Skip to content

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

README: clarify --watch auto-sync behavior for code vs docs

Safi014758f61d43
diff --git a/README.md b/README.md
index 62549802b..e89fbaa42 100644
--- a/README.md
+++ b/README.md
@@ -69,7 +69,7 @@ When the user types `/graphify`, invoke the Skill tool with `skill: "graphify"`
/graphify path "DigestAuth" "Response"
/graphify explain "SwinTransformer"
-/graphify ./raw --watch # auto-update graph whenever files change
+/graphify ./raw --watch # auto-sync graph as files change (code: instant, docs: notifies you)
/graphify ./raw --wiki # build agent-crawlable wiki (index.md + article per community)
/graphify ./raw --svg # export graph.svg
/graphify ./raw --graphml # export graph.graphml (Gephi, yEd)
@@ -96,6 +96,8 @@ Works with any mix of file types:
**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files.
+**Auto-sync** (`--watch`) - run in a background terminal and the graph updates itself as your codebase changes. Code file saves trigger an instant rebuild (AST only, no LLM). Doc/image changes notify you to run `--update` for the LLM re-pass. Useful for agentic workflows where multiple agents are writing code in parallel — the graph stays current between waves automatically.
+
**Wiki** (`--wiki`) - Wikipedia-style markdown articles per community and god node, with an `index.md` entry point. Point any agent at `index.md` and it can navigate the knowledge base by reading files instead of parsing JSON.
Every edge is tagged `EXTRACTED`, `INFERRED`, or `AMBIGUOUS` - you always know what was found vs guessed.