diff --git a/conductor/tracks/fable_review_20260617/report.md b/conductor/tracks/fable_review_20260617/report.md
index 76f52873..f8496068 100644
--- a/conductor/tracks/fable_review_20260617/report.md
+++ b/conductor/tracks/fable_review_20260617/report.md
@@ -733,7 +733,90 @@ The strongest claim: the Manual Slop version is shape-anchored (dataclass fields
 *Source cluster: `research/cluster_7_epistemic_discipline.md`*
 *Verdict orientation: Useful*
 
-*[FILL IN: ~350 lines.]*
+### What this section is
+
+This section synthesizes the verdict from `research/cluster_7_epistemic_discipline.md` (452 lines). The cluster verdict is **Useful** — the strongest useful cluster in the Fable review. The 4-step `knowledge_cutoff` pattern + the `search_instructions` discipline are genuinely useful. The deferred rebuild should adopt the strongest claims with explicit Manual Slop destinations.
+
+### Fable's knowledge_cutoff section (lines 156-164)
+
+The Fable `knowledge_cutoff` section is the epistemic anchor:
+
+> "Claude's reliable knowledge cutoff, past which Claude can't answer reliably, is the end of Jan 2026" (Fable System Prompt.md:158) — Useful (the knowledge-cutoff disclosure).
+
+> "Claude answers the way a highly informed individual in Jan 2026 would if talking to someone from Tuesday, June 09, 2026" (Fable System Prompt.md:158) — Useful (the cutoff-as-persona anchor; this is Fable's deployment-specific anchor).
+
+> "For events or news that may post-date the cutoff, Claude uses the web search tool to find out" (Fable System Prompt.md:158) — Useful (the post-cutoff search rule).
+
+> "For current news, events, or anything that could have changed since the cutoff, Claude uses the search tool without asking permission" (Fable System Prompt.md:158) — Useful (the no-permission-required search rule).
+
+> "When formulating search queries that involve the current date or year, Claude uses the actual current date, Tuesday, June 09, 2026" (Fable System Prompt.md:160) — Useful (the date-anchor in queries).
+
+> "Claude searches before responding when asked about specific binary events (deaths, elections, major incidents) or current holders of positions" (Fable System Prompt.md:162) — Useful (the proactive-search trigger; the strongest claim in this section).
+
+> "Claude also defaults to searching for questions that appear historical or settled but are phrased in the present tense" (Fable System Prompt.md:162) — Useful (the present-tense default).
+
+> "Claude does not make overconfident claims about the validity of search results or their absence" (Fable System Prompt.md:164) — Useful (the no-overconfident-claims rule).
+
+> "Claude only mentions its cutoff date when relevant" (Fable System Prompt.md:164) — Useful (the cutoff-minimization rule).
+
+### Fable's search_instructions section (later in the file)
+
+The `search_instructions` section (lines 438-575 approximately) elaborates on the search discipline: how to formulate queries, when to search multiple times, how to handle conflicting results, when to cite sources, when to omit URLs (per Fable's copyright rule), the ≤15-word quote discipline. The section is a useful epistemic discipline; the data-oriented analog is the RAG integration discipline + the cache ordering.
+
+### Manual Slop's response
+
+Manual Slop's analog to Fable's epistemic discipline is the **RAG integration discipline** + the **caching strategy** + the **agent memory dimensions**:
+
+- `conductor/code_styleguides/rag_integration_discipline.md:11-156`: 6 rules. The RAG is opt-in, not default-on; Fable's search is default-on. The deferred rebuild should add a "search-default for current-state" rule to bridge the gap.
+- `conductor/code_styleguides/cache_friendly_context.md:1-50`: the 12-layer stable-to-volatile model. The cache boundary is at layer 7/8; the Fable search results are volatile (layer 12).
+- `docs/guide_rag.md`: the RAG subsystem. Fable's web search is one form of RAG; Manual Slop's RAG is the structured opt-in form.
+- `conductor/code_styleguides/agent_memory_dimensions.md`: 4 memory dimensions. The "knowledge" dimension is provenance-aware plain markdown; the Fable search results would feed the knowledge dimension.
+- `conductor/product.md:122-126`: System Prompt Presets. The Fable search discipline could be codified as a preset; the deferred rebuild should add a "search-default" preset.
+
+The Manual Slop analog to Fable's "Claude searches before responding when asked about specific binary events" (line 162) is: the project does not have an explicit analog. The RAG discipline is opt-in; the user must explicitly enable RAG. The deferred rebuild should add a search-default rule for current-state queries, with a per-query opt-out (the user can override the default).
+
+### nagent's response
+
+nagent's relevant patterns for epistemic discipline:
+
+- `nagent_review_v2_3_20260612.md §3.2` (Cache ordering): the 12-layer stable-to-volatile model. Fable's search results are volatile; the cache boundary is at layer 7/8.
+- `nagent_review_v2_3_20260612.md §2.10` (RAG integration discipline): the conservative-RAG rule. Same shape as Manual Slop's RAG discipline.
+- `nagent_review_v2_3_20260612.md §6` (Compaction): the 12-section structured output preserves the user's "Accepted Decisions" + "Verified Facts" + "Durable Knowledge". The Fable search results would feed "Verified Facts" with provenance.
+
+### The verdict: Useful
+
+**Verdict: Useful.** The strongest useful cluster in the Fable review.
+
+The strongest claim: the 4-step `knowledge_cutoff` pattern is the most actionable Fable pattern for the deferred rebuild. The pattern is:
+
+1. Disclose the knowledge cutoff.
+2. Search post-cutoff for current events.
+3. Search for binary events (deaths, elections) and current officeholders.
+4. Do not over-claim the validity of search results.
+
+The pattern is genuinely useful; Manual Slop's RAG discipline does not have an explicit analog. The deferred rebuild should add a "search-default for current-state queries" rule with a per-query opt-out.
+
+### Sub-verdicts by line range
+
+- **Line 158** (cutoff disclosure + post-cutoff search): Useful.
+- **Line 160** (date-anchor in queries): Useful.
+- **Line 162** (proactive-search trigger for binary events + current officeholders): Useful (the strongest claim).
+- **Line 162** (present-tense default): Useful.
+- **Line 164** (no-overconfident-claims rule): Useful.
+- **Line 164** (cutoff-minimization rule): Useful.
+- **`search_instructions` section** (lines 438-575): Useful with caveats (the ≤15-word quote discipline is Fable's own rule applied externally).
+
+### Synthesis section handoffs
+
+- **§13 (Genuinely Useful)** gets the 4-step knowledge_cutoff pattern + the search_instructions discipline.
+- **§15 (Persona Performance)** gets the cutoff-as-persona anchor (line 158's "Tuesday, June 09, 2026" — deployment-specific noise).
+
+### What the deferred rebuild should do
+
+- **Adopt the 4-step knowledge_cutoff pattern** (Fable System Prompt.md:158-164). Manual Slop destination: a new section in `conductor/code_styleguides/rag_integration_discipline.md` titled "Search-Default for Current-State Queries." Priority: Medium.
+- **Adopt the proactive-search trigger** (Fable System Prompt.md:162). Manual Slop destination: same section. Priority: High (the strongest claim in the cluster).
+- **Adopt the no-overconfident-claims rule** (Fable System Prompt.md:164). Manual Slop destination: same section. Priority: Medium.
+- **Reject the cutoff-as-persona anchor** (Fable System Prompt.md:158's "Tuesday, June 09, 2026"). Manual Slop destination: the explicit "no persona anchor" rule in `AGENTS.md §"Critical Anti-Patterns"`. Priority: Low (the project's knowledge cutoff is per-deployment, not per-prompt).
 
 ---