docs(captain): the brief template sizes a fix as an eng-only plan too (GST-191 review)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

captain/templates/brief.md

@@ -17,8 +17,10 @@ Spend cap: <focused paid runs per PR, from SPEND>
    set, run dir under ~/.capy/work). Write the plan with its ## ELI5, ## Before → after,
    ## Why it matters, ## What caused this work, ## Big decisions and ## Implementation plan
    sections, then run gstack-autoplan next --out <run dir> --plan <plan.md> <scope flags>
-   sized to this brief (a one-file fix: --no-ui --no-dx --max-rounds 1 --estimate-usd <n>
-   --spend-cap <small>). At the gate send me the output of
+   sized to this brief (a fix: --no-ui --no-dx --max-rounds 1 --estimate-usd <n>
+   --spend-cap <small>, then close the CEO phase before dispatching its voices with
+   gstack-autoplan close --out <run dir> --phase ceo --deferred "eng-only fix plan").
+   At the gate send me the output of
    gstack-owner-brief render --captain --out <run dir> whole, as a needs-you report.
    Build nothing yet.
 2. Build after the word. I bring the owner's exact words back. Answer them into the run

test/captain-skill.test.ts

@@ -89,6 +89,7 @@ describe('/captain skill', () => {
       expect(text, rel).toContain('one-round, eng-only plan');
     }
     expect(read('docs/captain.md')).toContain('gstack-autoplan close --out <run dir> --phase ceo --deferred');
+    expect(read('captain/templates/brief.md').replace(/\s+/g, ' ')).toContain('gstack-autoplan close --out <run dir> --phase ceo --deferred');
   });
 
   test('is generic: parameters, not one crew\'s codes, names or repository', () => {