diff --git a/conductor/tracks/fable_review_20260617/report.md b/conductor/tracks/fable_review_20260617/report.md
index 33264976..54bf9b6d 100644
--- a/conductor/tracks/fable_review_20260617/report.md
+++ b/conductor/tracks/fable_review_20260617/report.md
@@ -1625,4 +1625,176 @@ The deferred rebuild is the user's next step. The Fable review is the evidence d
 
 ## §17. References (file:line index)
 
-*[FILL IN: ~150 lines. The full citation index.]*
+
+### Fable artifact citations
+
+- `docs/artifacts/Fable System Prompt.md:1` — H1 title
+- `docs/artifacts/Fable System Prompt.md:4` — `{antml:voice_note}` deployment quirk
+- `docs/artifacts/Fable System Prompt.md:12` — model-tier naming
+- `docs/artifacts/Fable System Prompt.md:14` — consumer redirect URL
+- `docs/artifacts/Fable System Prompt.md:18` — vendor catalogue
+- `docs/artifacts/Fable System Prompt.md:20` — Claude Code + Cowork
+- `docs/artifacts/Fable System Prompt.md:22` — beta products
+- `docs/artifacts/Fable System Prompt.md:24` — search-before-answering caveat
+- `docs/artifacts/Fable System Prompt.md:26` — prompting-technique guidance
+- `docs/artifacts/Fable System Prompt.md:28` — settings toggles
+- `docs/artifacts/Fable System Prompt.md:30` — ad-free policy
+- `docs/artifacts/Fable System Prompt.md:34-49` — `refusal_handling` section
+- `docs/artifacts/Fable System Prompt.md:50-63` — `critical_child_safety_instructions`
+- `docs/artifacts/Fable System Prompt.md:64-67` — `legal_and_financial_advice`
+- `docs/artifacts/Fable System Prompt.md:66` — data-discipline rule (Useful caveat)
+- `docs/artifacts/Fable System Prompt.md:68-91` — `tone_and_formatting` + `lists_and_bullets`
+- `docs/artifacts/Fable System Prompt.md:70` — warm-tone persona
+- `docs/artifacts/Fable System Prompt.md:80` — file-presence check
+- `docs/artifacts/Fable System Prompt.md:84-90` — formatting discipline
+- `docs/artifacts/Fable System Prompt.md:92-124` — `user_wellbeing` section
+- `docs/artifacts/Fable System Prompt.md:96, 98` — epistemic disclaimers
+- `docs/artifacts/Fable System Prompt.md:108` — model-has-concerns
+- `docs/artifacts/Fable System Prompt.md:110` — model-surveillance
+- `docs/artifacts/Fable System Prompt.md:122` — model-deserves-dignity
+- `docs/artifacts/Fable System Prompt.md:124` — model-has-wants + no-gratitude
+- `docs/artifacts/Fable System Prompt.md:128-132` — `anthropic_reminders`
+- `docs/artifacts/Fable System Prompt.md:134-146` — `evenhandedness` section
+- `docs/artifacts/Fable System Prompt.md:136` — framing rule
+- `docs/artifacts/Fable System Prompt.md:140` — stereotype rule
+- `docs/artifacts/Fable System Prompt.md:142` — fair-accurate-overview (Useful caveat)
+- `docs/artifacts/Fable System Prompt.md:144` — user-as-navigator (Useful caveat)
+- `docs/artifacts/Fable System Prompt.md:148-154` — `responding_to_mistakes_and_criticism`
+- `docs/artifacts/Fable System Prompt.md:150` — thumbs-down mention
+- `docs/artifacts/Fable System Prompt.md:152` — owns-the-mistake (Useful)
+- `docs/artifacts/Fable System Prompt.md:154` — model-deserves-respect + end_conversation
+- `docs/artifacts/Fable System Prompt.md:156-164` — `knowledge_cutoff` section
+- `docs/artifacts/Fable System Prompt.md:158` — cutoff-as-persona anchor
+- `docs/artifacts/Fable System Prompt.md:158-164` — 4-step knowledge_cutoff pattern
+- `docs/artifacts/Fable System Prompt.md:160` — date-anchor in queries
+- `docs/artifacts/Fable System Prompt.md:162` — proactive-search trigger
+- `docs/artifacts/Fable System Prompt.md:164` — no-overconfident-claims
+- `docs/artifacts/Fable System Prompt.md:166-170` — `memory_system` section
+- `docs/artifacts/Fable System Prompt.md:172-260` — `persistent_storage_for_artifacts`
+- `docs/artifacts/Fable System Prompt.md:177-200` — `Storage API` methods
+- `docs/artifacts/Fable System Prompt.md:203` — hierarchical-keys pattern
+- `docs/artifacts/Fable System Prompt.md:205` — batching pattern
+- `docs/artifacts/Fable System Prompt.md:211, 213` — personal-vs-shared scope
+- `docs/artifacts/Fable System Prompt.md:218` — try/catch rule
+- `docs/artifacts/Fable System Prompt.md:255-256` — "helpful person" framing
+- `docs/artifacts/Fable System Prompt.md:272-278` — opt-in gate
+- `docs/artifacts/Fable System Prompt.md:280-310` — `mcp_app_suggestions`
+- `docs/artifacts/Fable System Prompt.md:299` — audit-awareness
+- `docs/artifacts/Fable System Prompt.md:312-420` — `computer_use` section
+- `docs/artifacts/Fable System Prompt.md:380` — read-in-full rule
+- `docs/artifacts/Fable System Prompt.md:390` — format-check rule
+- `docs/artifacts/Fable System Prompt.md:400` — format-type rule
+- `docs/artifacts/Fable System Prompt.md:410` — no-boilerplate rule
+- `docs/artifacts/Fable System Prompt.md:438-575` — `search_instructions` section
+- `docs/artifacts/Fable System Prompt.md:1234` — error-routing pattern
+
+### Manual Slop project citations
+
+- `AGENTS.md:3-5` — project framing (local GUI orchestrator)
+- `AGENTS.md §"Critical Anti-Patterns"` — 8 named failure modes with hard caps
+- `AGENTS.md §"receiving-code-review"` — verify before agreeing
+- `AGENTS.md §"File Size and Naming Convention"` — system is the namespace
+- `conductor/product.md:5` — expert-level utility for personal developer use
+- `conductor/product.md:52` — 5 LLM providers
+- `conductor/product.md:122-126` — System Prompt Presets
+- `conductor/product.md:127` — Foundational Base System Prompt
+- `conductor/product.md:131-140` — Agent Personas & Unified Profiles
+- `conductor/product-guidelines.md §"AI-Optimized Compact Style"` — 1-space, 0 blanks, single-line if
+- `conductor/product-guidelines.md:39-49` — the project's actual style
+- `conductor/workflow.md §"Skip-Marker Policy"` — fix the underlying bug
+- `conductor/workflow.md §"Process Anti-Patterns"` — 8 named anti-patterns
+- `conductor/edit_workflow.md:1-209` — the edit protocol
+- `conductor/tech-stack.md` — file system layout
+- `conductor/code_styleguides/data_oriented_design.md:9` — "the data is the thing"
+- `conductor/code_styleguides/data_oriented_design.md:33-61` — 3 defaults to reject
+- `conductor/code_styleguides/agent_memory_dimensions.md:11-19` — 4 memory dimensions table
+- `conductor/code_styleguides/rag_integration_discipline.md:11-156` — 6 RAG rules
+- `conductor/code_styleguides/cache_friendly_context.md:1-50` — 12-layer model
+- `conductor/code_styleguides/knowledge_artifacts.md` — 5 category files + ledger + digest
+- `conductor/code_styleguides/error_handling.md` — Result[T] + ErrorInfo
+- `conductor/code_styleguides/feature_flags.md` — file presence, config flags, CLI flags
+- `.opencode/agents/tier1-orchestrator.md:6-7` — ONLY output the requested text
+- `.opencode/agents/tier2-tech-lead.md` — tier 2 role
+- `.opencode/agents/tier3-worker.md:3-4` — no pleasantries; BLOCKED + Anti-Patterns
+- `.opencode/agents/tier4-qa.md` — tier 4 role
+- `docs/guide_architecture.md` — threading model
+- `docs/guide_tools.md:7-53` — 3-layer security
+- `docs/guide_tools.md:55-196` — 45-tool inventory
+- `docs/guide_mcp_client.md` — 45 tools + 3-layer security
+- `docs/guide_rag.md` — RAG subsystem
+- `docs/guide_discussions.md:29-43` — entry dict schema
+- `docs/guide_discussions.md:71-86` — A1 (content) field
+- `docs/guide_discussions.md:253-272` — threading model
+- `docs/guide_discussions.md:288-302` — destructive reset
+- `docs/guide_knowledge_curation.md` — knowledge dim guide
+- `docs/guide_testing.md` — test suite architecture
+- `docs/Readme.md:9-12` — "What This Is"
+- `docs/AGENTS.md §4` — 4 memory dimensions decision tree
+- `src/models.py:523-559` — FileItem type
+- `src/history.py:8-100` — UISnapshot
+- `src/paths.py` — path resolution module
+- `src/mcp_client.py` — native tool registry
+- `scripts/audit_exception_handling.py` — static analyzer
+- `scripts/audit_weak_types.py` — type-strengthening
+- `scripts/audit_main_thread_imports.py` — main-thread import graph
+- `scripts/audit_no_models_config_io.py` — config-I/O ownership
+
+### nagent corpus citations
+
+- `conductor/tracks/nagent_review_20260608/nagent_review_v2_3_20260612.md:4` — adapted from Mike Acton's `context/data-oriented-design.md`
+- `nagent_review_v2_3_20260612.md:1174` — Anthropic as provider-SDK, not brand
+- `nagent_review_v2_3_20260612.md:1880-2019` — §3.8 CLAUDE.md / AGENTS.md @import pattern
+- `nagent_review_v2_3_20260612.md:2709-2780` — Anthropic `cache_prefix_blocks` implementation
+- `nagent_review_v2_3_20260612.md §2.1` — 4 memory dimensions
+- `nagent_review_v2_3_20260612.md §2.4` — Pattern 4: Self-Describing Tools
+- `nagent_review_v2_3_20260612.md §2.5` — "You Did Not Build an Agent"
+- `nagent_review_v2_3_20260612.md §2.7` — Conversations are editable state
+- `nagent_review_v2_3_20260612.md §2.8` — Pattern 8: Harvest Knowledge
+- `nagent_review_v2_3_20260612.md §2.10` — RAG integration discipline
+- `nagent_review_v2_3_20260612.md §2.14` — Own the Inputs
+- `nagent_review_v2_3_20260612.md §3.1` — Knowledge harvest
+- `nagent_review_v2_3_20260612.md §3.2` — Cache ordering
+- `nagent_review_v2_3_20260612.md §3.4` — Conversation compaction (12-section digest)
+- `nagent_review_v2_3_20260612.md §3.9` — Per-file knowledge notes (Candidate 11.1)
+- `nagent_review_v2_3_20260612.md §4.4` — Sub-pattern detail
+- `nagent_review_v2_3_20260612.md §5.5` — Self-review (10 questions)
+- `nagent_review_v2_3_20260612.md §6.3` — 10-question compaction self-review
+- `nagent_review_v2_3_20260612.md §8.4` — Tool discovery (the `--description` pattern)
+- `nagent_review_v2_3_20260612.md §9` — Large files
+- `nagent_review_v2_3_20260612.md:2956-2960` — §5.5 cache ordering caveat
+- `nagent_review_v2_3_20260612.md:3046-3100` — §6.3 10-question self-review detail
+- `nagent_review_v2_3_20260612.md:3748-3754` — §8.4 parse-then-dispatch
+- `nagent_review_v2_3_20260612.md:3827-4115` — §9 file splits/patches/summaries
+- `nagent_review_v2_3_20260612.md:390-426` — §2.4 Pattern 4 detail
+- `nagent_review_v2_3_20260612.md:1594` — run_discussion_compression GAP
+- `conductor/tracks/nagent_review_20260608/nagent_takeaways_20260608.md` — 10 takeaways (companion)
+- `conductor/tracks/nagent_review_20260608/report.md` — v1 14-section deep-dive
+- `conductor/tracks/nagent_review_20260608/decisions.md` — 10 future-track candidates
+- `conductor/tracks/nagent_review_20260608/comparison_table.md` — flat side-by-side table
+
+### Track-internal citations
+
+- `conductor/tracks/fable_review_20260617/spec.md` — the approved spec
+- `conductor/tracks/fable_review_20260617/metadata.json` — track metadata
+- `conductor/tracks/fable_review_20260617/state.toml` — track state
+- `conductor/tracks/fable_review_20260617/research/cluster_1_product_branding.md` — 250 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_2_refusal_architecture.md` — 402 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_3_user_wellbeing_watchdog.md` — 247 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_4_tone_and_formatting.md` — 230 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_5_mistakes_and_criticism.md` — 214 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_6_evenhandedness.md` — 348 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_7_epistemic_discipline.md` — 452 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_8_memory_and_storage.md` — 499 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_9_computer_use.md` — 373 lines
+- `conductor/tracks/fable_review_20260617/research/cluster_10_mcp_app_suggestions.md` — 263 lines
+- `conductor/tracks/fable_review_20260617/comparison_table.md` — flat side-by-side table
+- `conductor/tracks/fable_review_20260617/decisions.md` — 15-20 recommendations
+- `conductor/tracks/fable_review_20260617/nagent_takeaways_fable_20260617.md` — 17th nagent takeaway
+
+### External references
+
+- Anthropic's Claude Fable 5 / Mythos announcement: `https://www.anthropic.com/news/claude-fable-5-mythos-5` (referenced by Fable at line 14; not read directly)
+- Mike Acton's nagent: `https://github.com/macton/nagent` (source of the nagent_review corpus)
+- Mike Acton's data-oriented design talks: `https://www.youtube.com/results?search_query=mike+acton+data+oriented`
+- Ryan Fleury, "The Easiest Way To Handle Errors Is To Not Have Them": `https://www.dgtlgrove.com/p/the-easiest-way-to-handle-errors`
+- The project's "errors are data" convention: `conductor/code_styleguides/error_handling.md`