subagent-prompt

# Sub-Agent Orchestration Prompt Produce a single, self-contained prompt that the user can paste into a new Claude Code session to execute the work discussed in this conversation. The new session is the **orchestrator**: it dispatches a sub-agent per task and only synthesizes results — it does not implement code itself. ## Goal Hand off the current session's work to a fresh context window in a form that: - Runs to completion without needing the user to babysit each step - Uses one sub-agent per task so each task has its own context window - Forces each sub-agent to **verify** its own work before reporting back - Leaves the orchestrator with enough material to confirm the whole job is functional at the end ## Gates Complete in order. Do not advance until the **Pass when** condition holds. 1. **Source material identified** — **Pass when:** You can point to the concrete artifacts this prompt will hand off (a plan file, a checklist, a list of changes the user described, etc.). If the conversation has only vague intent, ask the user what the prompt should cover before drafting. 2. **Task decomposition explicit** — **Pass when:** You have a numbered list of tasks (or you can point to one already on disk) where each task is small enough for one sub-agent to own end-to-end. If the work is monolithic, decompose it before drafting the prompt. 3. **Verification per task specified** — **Pass when:** For every task, you have named the concrete check a sub-agent must run before repo...