[Docs] Update the squad from Squad-Spec-Repository-Template

.claude/skills/squad-issue/SKILL.md

@@ -188,9 +188,8 @@ every Git and GitHub action yourself, including follow-up issues the Lead decide
     notifications or mark them `--unreported`, and run it again; exit code 4 names commits after the PR that
     no step-11 review row follows — run their delta review (step 11), or log a verbatim fix as such, and run it
     again. Append the tables exactly as printed (a run
-    without them is not wrapped up) to the comment under "Squad run metrics". Ask the user for the output of
-    `/usage` for this session (you cannot run it) and add it below the tables under "Session usage (`/usage`)"
-    verbatim, or "not provided" (`.squad/routing.md`, step 12). Report the branch, the PR
+    without them is not wrapped up) to the comment under "Squad run metrics". In a Claude Code session, ask the user for a
+    screenshot of `/usage` (you cannot run it) and add only its numbers (never the image, never personal data) below the tables under "Session usage (`/usage`)" as `.squad/routing.md`, step 12, says. Report the branch, the PR
     URL, the tier, the `squad` issues (or "no lessons"), the metrics tables and any escalation or Lead
     decision to the user.
 

.squad/routing.md

@@ -190,7 +190,7 @@ head; step 10 then only posts the working record, removes `specs/` and marks not
 | 9 | PR approval | Orchestrator, Lead when needed | *PR approval* below; with an *Early draft PR* also green CI, the dry-run result and the Reviewer's round on the same head |
 | 10 | Pull request | Orchestrator | Working record posted as comment (a long `plan.md` may be given as a permalink to the last commit that contains it plus a summary), `specs/<folder>/` removed and `scope-check.py --no-specs` clean, PR opened **as a draft** (*Draft until green*; merged later with *Squash and merge*) — or, after an *Early draft PR*, only the record and the removal |
 | 11 | After the PR | Dev, Code Officer, Reviewer | *Draft until green* holds and the PR is marked ready for review; review comments worked |
-| 12 | Wrap-up | Orchestrator | Squad lessons filed as one issue per destination (*Squad lessons*), or "no lessons" logged; the run metrics of `squad-log.py --summary` (exit 0) appended to the working record exactly as printed and reported to the user, followed by the session's `/usage` output (below the tables, headed "Session usage (`/usage`)"; a built-in command only the user can run, so the orchestrator asks for it at the end of the run, and with no answer writes "not provided") |
+| 12 | Wrap-up | Orchestrator | Squad lessons filed as one issue per destination (*Squad lessons*), or "no lessons" logged; the run metrics of `squad-log.py --summary` (exit 0) appended to the working record exactly as printed and reported to the user, in a Claude Code session only (other agents cannot supply it, and nothing is logged for them), followed by the session's `/usage` panel (below the tables, headed "Session usage (`/usage`)"). Only the user can run it and the numbers exist only on screen, so at the end of the run the orchestrator asks for a screenshot and transcribes what it shows (cost, API time, lines, tokens per model) as shown into a Markdown table, never estimating one. The screenshot itself is never uploaded or attached, and nothing else on it is copied: no account, plan, e-mail, user or machine name, path or other personal data; with no answer it writes "not provided" |
 
 ### PR approval
 

.squad/template.json

@@ -1,6 +1,6 @@
 {
   "repository": "LarsLaskowski/Squad-Spec-Repository-Template",
-  "commit": "10c8e78aa57a4afaa0fec7ca6284617e8ec8b3a9",
+  "commit": "f253db8fb810fb1e31545f6fc7d3630ad76507e1",
   "profile": "dotnet",
   "profiles": [
     "dotnet"