Vibecode Yado

You are building a lean indie version of Yado.

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 =====
# Yado indie build

## Goal

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

## Scope

Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends.

## 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:
- a real chat with your Claude account instead of a terminal driven by a phone keyboard
- a machine that sleeps at zero and wakes before you type instead of a box you pay for all week
- one tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once
- diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building
- isolation · one box means everything on it can reach everything else on it

If those capabilities are essential, use Happy 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 phone-reachable Claude Code setup to replace Yado. Requirements:

- Runs on one always-on Ubuntu box I already own, a $5 VPS is fine. I reach it
  from Safari on my phone, there is nothing to install on the phone.
- Install Claude Code on the box and log it in by hand once over SSH, so the
  credentials sit on disk and nothing has to handle auth later. This step needs
  a laptop, say so in the README.
- Serve the terminal with ttyd running `tmux new -A -s claude`, so the session
  survives a dropped connection and keeps working while my phone is locked.
- Put Caddy in front for automatic HTTPS on a subdomain, with basic auth
  credentials read from .env. If I already run Tailscale, bind ttyd to the
  tailnet address instead and skip Caddy. No accounts, no telemetry, everything
  stays on my box.
- Make it usable with a thumb: start ttyd with `-t fontSize=18`, and write a
  ~/.tmux.conf with mouse mode on so I can scroll and switch panes by tapping.
- Add a Claude Code Stop hook in ~/.claude/settings.json that curls a private
  ntfy.sh topic, so my phone buzzes when a turn finishes instead of me sitting
  there watching output.
- A `work <repo>` shell function that attaches to the tmux session, cds into
  ~/code/<repo> and starts claude there. Repos live in ~/code, there is no
  database and nothing to migrate.
- Out of scope: multiple users and isolation between projects. Do not build a
  chat UI over `claude -p`, that is a far bigger project than this one.
- README: the one time SSH login, the DNS record for the subdomain, the ntfy
  topic name, and an honest warning that if the box goes down there is no way
  back in from the phone.

## Required capabilities

- an always-on Linux box or a $5 VPS
- a Claude Pro or Max subscription
- a domain for HTTPS, or Tailscale
- a laptop, once, to do the Claude login over SSH

## 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 Yado.

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 =====
# Yado indie build

## Goal

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

## Scope

Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends.

## 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:
- a real chat with your Claude account instead of a terminal driven by a phone keyboard
- a machine that sleeps at zero and wakes before you type instead of a box you pay for all week
- one tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once
- diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building
- isolation · one box means everything on it can reach everything else on it

If those capabilities are essential, use Happy 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 phone-reachable Claude Code setup to replace Yado. Requirements:

- Runs on one always-on Ubuntu box I already own, a $5 VPS is fine. I reach it
  from Safari on my phone, there is nothing to install on the phone.
- Install Claude Code on the box and log it in by hand once over SSH, so the
  credentials sit on disk and nothing has to handle auth later. This step needs
  a laptop, say so in the README.
- Serve the terminal with ttyd running `tmux new -A -s claude`, so the session
  survives a dropped connection and keeps working while my phone is locked.
- Put Caddy in front for automatic HTTPS on a subdomain, with basic auth
  credentials read from .env. If I already run Tailscale, bind ttyd to the
  tailnet address instead and skip Caddy. No accounts, no telemetry, everything
  stays on my box.
- Make it usable with a thumb: start ttyd with `-t fontSize=18`, and write a
  ~/.tmux.conf with mouse mode on so I can scroll and switch panes by tapping.
- Add a Claude Code Stop hook in ~/.claude/settings.json that curls a private
  ntfy.sh topic, so my phone buzzes when a turn finishes instead of me sitting
  there watching output.
- A `work <repo>` shell function that attaches to the tmux session, cds into
  ~/code/<repo> and starts claude there. Repos live in ~/code, there is no
  database and nothing to migrate.
- Out of scope: multiple users and isolation between projects. Do not build a
  chat UI over `claude -p`, that is a far bigger project than this one.
- README: the one time SSH login, the DNS record for the subdomain, the ntfy
  topic name, and an honest warning that if the box goes down there is no way
  back in from the phone.

## Required capabilities

- an always-on Linux box or a $5 VPS
- a Claude Pro or Max subscription
- a domain for HTTPS, or Tailscale
- a laptop, once, to do the Claude login over SSH

## 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 Yado.

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 =====
# Yado product brief

## Problem

Claude Code was never built to leave the laptop. A chat interface is easy. A terminal into a remote container, also fine. The pain starts when you want Claude, the container, and the app to forget they're three completely distinct entities and behave as one thing: signing in with one tap, when on paper that can only happen in a terminal. A chat, when underneath it is always a terminal. Infra that's fast and that keeps one person's AI away from everyone else's code. I thought that was weeks of work. It was months.

## Product outcome

Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends.

## Target user

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

## Required capabilities

- an always-on Linux box or a $5 VPS
- a Claude Pro or Max subscription
- a domain for HTTPS, or Tailscale
- a laptop, once, to do the Claude login over SSH

## Explicit non-goals for v1

- a real chat with your Claude account instead of a terminal driven by a phone keyboard
- a machine that sleeps at zero and wakes before you type instead of a box you pay for all week
- one tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once
- diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building
- isolation · one box means everything on it can reach everything else on it

## 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 phone-reachable Claude Code setup to replace Yado. Requirements:

- Runs on one always-on Ubuntu box I already own, a $5 VPS is fine. I reach it
  from Safari on my phone, there is nothing to install on the phone.
- Install Claude Code on the box and log it in by hand once over SSH, so the
  credentials sit on disk and nothing has to handle auth later. This step needs
  a laptop, say so in the README.
- Serve the terminal with ttyd running `tmux new -A -s claude`, so the session
  survives a dropped connection and keeps working while my phone is locked.
- Put Caddy in front for automatic HTTPS on a subdomain, with basic auth
  credentials read from .env. If I already run Tailscale, bind ttyd to the
  tailnet address instead and skip Caddy. No accounts, no telemetry, everything
  stays on my box.
- Make it usable with a thumb: start ttyd with `-t fontSize=18`, and write a
  ~/.tmux.conf with mouse mode on so I can scroll and switch panes by tapping.
- Add a Claude Code Stop hook in ~/.claude/settings.json that curls a private
  ntfy.sh topic, so my phone buzzes when a turn finishes instead of me sitting
  there watching output.
- A `work <repo>` shell function that attaches to the tmux session, cds into
  ~/code/<repo> and starts claude there. Repos live in ~/code, there is no
  database and nothing to migrate.
- Out of scope: multiple users and isolation between projects. Do not build a
  chat UI over `claude -p`, that is a far bigger project than this one.
- README: the one time SSH login, the DNS record for the subdomain, the ntfy
  topic name, and an honest warning that if the box goes down there is no way
  back in from the phone.

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

# Yado indie build

## Goal

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

## Scope

Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends.

## 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:
- a real chat with your Claude account instead of a terminal driven by a phone keyboard
- a machine that sleeps at zero and wakes before you type instead of a box you pay for all week
- one tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once
- diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building
- isolation · one box means everything on it can reach everything else on it

If those capabilities are essential, use Happy 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 phone-reachable Claude Code setup to replace Yado. Requirements:

- Runs on one always-on Ubuntu box I already own, a $5 VPS is fine. I reach it
  from Safari on my phone, there is nothing to install on the phone.
- Install Claude Code on the box and log it in by hand once over SSH, so the
  credentials sit on disk and nothing has to handle auth later. This step needs
  a laptop, say so in the README.
- Serve the terminal with ttyd running `tmux new -A -s claude`, so the session
  survives a dropped connection and keeps working while my phone is locked.
- Put Caddy in front for automatic HTTPS on a subdomain, with basic auth
  credentials read from .env. If I already run Tailscale, bind ttyd to the
  tailnet address instead and skip Caddy. No accounts, no telemetry, everything
  stays on my box.
- Make it usable with a thumb: start ttyd with `-t fontSize=18`, and write a
  ~/.tmux.conf with mouse mode on so I can scroll and switch panes by tapping.
- Add a Claude Code Stop hook in ~/.claude/settings.json that curls a private
  ntfy.sh topic, so my phone buzzes when a turn finishes instead of me sitting
  there watching output.
- A `work <repo>` shell function that attaches to the tmux session, cds into
  ~/code/<repo> and starts claude there. Repos live in ~/code, there is no
  database and nothing to migrate.
- Out of scope: multiple users and isolation between projects. Do not build a
  chat UI over `claude -p`, that is a far bigger project than this one.
- README: the one time SSH login, the DNS record for the subdomain, the ntfy
  topic name, and an honest warning that if the box goes down there is no way
  back in from the phone.

## Required capabilities

- an always-on Linux box or a $5 VPS
- a Claude Pro or Max subscription
- a domain for HTTPS, or Tailscale
- a laptop, once, to do the Claude login over SSH

## 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.

# Yado product brief

## Problem

Claude Code was never built to leave the laptop. A chat interface is easy. A terminal into a remote container, also fine. The pain starts when you want Claude, the container, and the app to forget they're three completely distinct entities and behave as one thing: signing in with one tap, when on paper that can only happen in a terminal. A chat, when underneath it is always a terminal. Infra that's fast and that keeps one person's AI away from everyone else's code. I thought that was weeks of work. It was months.

## Product outcome

Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends.

## Target user

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

## Required capabilities

- an always-on Linux box or a $5 VPS
- a Claude Pro or Max subscription
- a domain for HTTPS, or Tailscale
- a laptop, once, to do the Claude login over SSH

## Explicit non-goals for v1

- a real chat with your Claude account instead of a terminal driven by a phone keyboard
- a machine that sleeps at zero and wakes before you type instead of a box you pay for all week
- one tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once
- diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building
- isolation · one box means everything on it can reach everything else on it

## 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 phone-reachable Claude Code setup to replace Yado. Requirements:

- Runs on one always-on Ubuntu box I already own, a $5 VPS is fine. I reach it
  from Safari on my phone, there is nothing to install on the phone.
- Install Claude Code on the box and log it in by hand once over SSH, so the
  credentials sit on disk and nothing has to handle auth later. This step needs
  a laptop, say so in the README.
- Serve the terminal with ttyd running `tmux new -A -s claude`, so the session
  survives a dropped connection and keeps working while my phone is locked.
- Put Caddy in front for automatic HTTPS on a subdomain, with basic auth
  credentials read from .env. If I already run Tailscale, bind ttyd to the
  tailnet address instead and skip Caddy. No accounts, no telemetry, everything
  stays on my box.
- Make it usable with a thumb: start ttyd with `-t fontSize=18`, and write a
  ~/.tmux.conf with mouse mode on so I can scroll and switch panes by tapping.
- Add a Claude Code Stop hook in ~/.claude/settings.json that curls a private
  ntfy.sh topic, so my phone buzzes when a turn finishes instead of me sitting
  there watching output.
- A `work <repo>` shell function that attaches to the tmux session, cds into
  ~/code/<repo> and starts claude there. Repos live in ~/code, there is no
  database and nothing to migrate.
- Out of scope: multiple users and isolation between projects. Do not build a
  chat UI over `claude -p`, that is a far bigger project than this one.
- README: the one time SSH login, the DNS record for the subdomain, the ntfy
  topic name, and an honest warning that if the box goes down there is no way
  back in from the phone.

## 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 Yado 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