plan-execute

$ARGUMENTS is either a url to a ticket containing the request, a pointer to a file containing the request or the request in text format.

If it's a ticket, use either the Jira CLI (if it's a jira ticket), the Linear CLI (if it's a linear ticket) or the Github CLI (if it's a github ticket) to read and fully understand the request, including any comments or meta data associated with the ticket.

If it's a file, read the entire file without offset or limit to understand the request.

Is this a simple request? Just execute it as usual and ignore the rest...

Otherwise:

Review all available agent types listed in the Task tool's subagent_type options. This includes built-in agents (like Explore, general-purpose), custom agents (from .claude/agents/), and plugin agents (from .claude/settings.json enabledPlugins). For each agent, explain in one sentence why it IS or IS NOT relevant to this task. Then select all agents that are relevant. You MUST justify excluding an agent — inclusion is the default.

When deciding the agents to use, consider:

• Before any task is implemented, the agent team must explore the codebase for relevant research (documentation, code, git history, etc) and update each task's metadata.relevant_documentation with the findings.
• Each task must be reviewed by the team to make sure their verification passes.
• Each task must have their learnings reviewed by the learner subagent.