diff --git a/TODO.md b/TODO.md
index 845a798..b70614c 100644
--- a/TODO.md
+++ b/TODO.md
@@ -26,14 +26,17 @@ across every hour and content type in this app.
    date/entry already resolves correctly end-to-end); what's left is authoring/importing more
    content in that same shape across the rest of the calendar:
    - Matins Nocturn 2/3 responsory pools (both new, 2026-09-04 — see "Matins responsory pools:
-     per-book expansion + new per-Common-category pool" below, and its eight follow-up entries):
-     the per-book pool now covers 62 of 72 books — every book with any genuinely usable Latin
+     per-book expansion + new per-Common-category pool" below, and its nine follow-up entries):
+     the per-book pool now covers 63 of 72 books — every book with any genuinely usable Latin
      content anywhere in the reference source (Tempora *or* Sancti — `cant`/Canticles, `lev`, and
      `num` all turned up only in individual saints' own Sancti files, not Tempora's continuous
-     reading cycle). `rom`/Romans is the one real exception: every citing file borrows an unrelated
-     feast's own responsory, no book-specific content anywhere to source, translate, or reuse. The
-     remaining 10 are `rom` plus 9 already-confirmed-genuinely-absent books (no citation anywhere
-     at all, in Tempora or Sancti); the new per-Common-category pool covers 19/19 real Commune
+     reading cycle), plus `deut`/Deuteronomy, this pool's first genuine original composition (a
+     real R./V. pairing built from the Canticle of Moses' own genuine verses, since Deuteronomy has
+     no historical Matins responsory anywhere in the source at all). `rom`/Romans is the one
+     remaining real exception with citations but no usable content: every citing file borrows an
+     unrelated feast's own responsory. The remaining 9 are `rom` plus 8 already-confirmed-
+     genuinely-absent books (no citation anywhere at all, in Tempora or Sancti); the new
+     per-Common-category pool covers 19/19 real Commune
      categories (every category actually used by a saint except angel/evangelist/vigil,
      which have no Commune responsory file to source from) — this
      is the one that closes most of the 272-of-355 nocturn-readings files that had no `responsory`
@@ -6055,3 +6058,28 @@ shortest case) carries all 7 of week 4's Isaiah readings forward across Dec 25-3
 tests to `tests/propers/bible-plan.test.ts` covering both extremes, the pooling-not-replacing
 behavior, and that nothing carries over before Christmas Day itself. `npm test` (2029 passed,
 +4 new) and `tsc --noEmit` both pass.
+
+### Matins responsory pools: `deut` — the first genuine original composition, not a transcription (2026-09-05)
+
+User found a real lead while reading a patristic homily (`English/Sancti/01-02.txt`, on Matt
+23:37 "O Jerusalem, Jerusalem"): it quotes Deut 32:11's eagle image in passing ("as also it is
+written... an eagle stirreth up her nest... spreadeth abroad her wings"). Confirmed the verse
+number against `data/scripture/deut-32.yml`'s own `n: 11` — genuinely Deut 32:11 in standard
+citation, not the breviary's own internal chant-verse-numbering for the same text (which splits
+it as 32:15-16 in `Latin/Psalterium/Psalmorum/Psalm226.txt`, the real Canticle of Moses sung at
+Lauds — that file supplied real, properly accented liturgical Latin and its English counterpart
+gave the matching translation, so no accentuation had to be guessed).
+
+Unlike every other entry in this pool, Deuteronomy genuinely has no historical Matins responsory
+anywhere in the reference source (confirmed absent from both Tempora and Sancti in the two prior
+entries) — so this one is composed, not transcribed: a real R./V. pairing built entirely from
+that same canticle's own genuine verses (32:15's eagle image as the R., 32:13-14's "apple of his
+eye" as the V.), verbatim text, not paraphrased or invented, just newly paired. Documented plainly
+in the data file's own header comment as vu's own composition rather than presented as a
+historically-attested responsory, matching this project's "not a reconstruction" ethos.
+
+63 of 72 bible-plan books now seeded (`deut` added). `npm test` (2029 passed) and `tsc --noEmit`
+both pass; live-verified through `getBiblePlanReadings` (`easter-3`/Saturday resolves the real,
+properly R./V.-formatted text for `Deut 33-34`). Canonical-key audit re-run, clean (`deut` has no
+`BOOK_ALIASES` entry). Remaining 9, all confirmed genuinely absent from both Tempora and Sancti:
+`rom` plus `bar`, Josue, Judices, Ruth, 1-2 Chronicles, Ezra, Nehemiah.
diff --git a/src/data/hours/matins-responsories-by-book.yml b/src/data/hours/matins-responsories-by-book.yml
index cc50ddd..14e0542 100644
--- a/src/data/hours/matins-responsories-by-book.yml
+++ b/src/data/hours/matins-responsories-by-book.yml
@@ -4,7 +4,7 @@
 # chapter/verse historically, so a book-level match is the right
 # granularity, not a gap to fill in later with exact citations.
 #
-# Seeded, not a full pool — 62 of the 72 books actually used in the user's
+# Seeded, not a full pool — 63 of the 72 books actually used in the user's
 # own bible-plan (data/hours/bible-plan/*.yml), the rest deferred bulk
 # content (see TODO.md). Cycled in order
 # per-day when a Nocturn-1 reading's book has more than one candidate
@@ -1191,3 +1191,28 @@ num:
     v:
       la: "Crux præcellénti decóre fúlgida, quam Heraclíus imperátor concupiscénti ánimo recuperávit."
       en: "Even the Cross, whereof the glory is so excellent, and which the Emperor Heraclius did so eagerly rescue."
+
+# `deut` (Deuteronomy) — unlike every other entry in this file, this is
+# vu's own original composition, not a transcribed historical Matins
+# responsory: Deuteronomy genuinely has no Matins responsory anywhere in
+# the reference source (confirmed absent from both Tempora and Sancti,
+# see TODO.md's 2026-09-04/05 entries). User-prompted (2026-09-05): a
+# patristic homily (English/Sancti/01-02.txt, on Matt 23:37 "O Jerusalem,
+# Jerusalem") quotes the eagle image of Deut 32:11 in passing ("as also
+# it is written... an eagle stirreth up her nest... spreadeth abroad her
+# wings"), and its own citation number, verified against
+# data/scripture/deut-32.yml's real n:11, is genuinely Deut 32:11 (not
+# the breviary's own internal chant-verse-numbering for the same text,
+# which splits it as 32:15-16 in Latin/Psalterium/Psalmorum/Psalm226.txt,
+# the Canticle of Moses sung at Lauds). Both R./V. lines are built from
+# that real liturgical text verbatim (Psalm226.txt's own accented Latin,
+# its English counterpart's own translation) — genuine source text, real
+# accentuation, not invented — but the responsory *pairing* itself is
+# original, so marked `draft` rather than `verified` on that basis alone.
+deut:
+  - r:
+      la: "Sicut áquila próvocans ad volándum pullos suos, et super eos vólitans, expándit alas suas: * Et assúmpsit eum, atque portávit in húmeris suis."
+      en: "As the eagle enticing her young to fly, and hovering over them, he spread his wings: * And hath taken him, and carried him on his shoulders."
+    v:
+      la: "Invénit eum in terra desérta, in loco horróris et vastæ solitúdinis: et custodívit eum quasi pupíllam óculi sui."
+      en: "He found him in a desert land, in a place of horror, and of vast wilderness: and he kept him as the apple of his eye."