What is graph-model-selector?

A decision guide for choosing among three kinds of graph databases: labeled property graphs, RDF, and hypergraphs. It scores each option against reasoning, relationship types, speed, tools, and rule constraints.

Use it to compare graph models for applications such as medical reasoning, network analysis, or events involving several entities.

It helps prevent choosing a graph structure that cannot support the kind of reasoning or relationships your application needs.

graph-model-selector — Skill by AnthonyAlcaraz

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add AnthonyAlcaraz/agentic-graph-rag-skills --skill graph-model-selector

Clone the repo

git clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/graph-model-selector/github.svg)](https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/graph-model-selector)

Your own site

<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/graph-model-selector"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/graph-model-selector/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/graph-model-selector"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/graph-model-selector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,176 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00225	$0.02176
Opus 5.5	$0.00090	$0.00870
Sonnet 5.5	$0.00045	$0.00435
Haiku 4.5	$0.00022	$0.00218

Measured 2mo ago against content hash f6f4a4e8156c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

graph-model-selector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (cli.py, lib.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/knowledge-representation/graph-model-selector/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graph Model Selector

Overview

AI agents are only as intelligent as the knowledge structures you give them, and the model you choose constrains what they can reason about. The chapter is explicit: start with your reasoning requirements, not your data. Formal logical inference (medical diagnosis) demands a different model than traversal-heavy network analysis or many-entity events.

Three model classes, each with a characteristic profile:

Labeled property graph (LPG): fast traversals, mature ecosystem (Neo4j / Neptune / ArangoDB), flexible. Can only tell you what you explicitly programmed — no native inference.
RDF (subject-predicate-object triples): formal logical semantics enable native inference. Tell it Disease1 causes Symptom1 and Patient exhibits Symptom1 and it infers Disease1 is a candidate diagnosis with no rule written. Slower; n-ary needs reification.
Hypergraph: one hyperedge connects any number of entities, so n-ary relations are native — no auxiliary nodes. Ecosystem is immature.

The selector scores each model across the five features the chapter names (formal reasoning, n-ary, performance, tool ecosystem, constraint expressiveness) weighted by the caller's requirements, and surfaces a hybrid recommendation when the top two are close (the chapter's "Putting it all together" hybrid guidance).

The n-ary helper makes the trade-off concrete. A prescription (doctor + patient + medication + dosage + date + condition) is one hyperedge (representation_cost.hypergraph_elements == 1) but costs 1 + arity elements (one relation node + one edge per participant) under LPG or RDF reification.

When to Use

Choosing a graph backend model class for a new agentic system
Justifying a build-vs-buy or LPG-vs-RDF-vs-hypergraph decision in a design doc
Deciding whether a multi-entity fact warrants a hyperedge or reification

Phrases: "which graph model", "property graph vs RDF", "hypergraph", "n-ary relation", "reification", "graph data model selection", "Neo4j vs RDF".

Read the full file on GitHub · 144 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 144 lines · 225 tokens per session scan A f6f4a4e8156c

Subscribe to this mod's changes

graph-model-selector is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (28 stars, last pushed 3mo ago), licensed MIT. It adds 225 tokens to every session and 2,176 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Databases Planning agent-skills agentic-ai graphrag knowledge-graph llm-agents

graph-model-selector next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
graph-model-selectorAnthonyAlcaraz/agentic-graph-rag-skills	Skill	28	3mo ago	MIT	A	225	Claude Code, Codex
hugegraph-regression-testerapache/hugegraph-ai	Skill	145	yesterday	Apache-2.0	A	54	Codex
hugegraph-data-importerapache/hugegraph-ai	Skill	145	yesterday	Apache-2.0	A	62	Codex
hugegraph-operatorapache/hugegraph-ai	Skill	145	yesterday	Apache-2.0	A	63	Codex
hugegraph-schema-designerapache/hugegraph-ai	Skill	145	yesterday	Apache-2.0	A	51	Codex
hugegraph-query-analystapache/hugegraph-ai	Skill	145	yesterday	Apache-2.0	A	49	Codex
embeddingsruvnet/ruflo	Skill	81k	yesterday	MIT	A	62	Claude Code