Build Persistent Codebase Context Graphs with Graft
Build and maintain a repository-local context graph so coding agents can orient inside large codebases without rediscovering the same structure every session.
npx skills add agentskillexchange/skills --skill build-persistent-codebase-context-graphs-with-graft
npm install -g @nanonets/graft or run npx @nanonets/graft init; use graft init --dry-run first to inspect planned file changes, then build and wire the graph into the selected coding-agent workflow.Use Graft when an operator wants Claude Code, Codex, Cursor, Gemini, or another coding agent to work against a durable map of a repository instead of repeatedly exploring files from scratch. The agent/operator installs the CLI, runs Graft in the project, reviews the generated graph files, and wires the graph or MCP tools into coding-agent sessions for faster repo orientation, dependency tracing, and implementation planning. This is not a generic product listing: the bounded workflow is to generate, refresh, and use a local codebase knowledge graph as agent context for repository work.
What this skill actually does
Inputs and prerequisites: Node.js, npm or npx, Git, Claude Code/Codex/Cursor/Gemini or an MCP-compatible coding-agent setup.
Setup notes: Install with npm install -g @nanonets/graft or run npx @nanonets/graft init ; use graft init –dry-run first to inspect planned file changes, then build and wire the graph into the selected coding-agent workflow.
Source and verification boundary: use https://graft.nanonets.ai as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.