diff --git a/chat/runtime.py b/chat/runtime.py
index 777b8d42..fe4692c1 100644
--- a/chat/runtime.py
+++ b/chat/runtime.py
@@ -38,6 +38,7 @@ from core.epistemic_state import (
     epistemic_state_for_grounding_source,
     normative_detail_from_verdicts,
 )
+from core.proposal_review.summary import ProposalReviewIdleSummary, idle_summary
 from core.response_governance import govern_response, shape_surface
 from chat.telemetry import (
     TurnEventSink,
@@ -534,7 +535,9 @@ class IdleTickResult:
     The proposal pass is PROPOSAL-ONLY learning, never ratification (HITL ratifies). The
     Step D consolidation pass is SESSION-memory learning: ``facts_consolidated`` derived
     facts were written back into the held self so the next ``determine`` reaches them
-    directly — still never corpus mutation, never a proposal.
+    directly — still never corpus mutation, never a proposal.  The proposal-review sub-pass
+    (``proposal_review``) is READ-ONLY: it surfaces pending comprehension-failure proposals for
+    review and mutates nothing.
     """
 
     candidates_contemplated: int
@@ -543,6 +546,9 @@ class IdleTickResult:
     #: Step D — derived facts consolidated into the held self this tick (0 unless
     #: ``config.consolidate_determinations`` and the closure had a new layer to add).
     facts_consolidated: int = 0
+    #: IT — read-only proposal-review summary (None unless ``config.review_pending_proposals``).
+    #: Surfaces pending comprehension-failure proposals for review; mutates nothing.
+    proposal_review: ProposalReviewIdleSummary | None = None
 
 
 class ChatRuntime:
@@ -919,6 +925,21 @@ class ChatRuntime:
             facts_consolidated = consolidate_once(self._context).consolidated
             did_work = True
 
+        # 3. Proposal-review sub-pass (IT) — READ-ONLY. Surfaces pending comprehension-failure
+        #    proposals (the contemplation pass's N5 artifacts) for review. It NEVER mutates an
+        #    artifact, NEVER sets ``did_work`` (no state change → no checkpoint), NEVER ratifies
+        #    or mounts. A reporter failure is CAPTURED, not propagated, so it cannot corrupt the
+        #    tick. Gated off by default.
+        proposal_review = None
+        if self.config.review_pending_proposals:
+            try:
+                proposal_review = idle_summary()
+            except Exception as exc:  # noqa: BLE001 — a reporter failure must not corrupt the tick
+                proposal_review = ProposalReviewIdleSummary(
+                    safe=False, total=0, review_needed=0, malformed=0, by_family=(),
+                    errors=(f"proposal_review_failed:{type(exc).__name__}",),
+                )
+
         # Persist the advanced state once (backlog + lineage +, with
         # persist_session_state, the consolidated facts). Skipped on a no-op tick so an
         # idle engine with nothing to learn does not churn the checkpoint.
@@ -929,6 +950,7 @@ class ChatRuntime:
             proposals_created=created,
             pending_proposals=self._count_pending_proposals(),
             facts_consolidated=facts_consolidated,
+            proposal_review=proposal_review,
         )
 
     def record_recognition_example(
diff --git a/core/config.py b/core/config.py
index 30b57b41..17190a87 100644
--- a/core/config.py
+++ b/core/config.py
@@ -316,6 +316,13 @@ class RuntimeConfig:
     # same _SUBSUMPTION_SUBSET_FACT_BUDGET; converges (a saturated tick is a no-op).
     consolidate_determinations: bool = False
 
+    # IT (proposal-review surface) — when on, idle_tick runs a READ-ONLY sub-pass that scans
+    # the comprehension-failure proposal sink and surfaces a summary in
+    # IdleTickResult.proposal_review. It NEVER mutates an artifact, sets did_work, checkpoints,
+    # ratifies, mounts, or modifies readers; a reporter failure is captured, not propagated.
+    # OFF by default — idle ticks don't pay for the scan unless a deployment wants the surface.
+    review_pending_proposals: bool = False
+
     # Step E (ESTIMATION) — when on, a converse query the engine would otherwise REFUSE
     # (told p(a,b), asked p(b,a)) may be answered with a DISCLOSED [approximate] estimate
     # IF the predicate-class has earned the SERVE license on the ratified, committed
diff --git a/docs/runtime_contracts.md b/docs/runtime_contracts.md
index 01b7922f..6614548a 100644
--- a/docs/runtime_contracts.md
+++ b/docs/runtime_contracts.md
@@ -110,6 +110,26 @@ Contract:
   `algebra/versor.py` keeps closure.  Off by default; the falsification lane is
   `evals.determination_closure`.
 
+### Idle proposal review (read-only)
+
+When `review_pending_proposals` is enabled, `ChatRuntime.idle_tick` runs a **read-only**
+sub-pass (after the consolidation pass) that scans the comprehension-failure proposal sink
+(`teaching/proposals/comprehension_failures/`, the contemplation pass's proposal-only
+artifacts) and surfaces a summary in `IdleTickResult.proposal_review` (`safe`, `total`,
+`review_needed`, `malformed`, `by_family`, `errors`).
+
+Contract:
+
+- **Read-only, no mutation.**  The sub-pass scans, reports, and dry-checks; it writes, moves,
+  and deletes nothing.  It does **not** set `did_work`, so it never triggers a checkpoint, and
+  it never advances learning, ratifies, mounts, or modifies a reader.
+- **Failure-isolated.**  A reporter exception is **captured, not propagated** — surfaced as
+  `proposal_review.safe == False` with `errors == ("proposal_review_failed:<type>",)` — so a
+  malformed sink or filesystem error can never corrupt the idle tick's state or return.
+- **Default off, additive.**  Disabled, `proposal_review` is `None` and `IdleTickResult` is
+  unchanged for existing callers.  This is **not** a second idle loop and **not** the L10
+  always-on heartbeat — it only surfaces existing review obligations.
+
 ### Estimation surface (Step E — ESTIMATION)
 
 When `estimation_enabled` and a turn is a **converse query** DETERMINE refused (told
diff --git a/tests/test_idle_proposal_review.py b/tests/test_idle_proposal_review.py
new file mode 100644
index 00000000..14b18652
--- /dev/null
+++ b/tests/test_idle_proposal_review.py
@@ -0,0 +1,70 @@
+"""Contract tests for the read-only proposal-review sub-pass of idle_tick (IT-b).
+
+Pins the runtime contract: default-off preserves the existing IdleTickResult shape/behavior;
+enabled surfaces a summary; a reporter exception is CAPTURED (safe=False) and never corrupts
+the tick; the read-only sub-pass never sets did_work / checkpoints / mutates / creates proposals.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import chat.runtime as rtmod
+from chat.runtime import ChatRuntime
+from core.config import RuntimeConfig
+from core.proposal_review.summary import ProposalReviewIdleSummary
+
+_OK = ProposalReviewIdleSummary(safe=True, total=0, review_needed=0, malformed=0, by_family=())
+
+
+def _rt(tmp_path: Path, *, review: bool = False) -> ChatRuntime:
+    return ChatRuntime(
+        config=RuntimeConfig(review_pending_proposals=review), engine_state_path=tmp_path
+    )
+
+
+def test_default_off_proposal_review_is_none(tmp_path: Path) -> None:
+    result = _rt(tmp_path).idle_tick()
+    assert result.proposal_review is None  # additive field absent for existing callers
+    assert result.candidates_contemplated == 0 and result.proposals_created == 0
+
+
+def test_enabled_surfaces_the_summary(tmp_path: Path, monkeypatch) -> None:
+    sentinel = ProposalReviewIdleSummary(
+        safe=True, total=3, review_needed=3, malformed=0, by_family=(("missing_total_count", 3),)
+    )
+    monkeypatch.setattr(rtmod, "idle_summary", lambda *a, **k: sentinel)
+    assert _rt(tmp_path, review=True).idle_tick().proposal_review == sentinel
+
+
+def test_reporter_exception_is_captured_not_propagated(tmp_path: Path, monkeypatch) -> None:
+    def _boom(*a, **k):
+        raise ValueError("sink exploded")
+
+    monkeypatch.setattr(rtmod, "idle_summary", _boom)
+    result = _rt(tmp_path, review=True).idle_tick()  # must NOT raise
+    assert result.proposal_review is not None
+    assert result.proposal_review.safe is False
+    assert result.proposal_review.errors == ("proposal_review_failed:ValueError",)
+    assert result.candidates_contemplated == 0 and result.proposals_created == 0  # tick intact
+
+
+def test_review_subpass_does_not_checkpoint_or_set_did_work(tmp_path: Path, monkeypatch) -> None:
+    rt = _rt(tmp_path, review=True)
+    calls: list[int] = []
+    monkeypatch.setattr(rt, "checkpoint_engine_state", lambda: calls.append(1))
+    monkeypatch.setattr(rtmod, "idle_summary", lambda *a, **k: _OK)
+    result = rt.idle_tick()
+    assert result.proposal_review is not None  # the review ran
+    assert calls == []  # ...but a read-only review never checkpoints (no did_work)
+
+
+def test_enabled_does_not_perturb_other_passes(tmp_path: Path, monkeypatch) -> None:
+    monkeypatch.setattr(rtmod, "idle_summary", lambda *a, **k: _OK)
+    on = _rt(tmp_path, review=True).idle_tick()
+    off = _rt(tmp_path).idle_tick()
+    assert (on.candidates_contemplated, on.proposals_created, on.facts_consolidated) == (
+        off.candidates_contemplated,
+        off.proposals_created,
+        off.facts_consolidated,
+    )