grainulation

Fast pre-flight health check for all Grainulator MCP servers. Pings each server once, reports status in a table, and provides exact fix commands for any that are down. Use before starting any Grainulator session to avoid wasting time on MCP disconnections.

Generate a compiled decision brief from the current sprint's claims.

Generate a presentation deck from the compiled sprint data.

Size-efficient URL fetch with semantic extraction. Use for ad-hoc web research when you want content without the raw HTML overhead.

Corroborate a claim against an external source URL.

Intent router that detects user intent from plain messages and dispatches to the appropriate skill.

Sprint analytics — type distributions, stale claims, velocity, prediction scoring

Multi-sprint orchestration — view dependency graph, dispatch next ready sprint

Run a task as a recursive convergence loop, not a fixed checklist: investigate the most decisive open question, record what you learn as typed evidence in a ledger, let a compiler score what is still weak or contradictory, revise beliefs that new evidence overturns, and loop until the evidence converges — then deliver. Continuously spins up subagents and uses whatever skills/connectors exist. Verbose by default. Trigger on /bean, on "do this thoroughly / be systematic / deep work mode", OR when a task spans multiple files, sources, or sessions. Do NOT trigger on ordinary tasks a direct attempt handles fine. Auto-trigger applies only where the runtime allows it; on Codex, bean runs only on an explicit /bean.