Reflect

A skill named in bold or in backticks, or run as /<name>, is the file ../<name>/SKILL.md beside this skill's directory, and a principle named without its prefix is ../principle-<name>/SKILL.md. Read the file and follow it. Most pstack skills are user-only, so your skill tool cannot load them. Every subagent is a Rex worker pane: spawn, wait and close it per ../rex-subagents/SKILL.md, with the defaults in the Subagents section of ../poteto-mode/SKILL.md.

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.

1. Locate the active transcript

Before fanning out, find this conversation's transcript: run ../rex-subagents/scripts/sessions path <id> by absolute path, where <id> is $CLAUDE_CODE_SESSION_ID on Claude Code and $CODEX_THREAD_ID on Codex (your shell commands see both). Do not search other projects' transcripts. That crosses workspace boundaries and reads private chats from unrelated projects. If the path doesn't resolve, pass a tight digest of the session instead.

2. Spawn three reviewers in parallel

One turn, three subagent spawn calls, each named reflect <lens>, with --read-only and its entry from the role line below. Reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references. --read-only only adds a line to the brief, so MCP access stays, and a worker sees the MCP servers configured for its own harness.

Each reviewer and the synthesizer name a role line in ~/.config/pstack/pstack-models.md and a default harness. Pass the entry to subagent spawn --entry as written. Run the default harness on its default model if the file or the line is missing, and your own harness when the value is auto or inherit-parent. With no file, say so and suggest /setup-pstack. If a worker's model is rejected, run it on that harness's default model and say so. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the poteto-mode skill.