Two modes based on $ARGUMENTS:
Mode 1: Epic fan-out (MF projects only). If $ARGUMENTS is a Linear epic identifier (e.g. TEAM-100):
- Read the epic's child issues via Linear MCP (
mcp__claude_ai_Linear__list_issues with parentId: <epic-id>).
- For each child whose status is Backlog or Todo, call
magic-codex spawn with:
role: "implementer"
prompt: a clear task description from the child's title + description
issue_id: the child's identifier
- Collect all
agent_ids. Report: "Spawned N agents for epic TEAM-100 children: [list]."
- Suggest polling via
/magic-codex:status (no args → all-agents table) until all terminal.
Mode 2: Inline list. If $ARGUMENTS is a list of prompts separated by --- or ;;:
- Split into N prompts.
- Spawn one implementer per prompt (no
issue_id).
- Return the agent_ids.
Guardrails:
- Warn if spawning more than 5 agents at once (resource concern, and most users want to review in batches).
- If
get_delegation_policy returns minimal, ask the user to confirm before fan-out (fan-out is high-delegation by definition).