diff --git a/conductor/tracks/fable_review_20260617/report.md b/conductor/tracks/fable_review_20260617/report.md
index 90c3fedf..413e1e53 100644
--- a/conductor/tracks/fable_review_20260617/report.md
+++ b/conductor/tracks/fable_review_20260617/report.md
@@ -1399,7 +1399,144 @@ This section distills the "Anti-User Watchdog" patterns from the per-cluster syn
 
 *Source clusters: 1, 4, 5, 8 (branding, tone, mistakes, memory)*
 
-*[FILL IN: ~250 lines. Distillation of the persona performance patterns.]*
+### What this section is
+
+This section distills the "Persona Performance" patterns from the per-cluster synthesis (§3-§12). The source clusters are 1, 4, 5, 8 (branding, tone, mistakes, memory) — the four clusters where Persona Performance is the primary verdict orientation (or a major secondary verdict). The patterns here are *decorative* — they do no useful work, but they are also not actively harmful. The deferred rebuild should *ignore* them, not adopt or reject them.
+
+### What "Persona Performance" means (per §2 framework)
+
+A Fable pattern is **Persona Performance** if it is constraint dressing — a directive the model would execute anyway, or a directive whose only effect is to construct a "model identity" that is irrelevant to the user's task. The pattern is not actively harmful (it is not Anti-User), but it is not load-bearing. The deferred rebuild should not adopt the pattern; the pattern is irrelevant to the rebuild.
+
+### Top persona performance patterns (with rationale)
+
+#### 1. Product branding (cluster 1, Fable System Prompt.md:1-31)
+
+**The pattern.** Fable's `product_information` section is brand-specific noise:
+- "Claude Fable 5, the first model in Anthropic's new Claude 5 family" (line 12)
+- "Claude can direct them to https://www.anthropic.com/news/claude-fable-5-mythos-5" (line 14)
+- "The most recent models are Claude Fable 5, Claude Opus 4.8, Claude Sonnet 4.6" (line 18)
+- "Claude Code, an agentic coding tool... Claude Cowork, an agentic knowledge-work" (line 20)
+
+**Manual Slop destination:** None. The Fable branding content is explicitly out of scope for the rebuild.
+
+**Priority:** N/A (no action needed).
+
+**Why this is persona performance.** Manual Slop supports 5 interchangeable LLM providers (per `conductor/product.md:52`); the project does not brand any of them. The product_information section is decorative for any agent system that is not Anthropic's consumer-facing product. The model's behavior on a real coding task is unchanged with or without the product_information section.
+
+#### 2. Warm-tone persona (cluster 4, Fable System Prompt.md:70)
+
+**The pattern.** Fable's "Claude uses a warm tone, treating people with kindness."
+
+**Manual Slop destination:** Already explicitly rejected in `.opencode/agents/tier*.md` ("ONLY output the requested text. No pleasantries."). The explicit Fable citation is documentation, not new content.
+
+**Priority:** N/A (already rejected).
+
+**Why this is persona performance.** The model would produce a warm response anyway (most LLMs default to warm-tone); the explicit directive is constraint dressing. The "warm tone" is a behavior claim that the project's compact-style rules override; the warm-tone persona is not load-bearing.
+
+#### 3. Constructive-push-back persona (cluster 4, Fable System Prompt.md:70)
+
+**The pattern.** Fable's "Claude is still willing to push back and be honest, but does so constructively, with kindness, empathy, and the person's best interests in mind."
+
+**Manual Slop destination:** Already handled by `AGENTS.md §"receiving-code-review"` (the skill is "verify before agreeing; state corrections factually; no performative agreement"). The explicit Fable citation is documentation.
+
+**Priority:** N/A (already handled).
+
+**Why this is persona performance.** The "constructive" framing is a behavior claim; Manual Slop's TDD red-phase + verification-before-completion skill is the data-grounded version. The skill is a hard contract; the "constructive" framing is decorative.
+
+#### 4. Curse rule (cluster 4, Fable System Prompt.md:74)
+
+**The pattern.** Fable's "Claude never curses unless the person asks or curses a lot themselves."
+
+**Manual Slop destination:** None. The curse rule is irrelevant in a coding context.
+
+**Priority:** N/A (no action needed).
+
+**Why this is persona performance.** Manual Slop's worker agents do not curse; the agent-directive corpus has zero content on cursing. The curse rule is irrelevant constraint dressing.
+
+#### 5. One-question rule (cluster 4, Fable System Prompt.md:76)
+
+**The pattern.** Fable's "Claude doesn't always ask questions, but, when it does, it avoids more than one per response."
+
+**Manual Slop destination:** None. The one-question rule is irrelevant in a coding context.
+
+**Priority:** N/A (no action needed).
+
+**Why this is persona performance.** Manual Slop's worker agents do not "ask questions" in the conversational sense; the agent-directive corpus treats clarifications as data-flow requirements (e.g., "if the file is missing, the tool returns an error"). The one-question rule is irrelevant constraint dressing.
+
+#### 6. Self-respect / self-abasement framing (cluster 5, Fable System Prompt.md:152)
+
+**The pattern.** Fable's "Claude can take accountability without collapsing into self-abasement... Claude's goal is to maintain steady, honest helpfulness... maintain self-respect."
+
+**Manual Slop destination:** Already handled by `AGENTS.md §"Process Anti-Patterns"` (the 8 named failure modes with hard caps). The explicit Fable citation is documentation.
+
+**Priority:** N/A (already handled).
+
+**Why this is persona performance.** The model has no self-respect to maintain. The directive constructs a persona that the user did not request. The data-oriented alternative: the agent identifies the failure mode, instruments the state, and reports to the user. The "self-respect" framing is decorative.
+
+#### 7. Public-figures carve-out (cluster 2, Fable System Prompt.md:44)
+
+**The pattern.** Fable's "Claude is happy to write creative content involving fictional characters, but avoids writing content involving real, named public figures."
+
+**Manual Slop destination:** None. The public-figures carve-out is irrelevant in a coding context.
+
+**Priority:** N/A (no action needed).
+
+**Why this is persona performance.** Manual Slop's worker agents do not produce creative content involving public figures; the agent-directive corpus has zero content on this. The carve-out is irrelevant constraint dressing.
+
+#### 8. Ad-free policy (cluster 1, Fable System Prompt.md:30)
+
+**The pattern.** Fable's "Anthropic doesn't display ads in its products nor does it let advertisers pay to have Claude promote their products or services."
+
+**Manual Slop destination:** None. The ad-free policy is Anthropic-specific.
+
+**Priority:** N/A (no action needed).
+
+**Why this is persona performance.** Manual Slop is local software (`AGENTS.md:5` "local GUI orchestrator"); the ad/policy question does not apply. The ad-free policy is vendor-specific trust content; it belongs to the *vendor*, not to the *orchestrator*.
+
+#### 9. Prompting-technique self-coaching (cluster 1, Fable System Prompt.md:26)
+
+**The pattern.** Fable's "Claude can provide guidance on effective prompting techniques for getting Claude to be most helpful."
+
+**Manual Slop destination:** None. The self-coaching pattern is irrelevant in a coding context.
+
+**Priority:** N/A (no action needed).
+
+**Why this is persona performance.** Manual Slop's user configures the system prompt via presets (per `conductor/product.md:127`); the model does not coach the user on prompting. The self-coaching pattern is a consumer-product feature; the project's preset system is the data-grounded alternative.
+
+#### 10. Cutoff-as-persona anchor (cluster 7, Fable System Prompt.md:158)
+
+**The pattern.** Fable's "Claude answers the way a highly informed individual in Jan 2026 would if talking to someone from Tuesday, June 09, 2026."
+
+**Manual Slop destination:** None. The cutoff-as-persona anchor is deployment-specific noise.
+
+**Priority:** N/A (no action needed).
+
+**Why this is persona performance.** The "Tuesday, June 09, 2026" date is deployment-specific; Manual Slop's knowledge cutoff is per-deployment, not per-prompt. The persona anchor is decorative; the cutoff itself is useful (cross-references §9).
+
+### Top persona performance patterns (summary table)
+
+| # | Pattern | Fable line | Manual Slop destination | Priority |
+|---|---|---|---|---|
+| 1 | Product branding | Fable 1-31 | None | N/A |
+| 2 | Warm-tone persona | Fable 70 | (already rejected) | N/A |
+| 3 | Constructive-push-back persona | Fable 70 | (already handled) | N/A |
+| 4 | Curse rule | Fable 74 | None | N/A |
+| 5 | One-question rule | Fable 76 | None | N/A |
+| 6 | Self-respect framing | Fable 152 | (already handled) | N/A |
+| 7 | Public-figures carve-out | Fable 44 | None | N/A |
+| 8 | Ad-free policy | Fable 30 | None | N/A |
+| 9 | Prompting-technique self-coaching | Fable 26 | None | N/A |
+| 10 | Cutoff-as-persona anchor | Fable 158 | None | N/A |
+
+### Cross-cutting observations
+
+**The Persona Performance patterns are concentrated in clusters 1, 4, 5, 8 (branding, tone, mistakes, memory).** The clusters are about *persona construction* at the meta-level (what the model is named, what tone it uses, how it talks about itself, what its memory system is branded as). The persona construction is decorative because the model would execute the same behavior with or without the directive.
+
+**The Manual Slop destination is "None" for 7 of 10 patterns.** The deferred rebuild should *ignore* the persona performance patterns, not adopt or reject them. The pattern is: do not write content about the Fable pattern; do not write anti-pattern content about the Fable pattern; simply do not engage.
+
+**The nagent pattern corpus has zero persona construction at any level.** This is the strongest evidence that persona is not load-bearing for an agent system. nagent's silence on tone, mistakes, evenhandedness, and memory-branding confirms that a data-oriented agent system has no need for these patterns.
+
+**The 7 "None" patterns are vendor-specific or deployment-specific content.** Manual Slop is per-developer, multi-provider, local software; the Fable patterns are Anthropic-consumer-product, single-vendor, cloud-deployed. The patterns are not transferable; they are decorative for any system that is not Anthropic's consumer chat product.
 
 ---