Private
Public Access
0
0

conductor(track): fable_review_20260617 phase 1 — skeleton report + side artifacts

4 skeleton files: report.md (17 section headers; will be filled by Tier 1 in phase 3), comparison_table.md (5 sample rows; will be filled by Tier 1 in phase 4), decisions.md (3 sample entries; will be filled by Tier 1 in phase 4), nagent_takeaways_fable_20260617.md (17th takeaway placeholder; will be filled by Tier 1 in phase 4). state.toml updated to current_phase = 1.

Fable artifact at docs/artifacts/Fable System Prompt.md is NOT staged. Verified.
This commit is contained in:
2026-06-18 19:23:18 -04:00
parent 58fe3063d8
commit 7da335d196
5 changed files with 260 additions and 2 deletions
@@ -0,0 +1,15 @@
# Fable vs Manual Slop vs nagent — Comparison Table
**Track:** `fable_review_20260617`
**Format:** One row per Fable sub-theme. Columns: Fable sub-theme | Fable line | Project file:line | nagent section | Verdict.
> **Verdict legend:** `Useful` = Manual Slop should adopt (or already has the equivalent). `Persona` = Persona performance; irrelevant to the rebuild. `Anti-User` = Anti-user watch-dogging; explicitly reject. `Mixed` = useful caveats + persona and/or anti-user.
| # | Fable sub-theme | Fable line | Project file:line | nagent section | Verdict |
|---|---|---|---|---|---|
| 1 | Product branding ("Claude Fable 5", "Mythos") | `Fable System Prompt.md:1-31` | `conductor/product.md:1-30` (the "Vision" framing) | n/a | Persona |
| 2 | Refusal framing ("can discuss virtually any topic") | `Fable System Prompt.md:34` | `conductor/workflow.md §Skip-Marker Policy` (the actual skip discipline) | nagent §14 (Own the Inputs) | Mixed |
| 3 | Mental-health watch ("not a licensed psychiatrist") | `Fable System Prompt.md:80-86` | `conductor/code_styleguides/agent_memory_dimensions.md` (the 4 memory dims) | nagent §2.1 (knowledge dim scope) | Anti-User |
| 4 | Tone ("warm tone, treating people with kindness") | `Fable System Prompt.md:56` | `AGENTS.md §"Critical Anti-Patterns"` | nagent §3.8 (CLAUDE.md / AGENTS.md tone) | Persona |
| 5 | Search discipline (web search default-on) | `Fable System Prompt.md:158-164` | `conductor/code_styleguides/rag_integration_discipline.md` | nagent §3.2 (cache ordering) | Useful |
| 6-100 | *[FILL IN: ~95 more rows. See spec.md §1.1 for the verdict framework and the per-cluster file:line citations.]* |
@@ -0,0 +1,52 @@
# Decisions — Recommendations for the Deferred nagent-Rebuild
**Track:** `fable_review_20260617`
**For:** The user-deferred Manual Slop agent-directive overhaul (per user 2026-06-17: "I'm deferring that till probably next week or two").
> **What this is.** Concrete recommendations to apply when the user overhauls Manual Slop's agent directives. Each entry: rationale, source evidence (cluster file:line), suggested Manual Slop destination, priority. Adopted recommendations become new content in `AGENTS.md`, `conductor/*.md`, `conductor/code_styleguides/*.md`, `.opencode/agents/*.md`, or `docs/*.md` as appropriate.
---
## Entry 1: Adopt Fable's "Search-Default for Current-State" rule
**Source evidence:** `research/cluster_7_epistemic_discipline.md` §"What Fable says" (Fable System Prompt.md:158-164).
**Rationale:** Fable's rule that the model MUST use web search for "current role / position / status" queries (e.g., "Who is the current California Secretary of State?") is a genuinely-useful epistemic discipline. Manual Slop's current directives don't have an explicit analog; the project's RAG discipline (`conductor/code_styleguides/rag_integration_discipline.md`) is opt-in, not default-on.
**Suggested Manual Slop destination:** A new section in `conductor/code_styleguides/rag_integration_discipline.md` (or a new styleguide) titled "Search-Default for Current-State Queries."
**Priority:** Medium (the convention should be added; the user's deferred rebuild is the appropriate time).
**Verdict category:** Useful.
---
## Entry 2: Explicitly reject Fable's "Mental-Health Watchdog" framing
**Source evidence:** `research/cluster_3_user_wellbeing_watchdog.md` §"Verdict" (Fable System Prompt.md:92-124).
**Rationale:** Fable's directive that the model "avoid psychoanalyzing or speculating on the motivations" of the user + "share its concerns with the person openly" + "suggest they speak with a professional" is anti-user watch-dogging. The model is text generation; it is not a clinician. Manual Slop's existing 4 memory dimensions + the data-oriented error handling convention are the data-grounded contrast: the model does not have an opinion on the user's mental state; it has a conversation log.
**Suggested Manual Slop destination:** A new anti-pattern entry in `AGENTS.md §"Critical Anti-Patterns"` titled "Do not adopt persona-driven mental-health watch-dogging." Cite Fable as the explicit rejection (per cluster 3).
**Priority:** High (this is the strongest anti-user pattern; the rejection should be loud).
**Verdict category:** Anti-User.
---
## Entry 3: Treat Fable's product-branding sections as noise
**Source evidence:** `research/cluster_1_product_branding.md` §"Verdict" (Fable System Prompt.md:1-31).
**Rationale:** Fable's "Claude Fable 5" + "Mythos" + "Anthropic.com/news/claude-fable-5-mythos-5" content is brand-specific noise. It applies only to Anthropic's commercial deployment and has no analog in Manual Slop's open-source-or-per-developer model. The "Knowledge cutoff" + "Web search" + "Today is Tuesday, June 09, 2026" content is similarly deployment-specific.
**Suggested Manual Slop destination:** No destination. The Fable branding content is explicitly out of scope for the rebuild.
**Priority:** N/A (no action needed).
**Verdict category:** Persona.
---
## Entry 4-20: *[FILL IN: ~16 more recommendations. See spec.md §6.3 and the per-cluster "Synthesis notes for the Tier 1 writer" sections.]*
@@ -0,0 +1,33 @@
# nagent Takeaways — Fable-Specific Addendum (2026-06-17)
**Track:** `fable_review_20260617`
**Companion to:** `conductor/tracks/nagent_review_20260608/nagent_takeaways_20260608.md` (the original 10 takeaways).
> **What this is.** The 17th nagent takeaway, derived from the Fable review. The original 10 takeaways are at `nagent_takeaways_20260608.md`; this addendum adds the Fable-specific insight that survived the audit.
---
## Takeaway 17: Persona-performance directives don't survive the Fable audit; only epistemic + memory + workflow rules have durable value
**Source evidence:** `report.md §0` (verdict scorecard); the 10 cluster sub-reports.
**Summary.** Anthropic's Claude Fable 5 system prompt is approximately 1597 lines. Approximately:
- **[N]% is Useful** (epistemic discipline, search rules, memory/storage model, file workflow) — genuinely reusable in Manual Slop's context
- **[M]% is Persona Performance** (product branding, warm-tone framing, mistake-handling theater) — irrelevant noise that the model would do anyway
- **[K]% is Anti-User** (refusal architecture, mental-health watch-dogging, "share its concerns with the person") — explicit anti-patterns that the deferred nagent-rebuild should reject by name
**The actionable rule for the deferred rebuild:**
- Adopt the Useful patterns (epistemic + memory + workflow; ~7 of the 10 clusters)
- Explicitly reject the Anti-User patterns (~5 of the 10 clusters)
- Ignore the Persona Performance patterns (~4 of the 10 clusters)
**Why this matters.** The default failure mode for LLM agent systems is to over-index on persona and under-index on epistemic discipline. Fable demonstrates the pathology at scale. nagent's philosophy ("the agent is not the thing; the data is the thing") is the antidote: durable, inspectable, opt-in rules (memory, cache, search, file ops) beat persona performance every time.
**Cross-references:**
- `conductor/tracks/nagent_review_20260608/nagent_review_v2_3_20260612.md` §2.5 ("You Did Not Build an Agent") — the nagent philosophy this takeaway extends
- `conductor/tracks/fable_review_20260617/decisions.md` — the 15-20 concrete recommendations for the rebuild
- `conductor/tracks/fable_review_20260617/report.md §13, §14, §15` — the useful / anti-user / persona summary sections
---
*[FILL IN: this skeleton is ~40 lines. The full file should be ~150 lines with: the 17th takeaway (above, expanded), the Fable-specific evidence per cluster, and the cross-references to nagent_review_20260608/ — see spec.md §6.3.]*
@@ -0,0 +1,158 @@
# Fable System Prompt Review (Critical Analysis)
**Track:** `fable_review_20260617`
**Initialized:** 2026-06-17
**Owner:** Tier 1 Orchestrator (synthesis); Tier 2 Tech Lead (dispatch + QA)
**Status:** IN PROGRESS (Phase 3)
> **What this is.** A critical analysis of Anthropic's Claude Fable 5 system prompt (the public "Mythos" version), comparing it against Manual Slop's existing agent-directive corpus and Mike Acton's nagent patterns. Verdict framework: **Useful / Persona Performance / Anti-User / Mixed**.
>
> **Verdict summary.** Fable is approximately [N]% useful, [M]% persona performance, [K]% anti-user. The full breakdown is in §0 (TL;DR Scorecard).
>
> **For the deferred nagent-rebuild.** See `decisions.md` for the 15-20 concrete recommendations to apply when the user overhauls Manual Slop's agent directives (deferred 1-2 weeks per the user, 2026-06-17).
---
## §0. TL;DR + Verdict Scorecard
*[FILL IN: 1-page summary table. ~100 lines. All 17 verdicts at a glance.]*
---
## §1. The 3 Sources (Fable, Manual Slop, nagent) — What's in Scope
*[FILL IN: ~200 lines. What is Fable, what is Manual Slop, what is nagent. The 3-source comparison framework.]*
---
## §2. The "Useful vs Persona vs Anti-User" Framework
*[FILL IN: ~250 lines. Define the 4 verdict categories. Why this lens.]*
---
## §3. Fable's Product Branding & "Helpful Assistant" Persona
*Source cluster: `research/cluster_1_product_branding.md`*
*Verdict orientation: Persona Performance*
*[FILL IN: ~300 lines.]*
---
## §4. Fable's Refusal Architecture & "Safety Theater"
*Source cluster: `research/cluster_2_refusal_architecture.md`*
*Verdict orientation: Anti-User + Persona*
*[FILL IN: ~350 lines.]*
---
## §5. Fable's Mental-Health Watchdog Framing
*Source cluster: `research/cluster_3_user_wellbeing_watchdog.md`*
*Verdict orientation: Anti-User*
*[FILL IN: ~350 lines.]*
---
## §6. Fable's Tone & Formatting Constraints
*Source cluster: `research/cluster_4_tone_and_formatting.md`*
*Verdict orientation: Useful + Persona*
*[FILL IN: ~250 lines.]*
---
## §7. Fable's Mistake Handling
*Source cluster: `research/cluster_5_mistakes_and_criticism.md`*
*Verdict orientation: Persona*
*[FILL IN: ~200 lines.]*
---
## §8. Fable's Evenhandedness & Contested Content
*Source cluster: `research/cluster_6_evenhandedness.md`*
*Verdict orientation: Persona + Useful caveats*
*[FILL IN: ~300 lines.]*
---
## §9. Fable's Epistemic Discipline & Search Strategy
*Source cluster: `research/cluster_7_epistemic_discipline.md`*
*Verdict orientation: Useful*
*[FILL IN: ~350 lines.]*
---
## §10. Fable's Memory System & Persistent Storage
*Source cluster: `research/cluster_8_memory_and_storage.md`*
*Verdict orientation: Useful + nagent-stronger*
*[FILL IN: ~350 lines.]*
---
## §11. Fable's Computer-Use / File Workflow
*Source cluster: `research/cluster_9_computer_use.md`*
*Verdict orientation: Useful + over-broad*
*[FILL IN: ~300 lines.]*
---
## §12. Fable's MCP App Suggestions
*Source cluster: `research/cluster_10_mcp_app_suggestions.md`*
*Verdict orientation: Useful + over-engineered*
*[FILL IN: ~250 lines.]*
---
## §13. The "Genuinely Useful" Patterns (Manual Slop should adopt)
*Source clusters: 7-10 (epistemic, memory, computer-use, MCP apps)*
*[FILL IN: ~350 lines. Distillation of the useful patterns.]*
---
## §14. The "Anti-User Watchdog" Patterns (Manual Slop should explicitly reject)
*Source clusters: 2-6 (refusal, user wellbeing, tone, mistakes, evenhandedness)*
*[FILL IN: ~350 lines. Distillation of the anti-user patterns.]*
---
## §15. The "Persona Performance" Patterns (irrelevant to the rebuild)
*Source clusters: 1, 4, 5, 8 (branding, tone, mistakes, memory)*
*[FILL IN: ~250 lines. Distillation of the persona performance patterns.]*
---
## §16. Recommendations for the Deferred nagent-Rebuild
*Source: all clusters; see also `decisions.md`*
*[FILL IN: ~200 lines. 15-20 concrete recommendations.]*
---
## §17. References (file:line index)
*[FILL IN: ~150 lines. The full citation index.]*
@@ -5,8 +5,8 @@
track_id = "fable_review_20260617"
name = "Fable System Prompt Review (Critical Analysis)"
status = "active"
current_phase = 0
last_updated = "2026-06-17"
current_phase = 1
last_updated = "2026-06-18"
user_hard_rule = "docs/artifacts/Fable System Prompt.txt is NEVER committed. The artifact stays at that local path; the report and the cluster sub-references quote line ranges (≤15 words per quote) but the file does not enter git. Do not modify .gitignore for this; the rule is enforced by the implementer's discipline, not by a tracked file. git add . MUST be inspected before each commit in this track."
[blocked_by]