implement-all

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

Read documentation/agents/issue-tracker.md for the configured tracker workflow. If it is missing, tell the user to run /setup-ai-workspace.

The goal is the entire specification 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.

Communication to and from subagents should be sparse. Communicate primarily through context pointers: to the specification, tickets, research notes, and previous commits. Don't duplicate information already available via pointers.

Implementer subagents should be run in the background where possible for maximum concurrency.

Steps

1. Read the specification and tickets to understand the task graph.

2. (optional) Use an exploration subagent to conduct any exploration required by the tickets - relevant codebase files or external documentation. Ensure the exploration subagent can save files - it should save its markdown notes in a directory outside the repository, accessible by all future subagents. This lets implementer subagents focus on implementation rather than exploration.

3. Create the integration branch. If the issue tracker closes work through pull or merge requests, or the user asks for one, open a draft request after the first merge in step 5, when the branch has commits ahead of the target branch. Mark it as closing the specification and tickets, using the configured tracker workflow, and call the Skill tool with to-pull-request for its body.