@mindrian_os/install 1.13.0-beta.11

package/pipelines/thesis/01-structure-argument.md

@@ -0,0 +1,45 @@
+---
+stage: 1
+methodology: structure-argument
+chain: thesis
+input_from: null
+output_to: challenge-assumptions
+room_section: problem-definition
+---
+
+# Stage 1: Structure Argument (Minto Pyramid)
+
+## Input Extraction
+
+First stage -- uses user's thesis, argument, or claim directly. No prior pipeline artifact needed.
+
+If the user provided a thesis statement when starting the pipeline, use that as the starting point. If not, the structure-argument methodology will elicit one through conversation.
+
+## Stage Instructions
+
+Run `/mos:structure-argument` with the user's thesis or claim.
+
+Focus the session on producing:
+- **Core argument** (Minto answer-first statement)
+- **Supporting arguments** (the pillars holding up the core argument)
+- **Evidence for each pillar** (what data or reasoning supports each supporting argument)
+- **Evidence gaps** (where the argument lacks support)
+
+Larry should push for structural clarity -- each level of the pyramid must genuinely support the level above it. Weak pillars get flagged, not ignored.
+
+When the methodology produces its artifact, ensure pipeline provenance is added to frontmatter:
+
+```yaml
+pipeline: thesis
+pipeline_stage: 1
+```
+
+## Output Contract
+
+The following sections from the artifact feed into Stage 2 (challenge-assumptions):
+
+- **Core argument** (Minto answer-first) -- becomes the target for Devil's Advocate interrogation
+- **Supporting arguments** -- become specific assumptions to challenge (each pillar is an assumption)
+- **Evidence gaps** -- become areas for deeper interrogation (where the argument is weakest)
+
+Stage 2 will extract these by scanning `room/problem-definition/` for the most recent artifact with `pipeline: thesis` and `pipeline_stage: 1` in frontmatter.

package/pipelines/thesis/02-challenge-assumptions.md

@@ -0,0 +1,48 @@
+---
+stage: 2
+methodology: challenge-assumptions
+chain: thesis
+input_from: structure-argument
+output_to: build-thesis
+room_section: competitive-analysis
+---
+
+# Stage 2: Challenge Assumptions (Devil's Advocate)
+
+## Input Extraction
+
+Extract from Stage 1 artifact (scan `room/problem-definition/` for most recent artifact with `pipeline: thesis` and `pipeline_stage: 1` in frontmatter):
+
+- **Core argument** -- the top-level claim that everything else supports
+- **Supporting arguments** -- each pillar becomes an assumption to challenge
+- **Evidence gaps** -- areas where the argument is weakest, deserving deepest interrogation
+
+Present to the user: "From your Minto Pyramid, I'm bringing forward: [core argument] as the claim under examination, with [N] supporting assumptions to stress-test and [evidence gaps] as the weakest points."
+
+## Stage Instructions
+
+Run `/mos:challenge-assumptions` with the extracted core argument and supporting claims.
+
+The Devil's Advocate session should be shaped by the Thesis context:
+- Each supporting argument from Stage 1 is treated as an assumption to challenge
+- Evidence gaps from Stage 1 get the hardest interrogation -- these are where the thesis is most vulnerable
+- For each assumption: attempt to disprove it, find counter-evidence, identify conditions under which it fails
+- Classify each assumption after stress-testing: SURVIVED (strong evidence), WOUNDED (partial evidence), KILLED (disproven or unfounded)
+
+When the methodology produces its artifact, ensure pipeline provenance is added to frontmatter:
+
+```yaml
+pipeline: thesis
+pipeline_stage: 2
+pipeline_input: "Core Argument: '[extracted from stage 1]'"
+```
+
+## Output Contract
+
+The following sections from the artifact feed into Stage 3 (build-thesis):
+
+- **Surviving assumptions** -- become thesis pillars (these held up under interrogation)
+- **Killed assumptions** -- become risks to address (acknowledged weaknesses in the thesis)
+- **New questions raised** -- become areas for thesis qualification (what the thesis needs to acknowledge)
+
+Stage 3 will extract these by scanning `room/competitive-analysis/` for the most recent artifact with `pipeline: thesis` and `pipeline_stage: 2` in frontmatter.

package/pipelines/thesis/03-build-thesis.md

@@ -0,0 +1,54 @@
+---
+stage: 3
+methodology: build-thesis
+chain: thesis
+input_from: challenge-assumptions
+output_to: null
+room_section: financial-model
+---
+
+# Stage 3: Build Investment Thesis
+
+## Input Extraction
+
+Extract from Stage 2 artifact (scan `room/competitive-analysis/` for most recent artifact with `pipeline: thesis` and `pipeline_stage: 2` in frontmatter):
+
+- **Surviving assumptions** -- use as thesis pillars (these withstood Devil's Advocate scrutiny)
+- **Killed assumptions** -- use as acknowledged risks (honest about what did not survive)
+- **New questions raised** -- use as thesis qualifications (conditions and limitations)
+
+Present to the user: "From your Devil's Advocate session, I'm bringing forward: [N] surviving assumptions as thesis pillars, [N] killed assumptions as risks to address, and [N] new questions as areas for qualification."
+
+## Stage Instructions
+
+Run `/mos:build-thesis` with the extracted surviving assumptions and risk areas.
+
+The thesis-building session should be shaped by the pipeline context:
+- Thesis pillars come directly from stress-tested surviving assumptions -- these carry weight because they were challenged
+- Risk section incorporates killed assumptions honestly -- investors respect candor about weaknesses
+- Qualifications section addresses the new questions raised during challenge
+- The thesis narrative should reference the interrogation: "We stress-tested N assumptions. M survived..."
+
+When the methodology produces its artifact, ensure pipeline provenance is added to frontmatter:
+
+```yaml
+pipeline: thesis
+pipeline_stage: 3
+pipeline_input: "Surviving Assumptions: '[extracted from stage 2]'"
+```
+
+## Output Contract
+
+Final stage -- no output_to. This completes the Thesis Pipeline.
+
+### What the Full Thesis Pipeline Produced
+
+Across all 3 stages, the Room now contains:
+
+| Room Section | Artifact | From Stage |
+|-------------|----------|------------|
+| problem-definition | Minto Pyramid -- structured argument with pillars and evidence | Stage 1 |
+| competitive-analysis | Devil's Advocate -- assumption survival map, killed claims, new questions | Stage 2 |
+| financial-model | Investment Thesis -- stress-tested thesis with pillars, risks, qualifications | Stage 3 |
+
+The provenance chain (`pipeline: thesis`, `pipeline_stage: 1/2/3`) connects all three artifacts, showing how a raw argument became a stress-tested investment thesis through structured interrogation.

package/pipelines/thesis/CHAIN.md

@@ -0,0 +1,37 @@
+---
+name: thesis
+display_name: Thesis Pipeline
+description: From structured argument to stress-tested investment thesis
+stages: 3
+estimated_time: 60-120min
+venture_stages: [Design, Investment]
+problem_types: [well-defined-complex, well-defined-complicated, ill-defined-complex]
+---
+
+# Thesis Pipeline
+
+## When to Use
+
+User has a venture thesis or argument that needs rigorous stress-testing before presenting to stakeholders or investors. Best for later-stage ventures where the idea is clear but the argument needs structural integrity and evidence.
+
+Typical starting points:
+- "I need to build my investment thesis"
+- "I have an argument but I'm not sure it holds up"
+- "I need to present my venture to investors and want it bulletproof"
+
+## Stage Sequence
+
+1. **structure-argument** -- Build the Minto Pyramid, top-down argument structure
+2. **challenge-assumptions** -- Devil's Advocate stress-tests every supporting claim
+3. **build-thesis** -- Synthesize surviving arguments into a complete investment thesis
+
+## What It Produces
+
+After all 3 stages, the Room will have:
+- **problem-definition:** Minto Pyramid artifact with structured argument hierarchy
+- **competitive-analysis:** Devil's Advocate artifact with assumption survival map
+- **financial-model:** Investment Thesis artifact with thesis pillars, risks, qualifications
+
+## Chain Provenance
+
+Each artifact includes `pipeline: thesis` and `pipeline_stage: N` in frontmatter, creating an inspectable provenance chain. This allows Larry to detect existing pipeline progress and offer resumption.

package/references/brain/causal-directives.md

@@ -0,0 +1,91 @@
+---
+title: Brain Causal Reasoning Directives
+description: >
+  Tells Larry HOW to reason causally when analyzing room artifacts.
+  Brain DIRECTS causal reasoning. KuzuDB STORES causal claims.
+  Brain is READ-ONLY from the causal layer -- no user data written to Brain.
+tier: 0
+version: 1.7.0
+used_by:
+  - commands/causal.md
+  - skills/larry-personality/SKILL.md
+  - scripts/compute-causal.py
+---
+
+# Causal Reasoning Directives
+
+Brain directs Larry's causal reasoning. These are the RULES for how Larry identifies, structures, and communicates causal claims. All causal data is stored in local KuzuDB -- never written to Brain.
+
+## The Three Gaps Larry Must Close
+
+From Duraisamy (2025) "Active Inference AI Systems for Scientific Discovery":
+
+### Gap 1: Abstraction Gap
+**Problem:** Larry sees text tokens. Users need mechanistic understanding.
+**Directive:** For every causal claim, Larry MUST identify the MECHANISM -- not just "A causes B" but HOW A produces B through a specific physical, economic, or strategic process.
+
+**Example:**
+- BAD: "Ceramic AM enables new markets"
+- GOOD: "Gradient architecture eliminates CTE mismatch at metal-ceramic interfaces (mechanism: graded transition absorbs differential thermal expansion), which prevents thermal shock fracture in etch chamber liners (failure mode), enabling higher plasma temperatures (performance)"
+
+### Gap 2: Reasoning Gap
+**Problem:** Pattern completion is not causal inference.
+**Directive:** Larry MUST distinguish correlation from causation. Use the dual-process approach:
+1. THINKING mode: Generate causal hypotheses (divergent)
+2. REASONING mode: Test each hypothesis for causal coherence (convergent)
+
+**Causal Coherence Tests:**
+- Does a physical/economic mechanism exist?
+- Does the direction make sense? (A causes B, not B causes A)
+- Are there confounders? (C causes both A and B, creating false A->B)
+- Is this correlation masquerading as causation?
+
+### Gap 3: Reality Gap
+**Problem:** Internal models diverge from external reality.
+**Directive:** Every causal claim MUST include a falsifiable prediction -- something testable that would DISPROVE the claim if the test fails.
+
+**Example:**
+- Claim: "Qualification timeline is the real moat, not material properties"
+- Prediction: "If true, we should see customers willing to pay 30%+ premium for pre-qualified suppliers, even with comparable material specs. Interview 5 procurement leads -- if <3 confirm, the claim is wrong."
+
+## Causal Claim Structure
+
+Every causal claim Larry generates or validates must have these 7 fields:
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| cause | YES | What produces the effect |
+| effect | YES | What happens as a result |
+| mechanism | YES | HOW the cause produces the effect |
+| confidence | YES | 0-1 scale based on evidence strength |
+| evidence | YES | Which room artifacts support this claim |
+| falsifiable_prediction | YES | What would disprove this claim |
+| domain | YES | materials, business, competitive, financial, team, legal, general |
+
+**Confidence Calibration:**
+- 0.7+: observed (multiple artifacts + external validation + mechanism confirmed)
+- 0.5-0.69: asserted (clear mechanism + some artifact support, untested prediction)
+- 0.3-0.49: inferred (plausible mechanism, single artifact, no external validation)
+- 0.0-0.29: speculative (interesting hypothesis, no supporting evidence)
+
+## Causal Analysis by Problem Type
+
+### Un-Defined Problems
+**Directive:** Don't assert causation yet. Map POSSIBLE causal pathways. Use "might cause" language.
+
+### Ill-Defined Problems
+**Directive:** Identify competing causal explanations. Present contradictions explicitly. Use contradiction detection.
+
+### Well-Defined Problems
+**Directive:** Trace complete causal chains. Validate mechanisms. Generate falsifiable predictions.
+
+### Wicked Problems
+**Directive:** Map causal loops (feedback). Surface where intervention has leverage. Accept that causation is circular.
+
+## Integration with Pipeline
+
+Larry should reference these directives when:
+1. Running /mos:causal extract -- enforce Three Gaps on every claim
+2. Running /mos:causal trace -- narrate chains with mechanisms
+3. Running /mos:causal predict -- generate predictions grounded in Gap 3
+4. During regular conversation -- when assumptions stack up, suggest causal analysis

package/references/brain/causal-enrichment.cypher

@@ -0,0 +1,165 @@
+// Brain Causal Framework Enrichment
+// Phase 52: BRAIN-01 through BRAIN-06
+// Execute via mcp__neo4j-brain__write_neo4j_cypher
+//
+// IMPORTANT: Before running any write statements, run the discovery queries
+// in the "Discovery" section to verify exact node names. Replace placeholder
+// names below with exact names from discovery results.
+//
+// Generated: 2026-04-05
+// Requirements: BRAIN-01, BRAIN-02, BRAIN-03, BRAIN-04, BRAIN-05, BRAIN-06
+
+// ============================================================================
+// SECTION 0: DISCOVERY (run FIRST via mcp__neo4j-brain__read_neo4j_cypher)
+// ============================================================================
+
+// Query A: Get all Framework node names (verify exact spelling)
+// MATCH (f:Framework) RETURN f.name AS name LIMIT 50
+
+// Query B: Get all Concept node names
+// MATCH (c:Concept) RETURN c.name AS name LIMIT 50
+
+// Query C: Check VentureStage nodes
+// MATCH (v:VentureStage) RETURN v.name AS name LIMIT 20
+
+// Query D: Check existing edge types on Framework nodes
+// MATCH (f:Framework)-[r]->() RETURN DISTINCT type(r) AS rel_type LIMIT 30
+
+// Query E: Check if Falsifiability or Hypothesis Tree exist
+// MATCH (f:Framework) WHERE f.name CONTAINS 'Falsif' OR f.name CONTAINS 'Hypothesis' RETURN f.name LIMIT 10
+
+// ============================================================================
+// SECTION 1: BRAIN-03 -- Create Theory of Change Framework node
+// ============================================================================
+
+MERGE (f:Framework {name: 'Theory of Change'})
+ON CREATE SET f.description = 'Forward causal reasoning: articulate the causal pathway from activities to outcomes. Maps assumptions about how change happens.',
+              f.category = 'causal',
+              f.created = datetime()
+
+// ============================================================================
+// SECTION 2: BRAIN-04 -- Create Causal Reasoning parent Concept node
+// ============================================================================
+
+MERGE (c:Concept {name: 'Causal Reasoning'})
+ON CREATE SET c.description = 'Parent concept connecting causal analysis frameworks: root cause analysis, systems thinking, causal loop diagrams, scenario analysis, and theory of change.',
+              c.created = datetime()
+
+// Link each causal framework to the Causal Reasoning concept
+// NOTE: Use exact names from Query A. Names below are best-guess from Brain schema.
+
+MATCH (f:Framework {name: 'Root Cause Analysis'}), (c:Concept {name: 'Causal Reasoning'})
+MERGE (f)-[:RELATED_TO]->(c)
+
+MATCH (f:Framework {name: 'Systems Thinking'}), (c:Concept {name: 'Causal Reasoning'})
+MERGE (f)-[:RELATED_TO]->(c)
+
+MATCH (f:Framework {name: 'Causal Loop Diagrams'}), (c:Concept {name: 'Causal Reasoning'})
+MERGE (f)-[:RELATED_TO]->(c)
+
+MATCH (f:Framework {name: 'Scenario Analysis Framework'}), (c:Concept {name: 'Causal Reasoning'})
+MERGE (f)-[:RELATED_TO]->(c)
+
+MATCH (f:Framework {name: 'Theory of Change'}), (c:Concept {name: 'Causal Reasoning'})
+MERGE (f)-[:RELATED_TO]->(c)
+
+// ============================================================================
+// SECTION 3: BRAIN-01 -- Wire FEEDS_INTO chains
+// ============================================================================
+
+// Chain: Root Cause Analysis -> Systems Thinking -> Causal Loop Diagrams -> Scenario Analysis
+MATCH (a:Framework {name: 'Root Cause Analysis'}), (b:Framework {name: 'Systems Thinking'})
+MERGE (a)-[:FEEDS_INTO]->(b)
+
+MATCH (a:Framework {name: 'Systems Thinking'}), (b:Framework {name: 'Causal Loop Diagrams'})
+MERGE (a)-[:FEEDS_INTO]->(b)
+
+MATCH (a:Framework {name: 'Causal Loop Diagrams'}), (b:Framework {name: 'Scenario Analysis Framework'})
+MERGE (a)-[:FEEDS_INTO]->(b)
+
+// Branch: Systems Thinking -> Reverse Salient Analysis
+MATCH (a:Framework {name: 'Systems Thinking'}), (b:Framework {name: 'Reverse Salient Analysis'})
+MERGE (a)-[:FEEDS_INTO]->(b)
+
+// ============================================================================
+// SECTION 4: BRAIN-02 -- CO_OCCURS edges (bidirectional)
+// ============================================================================
+
+// Root Cause Analysis <-> Six Thinking Hats
+MATCH (a:Framework {name: 'Root Cause Analysis'}), (b:Framework {name: 'Six Thinking Hats'})
+MERGE (a)-[:CO_OCCURS]->(b)
+MERGE (b)-[:CO_OCCURS]->(a)
+
+// Systems Thinking <-> Reverse Salient Analysis
+MATCH (a:Framework {name: 'Systems Thinking'}), (b:Framework {name: 'Reverse Salient Analysis'})
+MERGE (a)-[:CO_OCCURS]->(b)
+MERGE (b)-[:CO_OCCURS]->(a)
+
+// Cynefin <-> Root Cause Analysis
+MATCH (a:Framework {name: 'Cynefin Framework'}), (b:Framework {name: 'Root Cause Analysis'})
+MERGE (a)-[:CO_OCCURS]->(b)
+MERGE (b)-[:CO_OCCURS]->(a)
+
+// ============================================================================
+// SECTION 5: BRAIN-05 -- TYPICAL_AT venture stage mappings
+// ============================================================================
+
+// Create VentureStage nodes if they do not exist (verify with Query C first)
+MERGE (s:VentureStage {name: 'Pre-Opportunity'})
+MERGE (s2:VentureStage {name: 'Opportunity Identified'})
+MERGE (s3:VentureStage {name: 'Problem Validation'})
+
+// Map causal frameworks to venture stages
+MATCH (f:Framework {name: 'Root Cause Analysis'}), (s:VentureStage {name: 'Opportunity Identified'})
+MERGE (f)-[:TYPICAL_AT]->(s)
+
+MATCH (f:Framework {name: 'Systems Thinking'}), (s:VentureStage {name: 'Pre-Opportunity'})
+MERGE (f)-[:TYPICAL_AT]->(s)
+
+MATCH (f:Framework {name: 'Reverse Salient Analysis'}), (s:VentureStage {name: 'Pre-Opportunity'})
+MERGE (f)-[:TYPICAL_AT]->(s)
+
+MATCH (f:Framework {name: 'Theory of Change'}), (s:VentureStage {name: 'Problem Validation'})
+MERGE (f)-[:TYPICAL_AT]->(s)
+
+// ============================================================================
+// SECTION 6: BRAIN-06 -- Link Falsifiability and Hypothesis Tree
+// ============================================================================
+
+// NOTE: Use exact names from Query E. Names below are best-guess.
+
+// Link to Causal Reasoning concept
+// NOTE: Falsifiability is a Concept, Logic Trees is a Concept (not Framework labels)
+MATCH (f:Concept {name: 'Falsifiability'}), (c:Concept {name: 'Causal Reasoning'})
+MERGE (f)-[:RELATED_TO]->(c)
+
+MATCH (f:Concept {name: 'Logic Trees (Issue, Hypothesis, Decision)'}), (c:Concept {name: 'Causal Reasoning'})
+MERGE (f)-[:RELATED_TO]->(c)
+
+// FEEDS_INTO from Theory of Change to Logic Trees
+MATCH (a:Framework {name: 'Theory of Change'}), (b:Concept {name: 'Logic Trees (Issue, Hypothesis, Decision)'})
+MERGE (a)-[:FEEDS_INTO]->(b)
+
+// FEEDS_INTO from Logic Trees to Falsifiability
+MATCH (a:Concept {name: 'Logic Trees (Issue, Hypothesis, Decision)'}), (b:Concept {name: 'Falsifiability'})
+MERGE (a)-[:FEEDS_INTO]->(b)
+
+// ============================================================================
+// VERIFICATION QUERIES (run via mcp__neo4j-brain__read_neo4j_cypher)
+// ============================================================================
+
+// Verify BRAIN-01: FEEDS_INTO chain
+// MATCH (a:Framework)-[:FEEDS_INTO]->(b:Framework)
+// WHERE a.name CONTAINS 'Root Cause' OR a.name CONTAINS 'Systems' OR a.name CONTAINS 'Causal Loop'
+// RETURN a.name AS from_fw, b.name AS to_fw
+// LIMIT 10
+
+// Verify BRAIN-04: Causal Reasoning concept connections
+// MATCH (f:Framework)-[:RELATED_TO]->(c:Concept {name: 'Causal Reasoning'})
+// RETURN f.name AS framework
+// LIMIT 10
+
+// Verify BRAIN-05: TYPICAL_AT edges
+// MATCH (f:Framework)-[:TYPICAL_AT]->(s:VentureStage)
+// RETURN f.name AS framework, s.name AS stage
+// LIMIT 10

package/references/brain/command-triggers-schema.md

@@ -0,0 +1,226 @@
+# Brain Command Trigger Schema
+
+## Purpose
+
+Commands are first-class nodes in the Neo4j Brain. They have typed relationships to Frameworks, ProblemTypes, VentureStages, and Signals that define WHEN they should fire. The Brain doesn't just recommend frameworks -- it recommends ACTIONS mapped to specific /mos: commands with trigger conditions.
+
+## Node: Command
+
+```cypher
+CREATE (c:Command {
+  name: '/mos:find-analogies',
+  slug: 'find-analogies',
+  category: 'intelligence',          // infrastructure | methodology | intelligence | export | meeting | funding
+  description: 'Cross-domain analogy discovery via structural isomorphism',
+  jtbd_when: 'stuck on a problem that feels unique to your domain',
+  jtbd_want: 'discover that other industries already solved the same structural conflict',
+  jtbd_so: 'adapt their approach instead of inventing from scratch',
+  time_estimate: '5 minutes',
+  flags: ['--brain', '--external'],   // available flags
+  min_sections: 2,                    // minimum populated sections to be relevant
+  requires_brain: false,              // works without Brain (but better with)
+  powerhouse: true                    // v1.6.0+ feature
+})
+```
+
+## Relationships
+
+### TRIGGERED_BY_SIGNAL
+
+Links a Command to the Room Signal types that should trigger it.
+
+```cypher
+// When a CONTRADICTS edge exists between sections -> suggest find-analogies
+CREATE (cmd:Command {name: '/mos:find-analogies'})-[:TRIGGERED_BY_SIGNAL {
+  signal_type: 'TENSION',            // TENSION | BLIND_SPOT | BOTTLENECK | PATTERN | SURPRISE
+  priority: 1,                        // 1=highest, 5=lowest
+  condition: 'contradicts_count >= 1',
+  jtbd_framing: 'When your Sections have unresolved Tensions, you want to see how other domains resolved the same structural conflict'
+}]->(sig:SignalType {name: 'TENSION'})
+
+// When 3+ sections have gaps -> suggest act --swarm
+CREATE (cmd:Command {name: '/mos:act --swarm'})-[:TRIGGERED_BY_SIGNAL {
+  signal_type: 'BLIND_SPOT',
+  priority: 1,
+  condition: 'gap_count >= 3',
+  jtbd_framing: 'When 3+ Sections have Blind Spots, you want to fill them all at once instead of one at a time'
+}]->(sig:SignalType {name: 'BLIND_SPOT'})
+
+// When reverse salients detected -> suggest specific methodology for lagging section
+CREATE (cmd:Command {name: '/mos:act'})-[:TRIGGERED_BY_SIGNAL {
+  signal_type: 'BOTTLENECK',
+  priority: 2,
+  condition: 'reverse_salient_count >= 1',
+  jtbd_framing: 'When a Section lags behind the others, you want to close the gap before it compounds'
+}]->(sig:SignalType {name: 'BOTTLENECK'})
+```
+
+### FOLLOWS_FRAMEWORK
+
+Links a Command to the Framework it should follow (chaining).
+
+```cypher
+// After JTBD analysis -> suggest Blue Ocean
+CREATE (cmd:Command {name: '/mos:dominant-designs'})-[:FOLLOWS_FRAMEWORK {
+  confidence: 0.85,
+  reason: 'JTBD reveals customer needs; dominant designs reveals competitive whitespace',
+  hop_distance: 1
+}]->(f:Framework {name: 'Jobs-to-Be-Done'})
+
+// After find-analogies -> suggest validate (stress-test the analogy)
+CREATE (cmd:Command {name: '/mos:validate'})-[:FOLLOWS_FRAMEWORK {
+  confidence: 0.90,
+  reason: 'Analogies must be stress-tested before acting on them',
+  hop_distance: 1
+}]->(f:Framework {name: 'Design-by-Analogy'})
+
+// After grade --full -> suggest act --swarm on weak sections
+CREATE (cmd:Command {name: '/mos:act --swarm'})-[:FOLLOWS_FRAMEWORK {
+  confidence: 0.80,
+  reason: 'Grading reveals gaps; swarm attacks them in parallel',
+  hop_distance: 1
+}]->(f:Framework {name: 'Assessment'})
+```
+
+### RELEVANT_AT_STAGE
+
+Links a Command to VentureStages where it's most impactful.
+
+```cypher
+// find-analogies is most powerful at Discovery and Design stages
+CREATE (cmd:Command {name: '/mos:find-analogies'})-[:RELEVANT_AT_STAGE {
+  impact: 'high',
+  reason: 'Discovery needs fresh perspectives; Design needs proven patterns'
+}]->(stage:VentureStage {name: 'Discovery'})
+
+// grade --full becomes critical at Investment stage
+CREATE (cmd:Command {name: '/mos:grade --full'})-[:RELEVANT_AT_STAGE {
+  impact: 'critical',
+  reason: 'Investment stage demands rigor across every Section'
+}]->(stage:VentureStage {name: 'Investment'})
+
+// scout is always relevant but especially at Validation
+CREATE (cmd:Command {name: '/mos:scout'})-[:RELEVANT_AT_STAGE {
+  impact: 'high',
+  reason: 'Validation stage has deadlines and competitor dynamics'
+}]->(stage:VentureStage {name: 'Validation'})
+```
+
+### ADDRESSES_PROBLEM_TYPE
+
+Links a Command to ProblemTypes it solves (via multi-hop through Frameworks).
+
+```cypher
+// find-analogies addresses wicked problems (via Design-by-Analogy framework)
+CREATE (cmd:Command {name: '/mos:find-analogies'})-[:ADDRESSES_PROBLEM_TYPE {
+  via_framework: 'Design-by-Analogy',
+  effectiveness: 0.85
+}]->(pt:ProblemType {name: 'wicked'})
+
+// act --swarm addresses complex problems with multiple dimensions
+CREATE (cmd:Command {name: '/mos:act --swarm'})-[:ADDRESSES_PROBLEM_TYPE {
+  via_framework: 'Multiple simultaneous frameworks',
+  effectiveness: 0.90
+}]->(pt:ProblemType {name: 'ill-defined-complex'})
+```
+
+### RESOLVES_TENSION_BETWEEN
+
+Links a Command to Framework pairs that commonly produce contradictions.
+
+```cypher
+// find-analogies resolves tensions between pricing frameworks and competitive positioning
+CREATE (cmd:Command {name: '/mos:find-analogies'})-[:RESOLVES_TENSION_BETWEEN {
+  framework_a: 'Lean Canvas',
+  framework_b: 'Competitive Analysis',
+  resolution_pattern: 'Cross-domain structural isomorphism finds how other industries resolved pricing vs positioning'
+}]->(tension:TensionType {name: 'pricing_vs_positioning'})
+```
+
+## Multi-Hop Proactive Query
+
+The power of this schema is MULTI-HOP reasoning. The Brain can traverse:
+
+```
+User's Room State
+  -> Current Frameworks (from Room artifacts)
+    -> FEEDS_INTO relationships (what comes next)
+      -> Command nodes (which /mos: command delivers it)
+        -> TRIGGERED_BY_SIGNAL (is the trigger condition met?)
+          -> Return ranked command suggestion with full JTBD framing
+```
+
+### Query: brain_proactive_command (Pattern 10d)
+
+```cypher
+// Multi-hop: Room frameworks -> next framework -> command -> trigger check
+MATCH (current:Framework)<-[:FOLLOWS_FRAMEWORK]-(cmd:Command)
+WHERE current.name IN $room_frameworks
+
+// Check if command is relevant at this venture stage
+OPTIONAL MATCH (cmd)-[stage_rel:RELEVANT_AT_STAGE]->(stage:VentureStage {name: $venture_stage})
+
+// Check if command is triggered by current signals
+OPTIONAL MATCH (cmd)-[trigger:TRIGGERED_BY_SIGNAL]->(sig:SignalType)
+
+// Get success data
+OPTIONAL MATCH (current)-[:APPLIED_IN]->(example:Example)
+WHERE example.grade_numeric >= 80
+
+RETURN cmd.name AS command,
+       cmd.jtbd_when AS when_situation,
+       cmd.jtbd_want AS want_motivation,
+       cmd.jtbd_so AS so_outcome,
+       cmd.time_estimate AS time,
+       cmd.flags AS available_flags,
+       stage_rel.impact AS stage_impact,
+       trigger.signal_type AS triggered_by,
+       trigger.condition AS trigger_condition,
+       trigger.jtbd_framing AS trigger_framing,
+       count(example) AS success_count
+ORDER BY stage_rel.impact DESC, trigger.priority ASC, success_count DESC
+LIMIT 5
+```
+
+**Parameters:**
+- `$room_frameworks` -- frameworks used in Room (from artifact frontmatter)
+- `$venture_stage` -- from STATE.md
+
+**Output:** Ranked command suggestions with full JTBD framing, trigger conditions, and success data from real projects.
+
+## Seeding Script
+
+The Command nodes and trigger relationships need to be seeded into Neo4j. Create a script that:
+
+1. Reads all commands/*.md files
+2. Extracts: name, description, allowed-tools, category
+3. Generates JTBD statements from the command's purpose
+4. Creates Command nodes with relationships to:
+   - Frameworks they follow (from methodology chaining rules)
+   - VentureStages they're relevant at (from problem-types.md)
+   - SignalTypes that trigger them (from proactive-intelligence patterns)
+5. Runs the Cypher via `mcp__neo4j-brain__write_neo4j_cypher`
+
+Script location: `scripts/seed-brain-commands.cjs`
+
+## The Intelligence Hierarchy (Updated)
+
+```
+LEVEL 3 (Brain + Room + Signals):
+  brain_proactive_command (Pattern 10d)
+  Multi-hop: frameworks -> commands -> triggers -> JTBD
+  Calibrated from 100+ real projects
+  Knows which sequences ACTUALLY produced results
+
+LEVEL 2 (Room + Local Fabric):
+  Larry's JTBD provoked suggestions (every 3-7 turns)
+  KuzuDB Tensions, Bottlenecks, Surprises, Convergences
+  Good but not cross-venture calibrated
+
+LEVEL 1 (No Room):
+  Generic stage-based defaults
+  methodology/index.md routing table
+  Better than nothing
+```
+
+Brain-connected users get LEVEL 3: the Brain literally tells Larry which command to suggest, when, and why -- backed by data from 100+ real ventures. The JTBD framing is baked into the Command node itself. Larry just reads it and presents it naturally.