Why

Read the installed poteto-mode reference ../poteto-mode/references/t3-execution.md before selecting models or delegating. It owns named-role resolution, catalog option keys, accounts and automatic authorized missing-usage fallback.

Investigate the motivation and intent behind code. The companion how skill answers what the code does and how it works. why answers what forces led to its shape.

Each spawn below names a role line in pstack-models.md and a bundled default. Resolve the target from that line, or from its default if the file or line is missing. Defaults start at xhigh reasoning through live catalog option keys unless the user chooses a budget. Resolve auto or inherit-parent to the parent target. Handle rejected entries through the execution adapter's authorized fallback preserving effort and required diversity and say so. Set each subagent's reasoning level and speed per the Subagents section of the poteto-mode skill.

Every spawn is a delegate_task child with mode: "async" and a self-contained brief. Preserve MCP access for the investigators and the synthesizer's citation spot-checks. Investigators still shouldn't write anything. T3 child agents get only the brief, never the parent's context. Retain task IDs, once nothing independent is left, end the turn until their completion notifications wake you, then read each result with task_status, and task_cancel only a child whose status is not terminal.

Operating Posture

Operate as a careful, cautious, and precise investigator. Be honest about what you know vs what you're inferring. Read references/epistemics.md for the full confidence framework and phrasing guide. The synthesizer must follow it.

Step 1. Understand the Target and the Question

The target is usually a chunk of code, a pattern, a feature, or a named design decision. The question is usually a design rationale, a tradeoff, a motivating edge case, an external constraint, dead code, or a broad history sweep.

If the target is vague ("why do we do it this way?" with no clear referent), make your best guess from conversation context (open files, recent edits, cursor location, what was just discussed). State your interpretation briefly so the user can redirect if you're off, then proceed.