graftlisted

# graft `graft` is a context graph over the repo: every file and symbol as a node, `calls`/`imports`/`contains` as edges, kept next to the code in `graft/`. Its whole point is that finding code should cost one ranked answer, not a widening sequence of greps. Requires the `graft` CLI on the machine (`npm i -g @nanonets/graft`). No API key and no model call for anything below — every command here is a local graph read. ## Pick the command from the question | The question you actually have | Command | |---|---| | "How does X work?" / "Where is X handled?" | `graft ask "<question>" --source -n 5` | | "Every place this string/pattern appears" | `graft grep "<pattern>"` | | "What does this file expose?" | `graft skeleton <path>` | | "Who calls this?" — before a rename or delete | `graft callers <symbol> --depth 2` | | "What does this call?" | `graft callers <symbol> --direction out` | | "I have never seen this repo" | `graft map` | `--source` is the flag that matters on `ask`: it inlines the code at each hit, so the answer replaces opening the files rather than pointing at them. Reach for `--full` only when a crux excerpt genuinely cut something you need. ## Rules 1. **No index, no graft.** If `graft/` is absent, say so and use `/search`; do not build one mid-task without asking. 2. **`ask` before `grep`.** `ask` is ranked and graph-aware; `grep` is exhaustive and unranked. Use `grep` when you need *every* occurrence, not to start a hunt. 3. **Depth is a claim about risk.**