/orient-status

Computes a fresh, honest read of where the current work stands — position, remaining work, and a banded ETA — and returns it as one ephemeral bundle (a structured YON record + a human markdown read + a small visual). --resume re-frames it for the "I just came back and lost the thread" case. Part of the orient- family; emits a slice of the shared record at orient-spec/orient-record.yon.

Structured execution spec: protocol.yon. Read it for the canonical steps, rules, and gates; this file is the human-readable, self-sufficient explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.

When to use

• "Where are we / what's the status / how far along / what's the ETA" on a project, repo, plan, or task.
• After a context fill or at the start of a session, before deciding the next move.
• --resume: you've been away (a gap, a context-switch) and lost the thread — you need what changed + exactly where to put your hands next.

How it works (self-sufficient — works without protocol.yon)

orient-status delegates the gathering to a bounded, read-only subagent so the calling session (a human's, or an agent orienting itself) never sees the search/inference noise — only the result bundle comes back. Nothing is stored; every call recomputes from current reality.

1. Take intent as input, never prompt for it. Intent (the goal / what "done" means) is the denominator every read leans on, and it is the least recoverable thing from evidence. Accept an intent argument if given. If intent can't be grounded (no stated goal, no plan, no README), gate every intent-dependent field — render it — (needs goal) and cap its confidence to guessed. Never fabricate a goal and hang a confident read off it. On an evidence-poor surface the highest-value output is the nudge: "name the goal in one line and I get sharper."