Vibecode Aldena

You are building a lean indie version of Aldena.

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 =====
# Aldena indie build

## Goal

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

## Scope

Run several role-scoped agents against one Docker sandbox, let a manager agent hand work to the others and collect their replies, gate the dangerous tools behind an approval prompt, and end the run with a branch and a pull request.

## 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 machine per project that someone else provisions, patches and bills by the hour
- connected GitHub, Bitbucket, Jira, Linear, Notion, Slack, Drive, Gmail, Sentry and Vercel, and the upkeep behind those tokens
- memory that outlives the run, private per agent and shared per project
- a screen a non-engineer can watch the run in and approve from
- one prepaid balance metering every model and every server hour

If those capabilities are essential, use Claude Agent SDK 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 local team of AI coding agents that ships pull requests, to replace Aldena. Requirements:

- A CLI plus a local web page: Node 24 + Express + better-sqlite3, server-rendered with
  a little vanilla JS. `agents run "add rate limiting"` starts a run and the page on
  localhost:7070 streams what every agent is doing.
- Agents are rows in SQLite: name, role, instructions, model. Seed five (manager, analyst,
  backend, frontend, reviewer) from a roles.json I can edit, each calling the Anthropic API
  with the key from .env.
- Only the manager takes my request. It hands work to at most 3 agents per turn and stops
  at depth 5. Every hand-off, reply and tool call is a row in SQLite so I can read a run
  back a week later.
- File edits and shell commands run inside one Docker container per project, mounting only
  that project's checkout. Never on my host, never two agents in the same container at once.
- A tools.json of allow / ask / deny per tool. On ask the run blocks and the web page shows
  the exact command with Approve and Reject buttons; on deny the tool is not in the schema
  the agent sees at all.
- Memory is two Markdown files loaded at the start of a run and appended to at the end:
  .agents/project.md that all of them read, .agents/NAME.md private to one agent. Cap each
  at 100 lines and make the agent delete a line before it writes a new one.
- A run ends with a branch, a commit and `gh pr create`. No agent gets the merge command,
  that stays mine.
- Out of scope: multi-user accounts, seat billing, and OAuth into Jira, Linear or Slack.
  Do not provision servers, the Docker container is the whole runtime.
- No accounts, no telemetry, everything on my machine except the model calls. Secrets in .env.
- Include a README with setup, where the SQLite file lives, and how to authenticate `gh`
  before the first run.

## Required capabilities

- Docker
- Anthropic or OpenAI API key
- GitHub CLI authenticated against the repo
- Node.js 24

## 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 Aldena.

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 =====
# Aldena indie build

## Goal

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

## Scope

Run several role-scoped agents against one Docker sandbox, let a manager agent hand work to the others and collect their replies, gate the dangerous tools behind an approval prompt, and end the run with a branch and a pull request.

## 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 machine per project that someone else provisions, patches and bills by the hour
- connected GitHub, Bitbucket, Jira, Linear, Notion, Slack, Drive, Gmail, Sentry and Vercel, and the upkeep behind those tokens
- memory that outlives the run, private per agent and shared per project
- a screen a non-engineer can watch the run in and approve from
- one prepaid balance metering every model and every server hour

If those capabilities are essential, use Claude Agent SDK 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 local team of AI coding agents that ships pull requests, to replace Aldena. Requirements:

- A CLI plus a local web page: Node 24 + Express + better-sqlite3, server-rendered with
  a little vanilla JS. `agents run "add rate limiting"` starts a run and the page on
  localhost:7070 streams what every agent is doing.
- Agents are rows in SQLite: name, role, instructions, model. Seed five (manager, analyst,
  backend, frontend, reviewer) from a roles.json I can edit, each calling the Anthropic API
  with the key from .env.
- Only the manager takes my request. It hands work to at most 3 agents per turn and stops
  at depth 5. Every hand-off, reply and tool call is a row in SQLite so I can read a run
  back a week later.
- File edits and shell commands run inside one Docker container per project, mounting only
  that project's checkout. Never on my host, never two agents in the same container at once.
- A tools.json of allow / ask / deny per tool. On ask the run blocks and the web page shows
  the exact command with Approve and Reject buttons; on deny the tool is not in the schema
  the agent sees at all.
- Memory is two Markdown files loaded at the start of a run and appended to at the end:
  .agents/project.md that all of them read, .agents/NAME.md private to one agent. Cap each
  at 100 lines and make the agent delete a line before it writes a new one.
- A run ends with a branch, a commit and `gh pr create`. No agent gets the merge command,
  that stays mine.
- Out of scope: multi-user accounts, seat billing, and OAuth into Jira, Linear or Slack.
  Do not provision servers, the Docker container is the whole runtime.
- No accounts, no telemetry, everything on my machine except the model calls. Secrets in .env.
- Include a README with setup, where the SQLite file lives, and how to authenticate `gh`
  before the first run.

## Required capabilities

- Docker
- Anthropic or OpenAI API key
- GitHub CLI authenticated against the repo
- Node.js 24

## 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 Aldena.

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 =====
# Aldena product brief

## Problem

One room's worth of this is a weekend now that the agent loop ships as an SDK: five role-scoped agents in a Docker sandbox, a manager that hands work down, a prompt before anything destructive, a pull request at the end. What does not fall out of that weekend is the rest of it. A server per project that somebody else patches and meters, ten OAuth integrations that stay authorized, memory that survives the run, and a screen where the person paying for the work can watch it and approve it. Build the room. The building around the room is the subscription.

## Product outcome

Run several role-scoped agents against one Docker sandbox, let a manager agent hand work to the others and collect their replies, gate the dangerous tools behind an approval prompt, and end the run with a branch and a pull request.

## Target user

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

## Required capabilities

- Docker
- Anthropic or OpenAI API key
- GitHub CLI authenticated against the repo
- Node.js 24

## Explicit non-goals for v1

- a machine per project that someone else provisions, patches and bills by the hour
- connected GitHub, Bitbucket, Jira, Linear, Notion, Slack, Drive, Gmail, Sentry and Vercel, and the upkeep behind those tokens
- memory that outlives the run, private per agent and shared per project
- a screen a non-engineer can watch the run in and approve from
- one prepaid balance metering every model and every server hour

## 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 local team of AI coding agents that ships pull requests, to replace Aldena. Requirements:

- A CLI plus a local web page: Node 24 + Express + better-sqlite3, server-rendered with
  a little vanilla JS. `agents run "add rate limiting"` starts a run and the page on
  localhost:7070 streams what every agent is doing.
- Agents are rows in SQLite: name, role, instructions, model. Seed five (manager, analyst,
  backend, frontend, reviewer) from a roles.json I can edit, each calling the Anthropic API
  with the key from .env.
- Only the manager takes my request. It hands work to at most 3 agents per turn and stops
  at depth 5. Every hand-off, reply and tool call is a row in SQLite so I can read a run
  back a week later.
- File edits and shell commands run inside one Docker container per project, mounting only
  that project's checkout. Never on my host, never two agents in the same container at once.
- A tools.json of allow / ask / deny per tool. On ask the run blocks and the web page shows
  the exact command with Approve and Reject buttons; on deny the tool is not in the schema
  the agent sees at all.
- Memory is two Markdown files loaded at the start of a run and appended to at the end:
  .agents/project.md that all of them read, .agents/NAME.md private to one agent. Cap each
  at 100 lines and make the agent delete a line before it writes a new one.
- A run ends with a branch, a commit and `gh pr create`. No agent gets the merge command,
  that stays mine.
- Out of scope: multi-user accounts, seat billing, and OAuth into Jira, Linear or Slack.
  Do not provision servers, the Docker container is the whole runtime.
- No accounts, no telemetry, everything on my machine except the model calls. Secrets in .env.
- Include a README with setup, where the SQLite file lives, and how to authenticate `gh`
  before the first run.

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

# Aldena indie build

## Goal

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

## Scope

Run several role-scoped agents against one Docker sandbox, let a manager agent hand work to the others and collect their replies, gate the dangerous tools behind an approval prompt, and end the run with a branch and a pull request.

## 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 machine per project that someone else provisions, patches and bills by the hour
- connected GitHub, Bitbucket, Jira, Linear, Notion, Slack, Drive, Gmail, Sentry and Vercel, and the upkeep behind those tokens
- memory that outlives the run, private per agent and shared per project
- a screen a non-engineer can watch the run in and approve from
- one prepaid balance metering every model and every server hour

If those capabilities are essential, use Claude Agent SDK 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 local team of AI coding agents that ships pull requests, to replace Aldena. Requirements:

- A CLI plus a local web page: Node 24 + Express + better-sqlite3, server-rendered with
  a little vanilla JS. `agents run "add rate limiting"` starts a run and the page on
  localhost:7070 streams what every agent is doing.
- Agents are rows in SQLite: name, role, instructions, model. Seed five (manager, analyst,
  backend, frontend, reviewer) from a roles.json I can edit, each calling the Anthropic API
  with the key from .env.
- Only the manager takes my request. It hands work to at most 3 agents per turn and stops
  at depth 5. Every hand-off, reply and tool call is a row in SQLite so I can read a run
  back a week later.
- File edits and shell commands run inside one Docker container per project, mounting only
  that project's checkout. Never on my host, never two agents in the same container at once.
- A tools.json of allow / ask / deny per tool. On ask the run blocks and the web page shows
  the exact command with Approve and Reject buttons; on deny the tool is not in the schema
  the agent sees at all.
- Memory is two Markdown files loaded at the start of a run and appended to at the end:
  .agents/project.md that all of them read, .agents/NAME.md private to one agent. Cap each
  at 100 lines and make the agent delete a line before it writes a new one.
- A run ends with a branch, a commit and `gh pr create`. No agent gets the merge command,
  that stays mine.
- Out of scope: multi-user accounts, seat billing, and OAuth into Jira, Linear or Slack.
  Do not provision servers, the Docker container is the whole runtime.
- No accounts, no telemetry, everything on my machine except the model calls. Secrets in .env.
- Include a README with setup, where the SQLite file lives, and how to authenticate `gh`
  before the first run.

## Required capabilities

- Docker
- Anthropic or OpenAI API key
- GitHub CLI authenticated against the repo
- Node.js 24

## 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.

# Aldena product brief

## Problem

One room's worth of this is a weekend now that the agent loop ships as an SDK: five role-scoped agents in a Docker sandbox, a manager that hands work down, a prompt before anything destructive, a pull request at the end. What does not fall out of that weekend is the rest of it. A server per project that somebody else patches and meters, ten OAuth integrations that stay authorized, memory that survives the run, and a screen where the person paying for the work can watch it and approve it. Build the room. The building around the room is the subscription.

## Product outcome

Run several role-scoped agents against one Docker sandbox, let a manager agent hand work to the others and collect their replies, gate the dangerous tools behind an approval prompt, and end the run with a branch and a pull request.

## Target user

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

## Required capabilities

- Docker
- Anthropic or OpenAI API key
- GitHub CLI authenticated against the repo
- Node.js 24

## Explicit non-goals for v1

- a machine per project that someone else provisions, patches and bills by the hour
- connected GitHub, Bitbucket, Jira, Linear, Notion, Slack, Drive, Gmail, Sentry and Vercel, and the upkeep behind those tokens
- memory that outlives the run, private per agent and shared per project
- a screen a non-engineer can watch the run in and approve from
- one prepaid balance metering every model and every server hour

## 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 local team of AI coding agents that ships pull requests, to replace Aldena. Requirements:

- A CLI plus a local web page: Node 24 + Express + better-sqlite3, server-rendered with
  a little vanilla JS. `agents run "add rate limiting"` starts a run and the page on
  localhost:7070 streams what every agent is doing.
- Agents are rows in SQLite: name, role, instructions, model. Seed five (manager, analyst,
  backend, frontend, reviewer) from a roles.json I can edit, each calling the Anthropic API
  with the key from .env.
- Only the manager takes my request. It hands work to at most 3 agents per turn and stops
  at depth 5. Every hand-off, reply and tool call is a row in SQLite so I can read a run
  back a week later.
- File edits and shell commands run inside one Docker container per project, mounting only
  that project's checkout. Never on my host, never two agents in the same container at once.
- A tools.json of allow / ask / deny per tool. On ask the run blocks and the web page shows
  the exact command with Approve and Reject buttons; on deny the tool is not in the schema
  the agent sees at all.
- Memory is two Markdown files loaded at the start of a run and appended to at the end:
  .agents/project.md that all of them read, .agents/NAME.md private to one agent. Cap each
  at 100 lines and make the agent delete a line before it writes a new one.
- A run ends with a branch, a commit and `gh pr create`. No agent gets the merge command,
  that stays mine.
- Out of scope: multi-user accounts, seat billing, and OAuth into Jira, Linear or Slack.
  Do not provision servers, the Docker container is the whole runtime.
- No accounts, no telemetry, everything on my machine except the model calls. Secrets in .env.
- Include a README with setup, where the SQLite file lives, and how to authenticate `gh`
  before the first run.

## 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 Aldena 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