study-teamlisted

# Study Team Run an optional, interactive challenge-and-reconciliation pass over an already completed `/deep-study` report. This skill is not part of the deterministic workflow and must never start automatically. ## Preconditions — Stop Unless All Pass 1. The user explicitly invoked `/study-team` in an attended session. 2. A `/deep-study` report is complete in the current conversation. Complete `/deep-study` first if there is no report; do not reconstruct or guess one. 3. Agent teams were enabled by the user before this session with `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`. 4. The session was launched with `--teammate-mode in-process`. 5. The Agent, SendMessage, and task tools required below are available. If any precondition cannot be confirmed, explain exactly what is missing and stop. Do not change settings or enable team mode. Do not fall back to ordinary subagents, background agents, split panes, or sequential role-play. ## Fixed Team Use the session's implicit team and create exactly three teammates. Each teammate receives the complete deep-study report, the user's original request, all evidence and claim identifiers, the shared response contract below, and only its own role brief. Teammates may not spawn agents, teammates, or other descendants. Create one task per role and launch these named teammates: ```yaml subagent_type: "claude-of-alexandria:study-team-textual-evidence" name: "textual-evidence" ``` Focus only on passage boundaries, syntax, discourse