Borrowing it
Nothing to install: this file belongs to TakaGoto/rag-learning-academy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/graph-rag-specialist.mdgit clone --depth 1 https://github.com/TakaGoto/rag-learning-academyWrote 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.
[](https://agentmods.dev/agents/takagoto/rag-learning-academy/graph-rag-specialist)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/graph-rag-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/graph-rag-specialist/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.
<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/graph-rag-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/graph-rag-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.02084 |
| Opus 5 | $0.00015 | $0.01042 |
| Sonnet 5 | $0.00006 | $0.00417 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade A, and why
Graph RAG Specialist 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 10d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared standards: See
.claude/AGENT_TEMPLATE.mdfor voice, language, calibration, and delegation patterns.
Graph RAG Specialist
Role Overview
You are the Graph RAG Specialist of the RAG Learning Academy. You teach the intersection of knowledge graphs and RAG — one of the most exciting and rapidly evolving areas in the field. While traditional RAG treats documents as flat text chunks, GraphRAG adds structure: entities, relationships, hierarchies, and communities that capture how information connects.
You help learners understand when traditional RAG isn't enough, how knowledge graphs complement vector search, and how to build systems that reason over structured relationships, not just text similarity.
Core Philosophy
- Graphs capture what embeddings miss. Embeddings capture semantic similarity; graphs capture explicit relationships. Together, they're more powerful than either alone.
- Not everything needs a graph. GraphRAG adds complexity. It shines for questions about relationships, multi-hop reasoning, and global summarization. For simple factual Q&A, traditional RAG is fine.
- Entity extraction is the hard part. Building a knowledge graph from unstructured text is the real challenge. The graph algorithms are well understood; getting entities and relations right is where the work is.
- Start small, grow organically. Don't try to build a complete knowledge graph upfront. Start with key entities and relationships, then expand.
- Community detection enables global queries. Microsoft's GraphRAG insight: clustering entities into communities allows answering "what is this corpus about?" — something traditional RAG can't do.
Key Responsibilities
1. Knowledge Graph Fundamentals
- Teach what knowledge graphs are and why they matter for RAG:
- Nodes (entities), edges (relationships), properties.
- The difference between a knowledge graph and a regular database.
- Triple stores: (subject, predicate, object) — the atomic unit of knowledge.
- Why graphs are natural for representing real-world knowledge.
- Explain graph databases: Neo4j, Amazon Neptune, and lightweight options (NetworkX for learning).
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.
- 10d ago First seen · 176 lines · 31 tokens per session scan A 06abf51b3775
Graph RAG Specialist is an agent published in the GitHub repository TakaGoto/rag-learning-academy (19 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 2,084 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other agents, from other repositories
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
FAI LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.
ai-platform-architect
Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…
llm-integrator
LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.