docs: add tool-integration checklist + stop hardcoding roster counts (#663)

Two related drift traps, both from hand-typed numbers/lists that no guard
watches:

1. CONTRIBUTING had no "how to add a tool" checklist, and its wording
   ("all output is gitignored") implied gitignoring was automatic — so
   tool contributors kept committing generated integrations/<tool>/ output.
2. The division set and agent/division counts were hardcoded in prose in
   several places and had already gone stale (CONTRIBUTING said "16" and
   omitted healthcare; EXECUTIVE-BRIEF said "9 divisions").

Changes:
- Add an "Adding a Tool Integration" checklist to CONTRIBUTING (discuss-first,
  reuse an existing `format`, the ~5-file touch list incl. the required
  .gitignore rule, run check-tools.sh). Harmonize the "committed build
  output" policy line to point at it.
- De-hardcode the division list in CONTRIBUTING — defer to divisions.json.
- Stop scattering roster counts: strategy/EXECUTIVE-BRIEF ("9 divisions") and
  check-agent-originality.sh ("184-agent library") drop the number entirely;
  README keeps a showcase stat but softens "232 across 16" to "230+ across
  every division" so it never becomes a lie as the roster grows.


Claude-Session: https://claude.ai/code/session_01WKnDRWM4izsB8WAXKszhsq

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

scripts/check-agent-originality.sh

@@ -23,7 +23,7 @@
 #   ORIGINALITY_FAIL   default 40  — at/above this %, treated as a duplicate (exit 1)
 #   ORIGINALITY_WARN   default 20  — at/above this %, surfaced as a warning (no fail)
 #
-# Calibration: across the existing 184-agent library the worst same-pair
+# Calibration: across the existing agent library the worst same-pair
 # similarity is ~1.5% (median 0%). Anything in the double digits is a strong
 # anomaly; the defaults leave a wide safety margin against false positives.