reflect
Reflect
Read the pstack-t3 runtime before spawning workers, choosing models, scheduling, or isolating work. It maps those steps onto T3's orchestrator tools.
Mine the current conversation for durable learnings, then route them into skill edits.
Invoke when the user says "reflect" or "/reflect". Skip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings.
The runtime's Modes section sets the mode lines of every brief this skill writes and how its spawns run in light mode.
1. Locate the active thread
Before fanning out, find this conversation's T3 thread, which the reviewers read with t3_thread_read (see the runtime's History section). Do not read threads from other projects. That reads private chats from unrelated work.
Use the thread id if the host already names it. Otherwise call t3_thread_list with statuses: ["running"] and take the newest candidates. Child task threads this session spawned are threads too. List them with t3_thread_list and includeSubagents: true when a reviewer needs a child's work.
For each candidate, call t3_thread_read with view: "messages" and limit: 1. Take the threadId of the thread whose first user message is the conversation's opening user prompt. If none matches, pass a tight digest of the session instead.