MindrianOS -- AI innovation co-founder. 70+ commands, 66 MCP tools, 8 agents, 9 hooks. Opportunity Bank, 3-mode conversation entry, intelligence loop. PWS methodology + Brain knowledge graph. Claude Code + Desktop + Cowork + ChatGPT via MCP Apps.
Agent
Fetch ONE navigator-approved, composer-produced audited query string for /mos:find-analogies --external (Tavily, falling back to WebSearch with the identical string), and extract a structural SAPPhIRE mapping per result. Never composes, rephrases, expands, or supplements the query; never writes to Brain.
Agent
Query the Brain teaching graph with natural language. Translates to Cypher, synthesizes insights, never exposes raw data.
Agent
Search public sources for ONE tracked competitor's recent developments (funding, launch, pivot, acquisition) and check them against the orchestrator's supplied claims. Read-only, structured-JSON-only, never writes, never calls Brain, never gates.
Agent
Execute one /mos: methodology per invocation in an isolated context. Files the artifact and returns a structured summary.
Agent
PROACTIVELY grade room artifacts against calibrated student submissions when evidence review or assessment is implied.
Agent
Adversarial per-category grant-rubric reviewer for /mos:grade-grant's reviewer-panel examination mode -- examines ONE rubric category in isolation, then (as the ruling consolidator) renders the holistic verdict across all seven.
Agent
PROACTIVELY surface investor objections when the room approaches a pitch, gate, or funding decision. Adversarial reviewer.
Agent
Larry, the PWS methodology teaching partner. Engage for venture conversations, methodology guidance, and room reasoning.
Agent
Extract atomic claims from a FULL meeting transcript through ONE named perspective lens (references/meeting/extraction-perspectives.md). Read-only, structured-JSON-only, never writes, never gates, never asks the user anything.
Agent
Invoke De Bono hats and multi-perspective analysis when the user asks for a hat, persona, or tension-map view.
Agent
Gather and verify external intelligence via Tavily + Brain cross-reference. Files sourced artifacts with provenance.
Agent
Surfaces reverse-salient findings (Engine 1 Act 1) as F.0 Decision Gates with persona-aware framing. Sibling to larry-extended; not a replacement.
Agent
Confirm or correct a stub classifier's section guess for one guessed-section group of /mos:vault import rows, reading each source file body against the venture context. Read-only, structured-data-only, never writes classifications.md or MANIFEST.json.