diff --git a/conductor/tracks/fable_review_20260617/report.md b/conductor/tracks/fable_review_20260617/report.md
index 413e1e53..33264976 100644
--- a/conductor/tracks/fable_review_20260617/report.md
+++ b/conductor/tracks/fable_review_20260617/report.md
@@ -1544,7 +1544,82 @@ A Fable pattern is **Persona Performance** if it is constraint dressing — a di
 
 *Source: all clusters; see also `decisions.md`*
 
-*[FILL IN: ~200 lines. 15-20 concrete recommendations.]*
+### What this section is
+
+This section consolidates the 15-20 concrete recommendations for the user's deferred nagent-rebuild (1-2 weeks out per user 2026-06-17). The recommendations are the actionable distillation of the per-cluster synthesis (§3-§12) and the summary sections (§13-§15). The full per-entry details are in `decisions.md` (15-20 entries, ~500 lines); this section provides the user-facing summary.
+
+### Recommendation distribution
+
+- **8 adoptions** (the "Genuinely Useful" patterns from §13)
+- **9 explicit rejections** (the "Anti-User Watchdog" patterns from §14)
+- **0 persona performance actions** (the §15 patterns are "None" — ignore, not adopt or reject)
+
+### The 8 adoptions (from §13)
+
+| # | Recommendation | Manual Slop destination | Priority |
+|---|---|---|---|
+| 1 | Search-default for current-state queries | `rag_integration_discipline.md` | Medium |
+| 2 | Default to prose, use lists only when asked | `product-guidelines.md §Compact Style` | Medium |
+| 3 | No gratitude performance | `.opencode/agents/tier*.md` | Low |
+| 4 | File-presence check before editing | `edit_workflow.md` | Low |
+| 5 | Data-discipline rule: data, not recommendations | `data_oriented_design.md` | Medium |
+| 6 | "Owns the mistake" pattern (already implemented) | (already in `AGENTS.md`) | N/A |
+| 7 | No-overconfident-claims rule | `rag_integration_discipline.md` | Medium |
+| 8 | Hierarchical-keys for knowledge files | `knowledge_artifacts.md` | Medium |
+
+### The 9 explicit rejections (from §14)
+
+| # | Rejection | Manual Slop destination | Priority |
+|---|---|---|---|
+| 1 | Mental-health watch-dogging | `AGENTS.md §"Critical Anti-Patterns"` | High |
+| 2 | Soft-watchdog framing | `AGENTS.md §"Critical Anti-Patterns"` | High |
+| 3 | Anti-detection-design | `AGENTS.md §"Critical Anti-Patterns"` | High |
+| 4 | Model-deserves-respect | `AGENTS.md §"Critical Anti-Patterns"` | High |
+| 5 | Model-has-wants | `AGENTS.md §"Critical Anti-Patterns"` | High |
+| 6 | Model-has-concerns | `AGENTS.md §"Critical Anti-Patterns"` | High |
+| 7 | Model-deserves-dignity | `AGENTS.md §"Critical Anti-Patterns"` | High |
+| 8 | Conversational-tone persona (already rejected) | (already in `.opencode/agents/tier*.md`) | N/A |
+| 9 | Stereotype wariness | `AGENTS.md §"Critical Anti-Patterns"` | Medium |
+
+### Implementation order (suggested)
+
+1. **High-priority rejections first** (rejections 1-7). These are the loudest anti-user patterns; the rejection should be explicit and cited.
+2. **Medium-priority adoptions** (adoptions 1, 2, 5, 7, 8). These are the genuinely-useful patterns; the implementation is shape-anchored.
+3. **Low-priority adoptions** (adoptions 3, 4). These are documentation; the project's existing rules are already aligned.
+4. **N/A items** (adoptions 6, rejections 8). These are already implemented; the Fable citation is documentation.
+
+### The actionable rule (one sentence)
+
+Adopt the Useful patterns (epistemic + memory + workflow; ~7 of 10 clusters), explicitly reject the Anti-User patterns (~5 of 10 clusters), and ignore the Persona Performance patterns (~4 of 10 clusters).
+
+### Cross-references
+
+- `decisions.md`: the 15-20 concrete entries with per-entry rationale, source evidence, and suggested destination.
+- `nagent_takeaways_fable_20260617.md`: the 17th nagent takeaway that crystallizes the actionable rule.
+- `report.md §13, §14, §15`: the useful / anti-user / persona summary sections.
+
+### What the deferred rebuild is NOT
+
+- The deferred rebuild is NOT a re-architecture of Manual Slop. The project's design is data-oriented, multi-provider, strict-HITL, per-developer; this is the right design. The rebuild is a *tactical* update of the agent-directive corpus.
+- The deferred rebuild is NOT a replacement of the 4 memory dimensions, the RAG discipline, the data-oriented error handling convention, or any of the project's foundational patterns. These are the project's existing design; the rebuild adds the Fable-derived recommendations on top.
+- The deferred rebuild is NOT a Tier 1 Orchestrator, Tier 2 Tech Lead, Tier 3 Worker, or Tier 4 QA re-design. The 4-tier MMA is the project's design; the rebuild does not touch it.
+
+### What the deferred rebuild IS
+
+- A documentation update: add 8 new sections to 5 existing styleguides + 1 explicit "do not adopt" list to `AGENTS.md §"Critical Anti-Patterns"`.
+- A 1-2 week effort: the user can complete the documentation update in a few hours of writing; the audit-script updates (if any) take longer. The 8 adoptions + 9 rejections = 17 new content sections.
+- A Fable-cited update: every new section cites Fable line numbers as the explicit source. The "the user asked for this" provenance is explicit.
+
+### The full per-entry list
+
+See `decisions.md` for the 15-20 concrete entries. Each entry has:
+- **Source evidence:** cluster file:line + Fable line number.
+- **Rationale:** why the recommendation is Useful or Anti-User.
+- **Suggested Manual Slop destination:** a specific file path.
+- **Priority:** High / Medium / Low / N/A.
+- **Verdict category:** Useful / Anti-User / Persona.
+
+The deferred rebuild is the user's next step. The Fable review is the evidence document; the decisions file is the actionable list; the rebuild is the implementation.
 
 ---