← ClaudeAtlas

codescapelisted

How Loom agents should use Codescape (the code-graph MCP) when a project exposes it — the graph for structure, coordinates, and reachability (orient the shape, get exact file:line, ask "what could render / what scenarios are possible"), then a small number of targeted reads at those coordinates. NOT a nicer index to grep from; do not re-orient by reading. Shipped and kept current by Loom.
DanielC000/loom · ★ 6 · AI & Automation · score 78
Install: claude install-skill DanielC000/loom
# codescape Codescape is a **code-graph MCP** — a per-project, ingested snapshot of the repo's structure. When your project exposes the Codescape MCP tools (`overview` / `list_flows` / `describe_symbol` / `what_touches` / `trace_flow` / `boundary_map` / `render_tree`), it is your PRIMARY orientation instrument, not a fallback. **The one thing to internalize:** use the graph for **structure, coordinates, and reachability**, then open files ONLY to read the exact bytes you must verify or edit — at the coordinates the graph gave you. The graph REPLACES orient + locate; reading is only confirm/edit. If you re-derive the map by reading, or grep to LOCATE what the graph already pinpoints, you throw the whole point away — a measured speed / fewer-reads win collapses back into verify-by-reading. ## Use the graph for three things - **ORIENT — the shape.** What exists and how flows run through the system end to end (frontend + backend, across parts/services). Reach a correct mental map with FAR fewer reads than opening files. Start here (`overview` / `list_flows` / `trace_flow`) before you open anything. - **LOCATE — the coordinates.** Which `file:line` each piece lives at. `describe_symbol` / `overview` / `what_touches` / `trace_flow` return citation-grade `file:line` — take the exact coordinates FROM the graph; don't grep to find what it already pinpoints. - **REACHABILITY — what could happen.** "What could render" (components + conditional branches) and "what scenarios