Skill Detail

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.

Developer ToolsMulti-Framework
Developer Tools Multi-Framework Security Reviewed
⭐ 2.1k GitHub stars ⬇ 2.2k/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill build-persistent-codebase-context-graphs-with-graft Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Node.js, npm or npx, Git, Claude Code/Codex/Cursor/Gemini or an MCP-compatible coding-agent setup
Install & setup
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.
Author
NanoNets
Publisher
Organization
Last updated
Aug 12, 2026
Quick brief

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.

How it works

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.