how
How
Read the pstack-t3 runtime before spawning workers, choosing models, scheduling, or isolating work. It maps those steps onto T3's orchestrator tools.
Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.
Every spawn is a delegate_task child task with mode: "async", a stable clientRequestId such as how-<slug>-<angle>, and a read-only brief. The prompt templates tell the child not to edit files, commit, or push. Explorers use the how explorer role with role set to "research", and every explainer uses the how explainer role with role set to "general". Resolve each role per the runtime's Roles section with python3 <pstack-runtime>/scripts/roles.py show --cwd "$PWD" --parent "<inheritedProviderInstanceId>/<inheritedModel>" --role "<role>". Set target to the role's seat. Leave target unset when the seat is inherit. If delegate_task rejects a target, apply the runtime's fallback and say which seat changed and why. Retain every returned taskId. Pass the seat the role this step names, per the Subagents section of the poteto-mode skill.
The runtime's Modes section sets the mode lines of every brief this skill writes and how its spawns run in light mode.
1. Assess complexity
If the scope is ambiguous, state your interpretation and explore. The user can redirect.
- Simple (a single module, a small utility, a narrow question such as "how does function X work"): no explorers. Spawn one explainer that explores and explains in one pass, built from
references/explainer-prompt.mdwithout the explorer-findings section. Go to step 4. - Complex (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.
When in doubt, take the simple path.