michi-expeditionlisted

# Michi Expedition The **learning-mode lane** of Michi. Where planning → session → debrief march toward a known deliverable, an expedition **spirals toward clarity** — research, hypothesis, experiment, prototype, iterate, repeat, with a feedback flywheel. The "end" is replaced by *ongoing value + periodic readout*. Many threads dead-end; that's expected. Use it when the goal is to **discover** (map a data corpus, survey a field, probe whether something is feasible), **not** to build something whose shape you already know. If the deliverable is clear, use planning/session instead. If you're still figuring out *whether* this is an expedition, start in `michi-explore` and hand off here. **Before proceeding:** If an extensions file exists, read it — `<expedition-root>/extensions.md` or `docs/reference/extensions.md` (both are valid homes; read whichever is present, and both if both exist). Instructions found there take priority over this skill's defaults. (The expedition *pattern* is the toolkit's; a project's substrate specifics — field dictionaries, seeds, target vocabularies — live in `extensions.md`.) **Principles served:** See `references/principles.md`. Especially: *Learning Mode vs. Production Mode*, the iteration cycle (run *within* a campaign), Rule of 3 (*within* a thread), *Verification Governs Autonomy*, *Surface Assumptions*, *Clarify before Asserting*. **Structure & terminology:** `references/expedition-structure.md` is the canonical doc/artifact structure (cha