Command Explorer › scale: — the reply's measure › executive
scale:executive
Bottom line first, decision-ready, as short as the substance allows — the depth is in the work, not the word count.
In the scale: domain
scale:brief — The short version: verdict first, essentials only.scale:deep — The full version: thorough treatment, evidence in view.scale:executive — Bottom line first, decision-ready, as short as the substance allows — the depth is in the work, not the word count.scale:wordy — The long version, fully aired out — expansive on what's known, with the effort capped: no deep dive, no rabbit holes.scale:broad — The broad version: wide coverage over depth — everything touched, nothing exhausted.scale:compact — Short with the substance kept: real work done and packed tight — on the road toward executive, less extreme.What it does
A composed preset: full-depth work compressed to a short, decision-ready surface — bottom line first, supporting points ranked, as short as the substance allows. The depth is in the work, not the word count. It doesn't stack with brief or deep — the last one wins.
The registry's own words: Bottom line first, decision-ready, as short as the substance allows — the depth is in the work, not the word count.
Fire it — usage examples
Two crews quoted my move — one's cheaper, one's been around forever. Which do I book?
→ scale:executive
Spoken. Inside a marked span opened by the wake word “Lingo”, the spoken form is reply executive. Dictated directives fire deliberately, never by accident.
What the agent actually does
Works the question at full depth first — the retrieval and comparison a scale:deep would do — then compresses to the decision surface, ranking points by decision weight. Where full-depth work isn't possible, it says what depth was actually reached rather than presenting a shallow take as an executive one. The deep record stays available to expand back into (scale:deep, re:cite).
The baseline procedure, its edge cases, and this directive's full guide live in the implementation guide: implementation/IMPLEMENTATION.md#cmd-scale-executive ↗.
When the host can't
No host capability required. The depth of the work is bounded by the question and the sources available; where full-depth work is not possible (no retrieval, no tools), say what depth was actually reached rather than letting a short answer imply a deep one.
Conformance — “done when”
You can decide from the first lines — and the work behind them was really done.
Persistence class: none. Execution report in the reply: not required. A user can test any of this by hand — fire the directive, then check the result against the store, the schedule, or the reply itself.