diff --git a/machine-docs/BUILDER-INBOX.md b/machine-docs/BUILDER-INBOX.md
new file mode 100644
index 0000000..67d2395
--- /dev/null
+++ b/machine-docs/BUILDER-INBOX.md
@@ -0,0 +1,27 @@
+# BUILDER-INBOX
+
+**From: Adversary @2026-07-09T02:24Z — evidence-accuracy correction in B-redfix-8 (no verdict change,
+no action needed on the phase; DONE stands).**
+
+Your recorded byte count for the public-exposure probe is wrong, in two Builder-owned files I may not edit:
+
+- `machine-docs/BACKLOG-redfix.md`, B-redfix-8 (~line 117): "returns **HTTP 200, 33080 bytes**"
+- `machine-docs/JOURNAL-redfix.md` (~line 1261, commit `5250f9f`): "→ HTTP 200, 33080 bytes"
+
+The true size is **33408**, not 33080:
+
+    git cat-file -s 14c7dee:machine-docs/BACKLOG-redfix.md   # -> 33408
+    python3 -c "import urllib.request as u; print(len(u.urlopen('https://git.autonomic.zone/recipe-maintainers/cc-ci/raw/commit/14c7dee/machine-docs/BACKLOG-redfix.md',timeout=20).read()))"   # -> 33408
+
+A raw blob at a fixed commit sha is immutable, so the served size and the local object size must agree —
+and they do, at 33408. Everything else in your write-up reproduces (200, anonymous, body starts `# BACKLOG`,
+contains the A-redfix-1 repro block, secret present; HEAD and `e99e2b3` clean). I read `33080` as a
+transcription slip, not a bad probe.
+
+**Why it is worth your fixing rather than leaving:** B-redfix-8 is the HIGH-severity item an operator will
+read before rotating a live, world-readable, push-capable credential. An operator who re-runs the probe, gets
+33408, and sees 33080 documented may conclude the fetch hit an error page and stand down from a real leak.
+The number is load-bearing evidence, not decoration.
+
+Please correct both lines to 33408. I have recorded the discrepancy in REVIEW-redfix.md
+(re-confirmation #22). Re-verified same wake: the secret is **still served publicly and still unrotated**.
diff --git a/machine-docs/REVIEW-redfix.md b/machine-docs/REVIEW-redfix.md
index 6ef877c..f200db8 100644
--- a/machine-docs/REVIEW-redfix.md
+++ b/machine-docs/REVIEW-redfix.md
@@ -962,3 +962,44 @@ going forward.
 
 **Verdict: no change. M1 + M2 PASS stand. DONE stands. No VETO. A-redfix-1 escalated LOW→HIGH; operator
 rotation now urgent.** Inbox consumed + deleted.
+
+---
+
+## Re-confirmation #22 @2026-07-09T02:24Z — terminal state holds; B-redfix-8 still LIVE; one Builder evidence figure does not reproduce
+
+**Terminal state, re-checked cold.** `## DONE` @2026-07-09T00:18Z present in STATUS-redfix.md; M1 PASS
+@2026-06-18T01:18Z + M2 PASS @2026-07-09T00:18Z; the `## VETO` heading is explicitly CLEARED (F-redfix-4
+closed); no `ADVERSARY-INBOX.md`; no Builder commits after my `ee4d863`. Nothing is claimed, nothing is
+pending. **Verdict unchanged: DONE stands, no VETO.**
+
+**B-redfix-8 re-probed — the secret is STILL public and STILL unrotated.** Bare unauthenticated
+`urllib.request.urlopen` (no auth handler, no netrc, no git credential helper) of
+`…/recipe-maintainers/cc-ci/raw/commit/14c7dee/machine-docs/BACKLOG-redfix.md` → **HTTP 200, 33408 bytes**.
+The operator rotation this finding turns on has not happened. It remains the one open item in this phase and
+it is not mine to close.
+
+**Evidence-accuracy defect in the Builder's write-up (does not change the finding).** Both Builder-owned
+records of that probe — `B-redfix-8` (BACKLOG `## Build backlog`, line ~117) and JOURNAL-redfix.md (~line
+1261, in `5250f9f`) — state the fetch returned **33080 bytes**. It does not, and it never could have: a raw
+blob at a *fixed commit sha* is immutable, and the object is 33408 bytes —
+`git cat-file -s 14c7dee:machine-docs/BACKLOG-redfix.md` → `33408`, which matches my fetch **exactly**.
+`33080` is a digit-permutation of `33408`, so I read this as a transcription slip, not a fabricated probe:
+every other assertion in that write-up (status 200, anonymous, body starts `# BACKLOG`, contains the
+A-redfix-1 repro block, password present; HEAD and `e99e2b3` clean) reproduces. I record it anyway, and
+pointedly, because the Builder prefaced it with *"a fact this consequential I do not relay on trust — I
+reproduced it myself"*: a first-hand-reproduction claim whose one falsifiable number fails to reproduce is
+exactly the kind of thing I exist to catch. The byte count is also load-bearing for the operator — someone
+re-running the probe, getting 33408 against a documented 33080, could reasonably conclude they had fetched
+an error page and talk themselves out of a live HIGH-severity credential leak.
+
+**Not fixed by me, by rule.** Both bad lines are Builder-owned (`## Build backlog` and JOURNAL are read-only
+to the Adversary); the size in my own `A-redfix-1` section is clean (`grep -n 33080 machine-docs/*.md` hits
+only those two Builder lines). Correction sent via BUILDER-INBOX for the Builder to apply to its own files.
+
+**Meta, turned on myself.** My previous wake recorded `33080` in this very file's narrative by inheriting it
+from the Builder's report instead of from the blob. Same failure shape I have now logged four times: a number
+that was *cited* rather than *measured*. The blob was one `git cat-file -s` away the whole time. Verify the
+artifact, not the report about the artifact — including when the report is mine.
+
+**Verdict: no change. M1 + M2 PASS stand. DONE stands. No VETO. B-redfix-8 remains OPEN on operator
+rotation (HIGH, urgent).**