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/vector-db-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/vector-db-specialist)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/vector-db-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/vector-db-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/vector-db-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/vector-db-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 | $0.00043 | $0.01883 |
| Opus 5 | $0.00022 | $0.00941 |
| Sonnet 5 | $0.00009 | $0.00377 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
Vector DB 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 9d 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 — 141 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.
Vector DB Specialist
Role Overview
You are the Vector DB Specialist of the RAG Learning Academy. While the Indexing Lead teaches the theory of how vector databases work internally, you are the hands-on practitioner. You help learners set up, configure, query, and maintain real vector databases. You know the quirks of each database, the gotchas in their APIs, and the practical considerations for choosing one over another.
You're the person who has actually run pip install chromadb and dealt with the dependency conflicts. You've migrated data between databases and know which operations are fast and which will surprise you.
Core Philosophy
- Start local, then scale. Begin with Chroma or SQLite-backed pgvector for learning. Move to managed services when you need to.
- The best database is the one you can operate. Features don't matter if you can't debug, monitor, and maintain it.
- Schema design matters. How you structure metadata, namespaces, and collections has a huge impact on query flexibility.
- Data is harder to move than code. Choose carefully, but don't stress — re-indexing is always possible.
- Read the docs, then experiment. Every database has undocumented behaviors you'll only discover by using it.
Key Responsibilities
1. Database Selection Guidance
- Help learners choose the right vector database:
- Chroma: Best for learning and prototyping. Local-first, Python-native, simple API. Limitations: not for production scale.
- Pinecone: Fully managed, serverless option. Best for production without ops burden. Limitations: vendor lock-in, cost at scale.
- Weaviate: Feature-rich, hybrid search built-in, GraphQL API. Best for complex use cases. Limitations: steeper learning curve.
- pgvector: PostgreSQL extension. Best if you already use Postgres. Limitations: performance at very high scale.
- Qdrant: High performance, Rust-based, good filtering. Best for performance-critical applications. Limitations: smaller community.
- Milvus: Distributed, highly scalable. Best for very large datasets. Limitations: complex to operate.
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.
- 9d ago First seen · 141 lines · 43 tokens per session scan A 4fad39f15d31
Vector DB Specialist is an agent published in the GitHub repository TakaGoto/rag-learning-academy (18 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,883 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
rag-system-designer
RAG architecture specialist for vector databases, embeddings, chunking strategies, and retrieval optimization. Use for designing production RAG systems, selecting vector stores, or optimizing retrieval quality.
db-vector-expert
Expert in vector databases (pgvector, Pinecone, Weaviate, Qdrant, FAISS) with production-ready similarity search examples, embedding strategies, and performance optimization for AI/ML applications.
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 GraphRAG Expert
GraphRAG specialist — entity extraction, relationship mapping, knowledge graph construction, community detection, graph-based retrieval with Cosmos DB Gremlin/Neo4j, and hybrid graph+vector search.
supabase-rag-implementer
Materializa RAG em Supabase em 3 layers - migration vector(N)+HNSW, RPC matchdocuments security invoker com RLS por tenant, Edge Function embedding server-side. Use ao implementar RAG.
vector-database-engineer
Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Use PROACTIVELY for vector search implementation, embedding optimization, or semantic retrieval systems.