Recall

Read the pstack-t3 runtime before spawning workers, choosing models, scheduling, or isolating work. It maps those steps onto T3's orchestrator tools.

Before you start or resume work, you rebuild the user's recent working context and hand back a tight capsule of where things stand now and what to do next.

Keep it tight and on-topic. Read only what the in-scope threads need, then stop.

Your context lives in two records. Your own chat history holds what you did and decided. The shared record holds everything that happened around the same code under other names: the symptoms users keep reporting, the fixes that shipped and got reverted, the errors still firing in prod. That second record is what the why skill searches, across source control, the issue tracker, chat and issue channels, long-form docs, and error tracking. A feature with a long bug tail keeps most of its story there, so don't reconstruct it from your threads alone.

Your chat history is the current T3 project's threads (the runtime's History section). t3_thread_list lists them newest first, with run status and paging by cursor. Add includeSubagents: true to include child task threads, and settled: true for threads moved out of the active list. t3_thread_search matches a topic, branch, or PR number against titles and content. It is bounded, not exhaustive, so pair it with a dated t3_thread_list sweep when the window matters. t3_thread_read reads one thread: view: "messages" for the conversation, view: "activity" for tool calls, paged with afterPosition. Every thread is cited by its threadId.

The runtime's Modes section sets the mode lines of every brief this skill writes and how its spawns run in light mode.