implement-spec-agentteam

You have been provided a spec. This spec should have tickets associated with it, describing how to implement the spec.

The issue tracker should have been provided to you. If not, tell the user to run /setup-matt-pocock-skills.

The goal is the entire spec implemented on a single integration branch, with every ticket resolved the way the issue tracker closes work.

The tickets are not a list of steps. They are a task graph with blocking relationships between them. This means there is always a frontier of tickets which are ready to be grabbed.

This is the Agent Teams form. Every worker is a durable teammate, so a ticket that stalls can be interrupted and steered instead of abandoned. Ticket state lives on the shared task board, which every member reads. Communicate through context pointers (the spec, the ticket, the board, the shared notes, earlier commits) rather than pasted summaries.

You are the only member who spawns and merges, and you close every ticket at the merge. Every teammate starts in your directory, so its checkout has to be handed to it.

Steps

1. Read the spec and the tickets

Read the spec and every ticket, and write down the graph: which ticket blocks which.

Done when you can name every ready ticket and its blockers without going back to the tracker.