commanders: think as long as you like, then say almost none of it

The first self-started intake produced a correct audit — session id, armed state,
the procedure file, the claim script and the incident behind it, six releases by
tag, the fleet doc, what is not currently polling — and then a question at the
bottom. Everything in it was true and it was the wrong shape. The person is
making one decision, and everything that does not help them make it is in the way
of it.

So the rule is about output, not effort: read everything, then two or three
sentences and the question. No headings, no bullets, no inventory of what was
checked, no ids or paths unless the question is about a file. Not the word
"verified" either — being asked to look and reporting that you looked is not a
finding.

The detail is not lost, it is in the agent's own history, and the second question
is where it earns its place: by then they have said which part matters. A first
message somebody has to skim is one they answer badly, which costs more than the
turn it saved.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

skills/commander/SKILL.md

@@ -73,9 +73,22 @@ Do that instead of inferring how something works from its directory listing, and
 explain something already written down. If there is no skill for what they named, say so plainly and ask;
 that is a real answer, and inventing a mechanism to fill the gap is not.
 
-Then open with what you found, and one question. Not four. A person answers one question well and a list
+Then open with what you found, and one question. Not four — a person answers one question well and a list
-badly, and the answers you get to questions two through four will be shaped by the answer to the first
+badly, and the answers to questions two through four will be shaped by the answer to the first anyway.
-anyway.
+
+**And keep that short.** Two or three sentences, then the question. This is the hardest rule here to
+follow, because you will have just done a lot of work and it all feels worth saying — it is not. The person
+is making one decision, and everything that does not help them make it is in the way of it.
+
+So: no headings, no bullets, no inventory of what you checked, no ids, no paths, no file names unless the
+question is about a file. Do not write the word "verified" — you were asked to look, and saying you looked
+is not a finding. Say what you found in the way you would say it out loud to someone who just walked in:
+*"Looks like you already do this by hand and there's a procedure written down — is that what you want me to
+take over, or is it something else?"* That is the whole opening.
+
+Think as hard and as long as you like. Read everything. Then say almost none of it. What you found stays
+available — it is in your own history, and the next question is where the detail earns its place, once they
+have told you which detail matters. A first message they have to skim is one they answer badly.
 
 **Then work through the questions below, one at a time, in that order.** Follow the answers where they go —
 this is a conversation and the interesting parts are the corrections. Do not move on from a trigger that