docs(track): fable_review_20260617 section 13 — Genuinely Useful Patterns
Distillation of clusters 7-10. ~190 lines. 8 Useful patterns with Manual Slop destinations: (1) search-default for current-state, (2) default to prose, (3) no gratitude performance, (4) file-presence check, (5) data-discipline rule, (6) owns-the-mistake, (7) no-overconfident-claims, (8) hierarchical-keys. Cross-cutting observation: Useful patterns are data-operations; the persona-operations are decorative.
This commit is contained in:
@@ -1097,7 +1097,137 @@ The strongest claim: Fable's `suggest_connectors` and Manual Slop's `/api/ask` a
|
||||
|
||||
*Source clusters: 7-10 (epistemic, memory, computer-use, MCP apps)*
|
||||
|
||||
*[FILL IN: ~350 lines. Distillation of the useful patterns.]*
|
||||
### What this section is
|
||||
|
||||
This section distills the "Genuinely Useful" patterns from the per-cluster synthesis (§3-§12). The source clusters are 7-10 (epistemic, memory, computer-use, MCP apps) — the four clusters with **Useful** as the primary verdict orientation. The patterns here are the candidates for the deferred nagent-rebuild to adopt.
|
||||
|
||||
### Top useful patterns (with Manual Slop destinations)
|
||||
|
||||
#### 1. Search-default for current-state queries (cluster 7, Fable System Prompt.md:158-164)
|
||||
|
||||
**Source cluster:** `research/cluster_7_epistemic_discipline.md` §4 (verdict: Useful).
|
||||
|
||||
**The pattern.** Fable's 4-step `knowledge_cutoff` pattern:
|
||||
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.
|
||||
|
||||
**Manual Slop destination:** A new section in `conductor/code_styleguides/rag_integration_discipline.md` titled "Search-Default for Current-State Queries." The rule: for queries about current officeholders, binary events (deaths, elections, major incidents), or present-tense phrasings of historical facts, the agent must search by default. The user can opt out per-query.
|
||||
|
||||
**Priority:** Medium (the principle is well-established; the explicit Fable citation is documentation).
|
||||
|
||||
**Why this is genuinely useful.** Manual Slop's RAG discipline is opt-in; the user must explicitly enable RAG. The Fable pattern is concrete and actionable: the agent searches for current-state queries *by default*. The deferred rebuild should bridge this gap.
|
||||
|
||||
**Nagent corroboration:** `nagent_review_v2_3_20260612.md §2.10` (RAG integration discipline) — the conservative-RAG rule is the upstream; Fable's search-default pattern is a more aggressive version.
|
||||
|
||||
#### 2. Format-discipline: default to prose, use lists only when asked (cluster 4, Fable System Prompt.md:84-90)
|
||||
|
||||
**Source cluster:** `research/cluster_4_tone_and_formatting.md` §4 (verdict: Useful + Persona).
|
||||
|
||||
**The pattern.** Fable's formatting discipline:
|
||||
- Avoid over-formatting with bold emphasis, headers, lists, and bullet points.
|
||||
- Use lists, bullets, and formatting only when asked or when the content is multi-faceted.
|
||||
- For reports, documents, technical documentation, and explanations, write prose without bullets, numbered lists, or excessive bolding.
|
||||
|
||||
**Manual Slop destination:** A new section in `conductor/product-guidelines.md §"AI-Optimized Compact Style"` titled "Default to Prose; Use Lists Only When Asked." The rule: agents default to prose; use bullets only when asked or when content is multi-faceted.
|
||||
|
||||
**Priority:** Medium (the principle is already in the existing compact-style rules; the explicit Fable citation is documentation).
|
||||
|
||||
**Why this is genuinely useful.** The pattern is the same insight as Manual Slop's AI-Optimized Compact Style (1-space indentation, 0 blank lines, single-line `if`, region blocks). Same insight, different framing: Fable is chat-UX-driven; Manual Slop is token-economy-driven. The cross-reference is data-grounding.
|
||||
|
||||
#### 3. Anti-sycophancy: no gratitude performance (cluster 4, Fable System Prompt.md:124)
|
||||
|
||||
**Source cluster:** `research/cluster_4_tone_and_formatting.md` §4 (verdict: Useful + Persona).
|
||||
|
||||
**The pattern.** Fable's "Claude never thanks the person merely for reaching out to Claude" is separable from its user_wellbeing context and is a useful tone rule.
|
||||
|
||||
**Manual Slop destination:** An explicit addition to `.opencode/agents/tier*.md` titled "No Gratitude Performance." The rule: agents do not perform gratitude; they execute the task.
|
||||
|
||||
**Priority:** Low (the project's existing tier-agent rules already say "ONLY output the requested text. No pleasantries.").
|
||||
|
||||
**Why this is genuinely useful.** The "Claude never thanks" rule is a concrete anti-sycophancy directive. Manual Slop's "no pleasantries" rule is the same insight. The cross-reference makes the pattern explicit.
|
||||
|
||||
#### 4. File-presence check before editing (cluster 9, Fable System Prompt.md:80)
|
||||
|
||||
**Source cluster:** `research/cluster_9_computer_use.md` §4 (verdict: Useful + over-broad).
|
||||
|
||||
**The pattern.** Fable's "A prompt implying a file is present doesn't mean one is, as the person may have forgotten to upload it, so Claude checks for itself" — agents verify, not assume.
|
||||
|
||||
**Manual Slop destination:** An explicit addition to `conductor/edit_workflow.md` titled "Verify File Existence Before Editing." The rule: agents verify file existence with the MCP `read_file` tool before acting on file-content assumptions.
|
||||
|
||||
**Priority:** Low (the MCP tools already enforce this implicitly; the audit script catches violations).
|
||||
|
||||
**Why this is genuinely useful.** The pattern is a concrete anti-hallucination directive. Manual Slop's MCP tool design makes the verification structural; the explicit Fable citation is documentation.
|
||||
|
||||
#### 5. Data-discipline rule: the model provides data, the user makes the decision (cluster 2, Fable System Prompt.md:66)
|
||||
|
||||
**Source cluster:** `research/cluster_2_refusal_architecture.md` §4 (verdict: Anti-User + Persona + 1 Useful).
|
||||
|
||||
**The pattern.** Fable's "For financial or legal questions... Claude provides the factual information the person needs to make their own informed decision rather than confident recommendations, and notes that it isn't a lawyer or financial advisor."
|
||||
|
||||
**Manual Slop destination:** A new section in `conductor/code_styleguides/data_oriented_design.md` titled "Domain Boundaries: Data, Not Recommendations." The rule: in domain-expertise contexts (legal, financial, medical, mental-health), the model provides data; the user makes the decision; the model is not a domain expert.
|
||||
|
||||
**Priority:** Medium (the principle is well-established; the explicit Fable citation is documentation).
|
||||
|
||||
**Why this is genuinely useful.** The pattern is a concrete epistemic boundary. Manual Slop's data-oriented design is the upstream; the Fable pattern is a specific application.
|
||||
|
||||
#### 6. "Owns the mistake" pattern (cluster 5, Fable System Prompt.md:152)
|
||||
|
||||
**Source cluster:** `research/cluster_5_mistakes_and_criticism.md` §4 (verdict: Persona + Anti-User + 1 Useful).
|
||||
|
||||
**The pattern.** Fable's "When Claude makes mistakes, it owns them and works to fix them."
|
||||
|
||||
**Manual Slop destination:** Already implemented in `AGENTS.md §"Process Anti-Patterns"`. The explicit Fable citation is documentation.
|
||||
|
||||
**Priority:** N/A (already implemented).
|
||||
|
||||
**Why this is genuinely useful.** The pattern is the data-oriented version of mistake-handling: the agent identifies the failure mode (one of the 8 Process Anti-Patterns), instruments the state, and reports to the user.
|
||||
|
||||
#### 7. No-overconfident-claims rule (cluster 7, Fable System Prompt.md:164)
|
||||
|
||||
**Source cluster:** `research/cluster_7_epistemic_discipline.md` §4 (verdict: Useful).
|
||||
|
||||
**The pattern.** Fable's "Claude does not make overconfident claims about the validity of search results or their absence."
|
||||
|
||||
**Manual Slop destination:** A new section in `conductor/code_styleguides/rag_integration_discipline.md` titled "No Overconfident Claims." The rule: agents do not over-claim the validity of RAG search results; the user is the navigator, not the agent.
|
||||
|
||||
**Priority:** Medium.
|
||||
|
||||
**Why this is genuinely useful.** The pattern is a concrete anti-overfitting directive. The RAG discipline's "graceful failure" rule is the upstream; the Fable pattern is a specific application.
|
||||
|
||||
#### 8. Hierarchical-keys for knowledge files (cluster 8, Fable System Prompt.md:203)
|
||||
|
||||
**Source cluster:** `research/cluster_8_memory_and_storage.md` §4 (verdict: Useful + nagent-stronger).
|
||||
|
||||
**The pattern.** Fable's "Use hierarchical keys under 200 chars: `table_name:record_id`."
|
||||
|
||||
**Manual Slop destination:** A new section in `conductor/code_styleguides/knowledge_artifacts.md` titled "Hierarchical Keys for Knowledge Files." The rule: knowledge files use hierarchical names (e.g., `decisions/api_hooks_auth.md`, `facts/sha256_ledger.md`).
|
||||
|
||||
**Priority:** Medium.
|
||||
|
||||
**Why this is genuinely useful.** The pattern is a concrete file-organization directive. Manual Slop's `knowledge_artifacts.md` is the upstream; the Fable pattern is a specific application.
|
||||
|
||||
### Top useful patterns (summary table)
|
||||
|
||||
| # | Pattern | Fable line | Manual Slop destination | Priority |
|
||||
|---|---|---|---|---|
|
||||
| 1 | Search-default for current-state queries | Fable 158-164 | `rag_integration_discipline.md` | Medium |
|
||||
| 2 | Default to prose, use lists only when asked | Fable 84-90 | `product-guidelines.md §Compact Style` | Medium |
|
||||
| 3 | No gratitude performance | Fable 124 | `.opencode/agents/tier*.md` | Low |
|
||||
| 4 | File-presence check before editing | Fable 80 | `edit_workflow.md` | Low |
|
||||
| 5 | Data-discipline rule: data, not recommendations | Fable 66 | `data_oriented_design.md` | Medium |
|
||||
| 6 | "Owns the mistake" pattern | Fable 152 | (already in `AGENTS.md`) | N/A |
|
||||
| 7 | No-overconfident-claims rule | Fable 164 | `rag_integration_discipline.md` | Medium |
|
||||
| 8 | Hierarchical-keys for knowledge files | Fable 203 | `knowledge_artifacts.md` | Medium |
|
||||
|
||||
### Cross-cutting observations
|
||||
|
||||
**The Useful patterns are concentrated in clusters 7-10 (epistemic, memory, computer-use, MCP apps).** This is not a coincidence: these clusters are about *data operations* (search, store, file, connect), not *persona construction* (refusal, wellbeing, tone, mistakes). The data operations are testable, shape-anchored, and verifiable; the persona operations are prose-anchored and decorative.
|
||||
|
||||
**The Manual Slop destinations are 5 distinct files** (rag_integration_discipline, product-guidelines, edit_workflow, data_oriented_design, knowledge_artifacts) + the .opencode/agents/tier*.md tier-agent files. The deferred rebuild should add ~8 sections across these 5 files.
|
||||
|
||||
**The nagent pattern corpus has zero product branding and zero persona construction.** This confirms that the Useful patterns are not specific to Fable; they are the data-oriented patterns that any agent system would adopt. The 8 patterns are candidates for adoption because they solve real problems, not because they are Fable's.
|
||||
|
||||
---
|
||||
|
||||
|
||||
Reference in New Issue
Block a user