Skip to content

t1k:graphify

FieldValue
Modulet1k-maintainer
Version4.10.58
Efforthigh
Tools—

Keywords: ast, code-analysis, codebase-understanding, graphify, knowledge-graph, tree-sitter

/t1k:graphify
[path] [--mcp|--report|--watch]

Turn any folder of code, docs, papers, or images into a queryable knowledge graph. Uses tree-sitter AST for code (20 languages), Whisper for audio/video, and LLM subagents for documents.

Pre-flight Step 0 — Fuzzy plan/path arg resolution (MANDATORY)

Section titled “Pre-flight Step 0 — Fuzzy plan/path arg resolution (MANDATORY)”

If the user provides a fuzzy plan/path/phase arg (e.g. chaosforge-demo, plans/chaosforge-demo, phase-3), an empty arg, or natural-language ref like “active plan” / “current plan” / “this plan”, run the Fuzzy Plan / Path Resolution Protocol at skills/t1k-cook/references/fuzzy-plan-resolution.md BEFORE bail. Skill MUST NOT emit “no path matching” / “exact path required” until that protocol has been applied and Step 6 reached.

  • Understanding unfamiliar codebase architecture before planning
  • Discovering cross-file relationships and dependency chains
  • Finding “god nodes” (most-connected concepts) in large projects
  • Navigating by structure instead of grepping every file
  • Preparing context-efficient codebase representation (71.5x fewer tokens vs raw files)

Typically precedes: /t1k:plan (understand architecture before planning) Related: /t1k:scout (quick file search), /t1k:repomix (full context dump)

This is an optional skill wrapping the third-party graphifyy package (Python 3.10+; PyPI name is double-y — other graphify* packages are unaffiliated). Install + full CLI/MCP/architecture detail: references/reference.md.

Terminal window
pip install graphifyy && graphify install # install + download tree-sitter grammars
graphify . # build knowledge graph from current directory
graphify /path/to/project # or a specific path
graphify . --watch # watch mode, auto-rebuild on file changes

Output lands in graphify-out/ — graph.html (interactive viz), GRAPH_REPORT.md (god nodes, suggested questions), graph.json (persistent graph), cache/ (incremental rebuilds).

graphify’s result cap is token_budget (default 2000; CLI flag --budget). Rendering cuts at roughly token_budget * 3 characters.

There is no maxResultSizeChars parameter and no limit parameter — earlier revisions of this section instructed both, and passing either is silently ignored, so a caller who “capped” a query had no cap at all. Verified against the installed graphify/serve.py (2,617 lines): zero occurrences of maxResultSizeChars, and limit appears only in prose.

To keep a result small, in order of preference:

  • Narrow the query — context_filter=['call'] rather than an unfiltered walk.
  • Ask for one symbol — get_node instead of a subgraph.
  • Raise the budget deliberately — --budget N, when you genuinely need more.

Truncation is not a returned field. The server does not return truncated: true; it prepends a banner to the TOP of the returned text, deliberately, so a cut answer cannot be mistaken for a complete one:

[!] TRUNCATED: showing 40 of 315 nodes (~2000-token budget). The answer may be among the
275 cut nodes — raise the token budget (CLI: --budget) or narrow the query ...

A matching ... (truncated — N more nodes cut ...) marker closes the text. Both sit outside the character budget by design.

So detect truncation by the [!] TRUNCATED: prefix, never by reading a field. A field read returns undefined, which is falsy — testing for one makes every truncated result look complete, which is exactly the failure this section exists to prevent. When it fires, surface it with a hint to narrow the query; never present a partial result as whole.