diff --git a/CONTEXT.md b/CONTEXT.md
index d68db48..8269ee9 100644
--- a/CONTEXT.md
+++ b/CONTEXT.md
@@ -41,6 +41,15 @@ Campaign 12 tried it.
    section keys are decoded by `hostHalfShape` / `appHalfShape`, and those are allow-lists that
    already silently swallowed `offsite_restic` for months (R-122). The sections are checked.
 
+5. **A NEW GATE MUST BE CHECKED IN BOTH AUTOMATED HOMES.** The pre-push hook runs on a workstation
+   where every sibling repo is a real clone; CI checks out ONE repo, shallow. A gate needing a
+   sibling therefore passes locally and exits 2 INCONCLUSIVE in CI — measured here, three red runs
+   before it was right. Give the gate what it needs in `.gitea/workflows/gates.yml`; **never let it
+   skip when a sibling is absent**, which is the fail-open shape and leaves it running in neither
+   home (R-29). And **a gate must not shell out to a tool the CI image may not have**: this one used
+   `grep --include`, which the runner's grep does not support, and read the empty output as a
+   finding — convicting all 174 tags. Pure-Python searching now.
+
 **Scenario F's choice, and why (the same ruling's second half).** When the receiving side gains a
 field, the absence of that field from an older emitter must not read as a value. `operator_key_configured`
 decodes as a **pointer**: nil means the agent never said, and is reported **distinctly** from a
diff --git a/REPORT-wire-contract-gate.md b/REPORT-wire-contract-gate.md
index 531bae9..99e2562 100644
--- a/REPORT-wire-contract-gate.md
+++ b/REPORT-wire-contract-gate.md
@@ -76,12 +76,36 @@ turned out blind to one of the three shapes it was written for:
 `--selftest` plants an unreachable tag on a real root in a throwaway copy and asserts conviction:
 **exit 1, planted tag named**; unplanted tree **exit 0**.
 
-**Two instrument defects the CONTROL caught before the gate was trusted:**
+**THREE instrument defects this gate's own controls caught before it was trusted.** None was found
+by review; each was found by making the gate prove something.
 
 1. **A substring false negative** — `grep -F healed_at` also matched `privsep_healed_at`. R-260 named
-   `healed_at`, so its absence from the output was the tell. Now a whole-token regex; 40 not 39.
+   `healed_at`, so its absence from the output was the tell. Whole-token now; 40, not 39.
 2. **`dr_recipe` is not wholly opaque** — its top-level section keys ARE decoded, through allow-lists
    that already swallowed `offsite_restic` for months (R-122). Now opaque only **below depth 1**.
+3. **The search shelled out to `grep` and read its failure as a finding.** CI convicted **all 174**
+   checked tags while the pre-push hook was green. The CI runner's image carries python3 and git and
+   deliberately little else, and its `grep` does not support `--include`, so stdout was empty and
+   empty was read as "absent". **A gate that silently turns a tool failure into a finding is worse
+   than no gate**, and its green would have been as untrustworthy as its red. Removed the dependency
+   rather than working around it: the search is pure Python now, one token index per receiving repo.
+
+**The BEFORE capture was RE-VERIFIED, not re-generated** — the stronger claim. All 40 recorded fields
+were re-tested against the new implementation: **agree=40, disagree=0**, i.e. exactly the four this
+session fixed are now present and the other 36 still absent. The number stands under both
+implementations.
+
+**And the reusable half, which is about the gates and not about this gate.** The pre-push hook runs on
+a workstation where every sibling repo is a real clone; CI checks out one repo, shallow. **A gate
+that needs a sibling passes locally and is INCONCLUSIVE in CI — the two automated homes are not
+interchangeable, and a new gate must be checked in BOTH.** The workflow's own alarm mail says a
+hook-versus-CI disagreement "outranks whatever the push was for"; it did. Fixed by fetching the agent
+clone in CI (`.gitea/workflows/gates.yml`), never by letting the gate skip when a sibling is absent —
+that is the fail-open shape and would leave it running in neither home (R-29).
+
+**Cost, stated plainly:** three CI runs went red (260, 261, 262) and each sent the operator an alarm
+mail before run **263** went green. The alarm working is the system behaving correctly; the noise was
+mine.
 
 ## 6. What `oobDegraded` says when it fails