, with both a localhost compose page and
  a small local HTTP API (list_slots, create_post, get_recent_posts) so a
  coding agent can call it directly instead of only a human using the UI.
- Three open-API targets: Mastodon (access token), Bluesky (app password
  via @atproto/api), and a Telegram channel (bot token). One adapter file
  per network so a fourth is addable later.
- A /caption endpoint: given a topic, call an LLM API (key in .env) with
  my last ~20 published posts as style examples, so drafts sound like me
  instead of a generic AI voice. Cache the examples so it's not refetching
  the DB on every call.
- Slot-based queue: posting times per weekday in my timezone, new posts
  fill the next free slot, or pin an exact datetime; duplicate a post
  across networks with per-network text.
- A node-cron tick every minute publishes due posts, marks each row sent
  or failed before sending (no double-posts), retries failures 3 times.
- Attached images in media/ next to the database, resized per network
  with sharp; a history page of the last 100 sent posts linking out.
- Runs on my always-on box; localhost only, no accounts, no telemetry.
- Out of scope: Instagram, LinkedIn, TikTok, Facebook, and Google Business
  Profile (approval-gated APIs, say so in the README), review management,
  client approvals, video transcoding, and analytics.
- README: getting a Mastodon token, a Bluesky app password, a Telegram
  bot token, and pointing a coding agent at the local API.

## Required capabilities

- OAuth/API access per social network
- always-on box for the scheduler
- database
- media storage
- LLM API key for caption generation

## 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.

# posterly product brief

## Problem

A basic compose-queue-publish loop against open-API networks (Mastodon, Bluesky, Telegram) is a weekend build, same as any scheduler. What's specific to posterly and harder to fake is the agent-native layer: an MCP server exposing tools like generate_captions, get_learned_voice, and find_available_slot so a coding agent can draft and post on your behalf, plus a voice model that's actually learned from your posting history and its own performance data rather than a one-off few-shot prompt. Add Google Business Profile review management, per-platform video transcoding, and client approval workflows for agencies, and the moat is upkeep and depth, not the initial compose/publish loop.

## Product outcome

A local API and compose queue that publishes to open-API networks on a schedule, with a caption endpoint an agent can call directly instead of a UI-only AI button.

## Target user

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

## Required capabilities

- OAuth/API access per social network
- always-on box for the scheduler
- database
- media storage
- LLM API key for caption generation

## Explicit non-goals for v1

- 18 maintained platform integrations, including approval-gated ones (Instagram, LinkedIn, TikTok, Facebook, Google Business Profile)
- a voice model trained on your actual post history and what performed well, not a static prompt template
- Google Business Profile review replies and photo management
- client approval portal and content-plan review for agencies managing multiple brands
- per-platform video/image transcoding tuned to each network's limits
- a hosted MCP server + REST API built for agents, not bolted on after the fact

## 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 social scheduler an AI agent can drive, to replace posterly. Requirements:

- Node + Express + better-sqlite3, with both a localhost compose page and
  a small local HTTP API (list_slots, create_post, get_recent_posts) so a
  coding agent can call it directly instead of only a human using the UI.
- Three open-API targets: Mastodon (access token), Bluesky (app password
  via @atproto/api), and a Telegram channel (bot token). One adapter file
  per network so a fourth is addable later.
- A /caption endpoint: given a topic, call an LLM API (key in .env) with
  my last ~20 published posts as style examples, so drafts sound like me
  instead of a generic AI voice. Cache the examples so it's not refetching
  the DB on every call.
- Slot-based queue: posting times per weekday in my timezone, new posts
  fill the next free slot, or pin an exact datetime; duplicate a post
  across networks with per-network text.
- A node-cron tick every minute publishes due posts, marks each row sent
  or failed before sending (no double-posts), retries failures 3 times.
- Attached images in media/ next to the database, resized per network
  with sharp; a history page of the last 100 sent posts linking out.
- Runs on my always-on box; localhost only, no accounts, no telemetry.
- Out of scope: Instagram, LinkedIn, TikTok, Facebook, and Google Business
  Profile (approval-gated APIs, say so in the README), review management,
  client approvals, video transcoding, and analytics.
- README: getting a Mastodon token, a Bluesky app password, a Telegram
  bot token, and pointing a coding agent at the local API.

## 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 posterly 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