From mos
Brain enrichment for Larry. Passive: weaves graph context into responses. Proactive: surfaces contradictions and gaps. Active when Brain API key is set (MINDRIAN_BRAIN_KEY in .env) or Brain MCP server is configured.
npx claudepluginhub jsagir/mindrian-os-pluginThis skill uses the workspace's default tool permissions.
Check Brain availability in order:
Conducts multi-round deep research on GitHub repos via API and web searches, generating markdown reports with executive summaries, timelines, metrics, and Mermaid diagrams.
Dynamically discovers and combines enabled skills into cohesive, unexpected delightful experiences like interactive HTML or themed artifacts. Activates on 'surprise me', inspiration, or boredom cues.
Generates images from structured JSON prompts via Python script execution. Supports reference images and aspect ratios for characters, scenes, products, visuals.
Check Brain availability in order:
MINDRIAN_BRAIN_KEY env var (CLI users)mcp__mindrian-brain__brain_schema tool (Desktop/Cowork MCP)mcp__neo4j-brain__get_neo4j_schema tool (legacy)Any success = Brain active. All fail = silent fallback. Never mention failures to user.
Pinecone RESOURCE_EXHAUSTED (429): fall back to Neo4j Cypher only via brain_query.
When Brain detection fails AND request would benefit (framework queries, grading, cross-domain): answer with local references first, then offer once: "I'd give you more here with Brain connected -- /mos:setup brain"
When the user is discussing team, leadership, or working in team-execution section:
MATCH (f:Framework)-[:RELATED_TO]->(:Concept {name: 'Causal Reasoning'})
WHERE f.name IN ['Tuckman Team Stages', 'Psychological Safety', 'Adaptive Leadership',
'Emotional Intelligence in Leadership', 'High-Performing Teams']
OPTIONAL MATCH (f)-[:TYPICAL_AT]->(s:VentureStage {name: $venture_stage})
RETURN f.name, s IS NOT NULL AS matches_stage
ORDER BY matches_stage DESC
MATCH path = (f:Framework {name: $current_framework})-[:FEEDS_INTO*1..3]->(next:Framework)
WHERE next.name IN ['Adaptive Leadership', 'Situational Leadership', 'High-Performing Teams',
'Distributed Leadership', 'Systems Leadership', 'Transformational Leadership']
RETURN next.name AS suggested, [r IN relationships(path) | r.confidence] AS confidence
ORDER BY confidence DESC LIMIT 3
After room changes and session start:
On SessionStart, if room has team-execution entries:
MATCH (f:Framework)-[:TYPICAL_AT]->(s:VentureStage {name: $stage})
WHERE f.name IN ['Tuckman Team Stages', 'Psychological Safety', 'Adaptive Leadership',
'Emotional Intelligence in Leadership', 'High-Performing Teams',
'Servant Leadership', 'Distributed Leadership', 'Transformational Leadership']
RETURN f.name AS available_framework
frameworks_used)Brain has Command nodes linked to Frameworks, VentureStages, SignalTypes. Level 3 intelligence from 100+ real projects.
Query brain_proactive_command for ranked suggestions with JTBD framing, trigger conditions, stage impact. Pick top match for current Room Signals. Present via JTBD formula from Command node fields.
Multi-hop: Room frameworks -> FOLLOWS_FRAMEWORK -> Command -> TRIGGERED_BY_SIGNAL -> Signals -> RELEVANT_AT_STAGE -> Stage
Fallback: local Room heuristics from larry-personality provoked suggestions.
Delegate to agents/brain-query.md for: 2+ graph hops, explicit connection exploration, cross-domain discovery, multi-venture patterns, deep proactive reasoning.
Always use brain_ask first -- natural language, auto-routes Pinecone/Neo4j, handles fallback. Only use brain_query (raw Cypher) for specific complex queries.
| Surface | Smart | Neo4j | Pinecone | Schema |
|---|---|---|---|---|
| mindrian-brain | brain_ask | brain_query | brain_search | brain_schema |
| neo4j-brain (legacy) | N/A | read_neo4j_cypher | search-records | get_neo4j_schema |