graphylisted

# graphy graphy turns a folder of source code into a structured knowledge graph: nodes are top-level declarations (functions, classes, structs, modules, …) and edges are imports, calls, and explicit references. Once a workspace has been graphed, you can query it through the `graphy` MCP server's tools instead of grepping. The plugin auto-builds the graph the first time you read source in a workspace and rebuilds in the background after edits, so the MCP tools are usually fresh. ## When to use this skill Reach for graphy first whenever you would otherwise: - Grep for a symbol name to find its definition or callers - Read a directory tree to figure out what files implement a feature - Trace how data flows between two modules - Audit which third-party packages a file depends on - Spot god-objects, high-coupling hotspots, or hidden cycles The graph is cheaper to query than re-reading files, deduplicates results across re-exports, and produces typed edges (`calls`, `imports`, `references`) so the answer is precise. ## Tools The `graphy` MCP server exposes five tools. Use them through the standard MCP tool-call mechanism. | Tool | Input | Returns | |------------------|------------------------------------------------|-------------------------------------------------------------------------| | `stats` | `{}` |