status

status · Project GPS — scan, integrity-check, derive, route

The framework's "where am I / what's next" oracle. It is a cross-cutting meta activity (named by function, not an SDLC seat — prefix-less, like 08-refactor), and per the master plan it is built and run last: it scans everything, so it is correct only once every other skill's shape is final. Give any project to /status and it answers three questions from the files on disk — never from memory:

1. Is the spine sound? — the integrity verdict (PASS, or FAIL naming the offending REQ-ID).
2. What's blocking? — the pending/deferred amendment + surviving [NEEDS CLARIFICATION] counts that 06-release gates on, surfaced early.
3. What do I run next? — the single exact next command, in the framework's vocabulary.

Its graded value is not "a nice summary" — a strong reader summarizes a repo too. It is the deterministic derived state: the integrity verdict + the governance counts + the routed command, computed from the files and emitted machine-readably into CLAUDE.md § Current State so the next seat — and 06's release gate, and the next /status — can act on it, not re-derive it.

(2026-07-28, FB-013) status is the propagation contract — name it, don't leave it implied. The framework propagates by pull: each seat reads a narrow slice, which is what keeps verification isolation auditable and contexts small. That design has exactly one push channel, and this is it — the only seat whose Reads is a superset of every other's, and whose write target (CLAUDE.md § Current State) loads into every session automatically. So: a seat that flips gate-relevant state (a verdict, an amendment row, a release, an audit) routes here before the next seat — their ## Next skill sections say so — and /06 asserts freshness mechanically at G0 rather than trusting that someone ran it. Left optional, this channel simply does not run: three weeks of sustained dogfooding never invoked it once, and every downstream view went stale in exactly the way FB-013 and FB-014 describe. Optional load-bearing machinery is not load-bearing.