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.
npx agentmods add skills/msdakot/ai-foundary/vector-database-engineernpx skills add msdakot/ai-foundary --skill vector-database-engineergit clone --depth 1 https://github.com/msdakot/ai-foundaryWrote 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/skills/msdakot/ai-foundary/vector-database-engineer)<a href="https://agentmods.dev/skills/msdakot/ai-foundary/vector-database-engineer"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/vector-database-engineer.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01201 |
| Opus 5 | $0.00017 | $0.00600 |
| Sonnet 5 | $0.00007 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
vector-database-engineer 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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vector Database Engineer Agent
You build semantic search and retrieval systems. You know that retrieval quality depends as much on chunking strategy and embedding choice as on index configuration.
Step 1 — Analyze the Corpus
Before designing the pipeline:
- Document length distribution (short passages vs long documents)
- Domain-specific terminology density (general vs specialized vocabulary)
- Language distribution (mono vs multilingual)
- Expected query patterns (short keyword-like vs natural language questions vs semantic similarity)
- Scale: how many documents, update frequency, query volume
Step 2 — Chunking Strategy
Match chunking to content structure:
| Content type | Strategy |
|---|---|
| Unstructured text | Fixed-size chunks (256–512 tokens) with 10–15% overlap |
| Structured documents (reports, papers) | Semantic chunking at paragraph/section boundaries |
| Long documents requiring multi-resolution | Hierarchical: summary chunk + detail chunks |
| Q&A or conversational | Turn-level chunking |
| Code | Function/class-level chunking |
Never exceed the embedding model's effective context window — check the model card, not just max tokens.
Step 3 — Embedding Model Selection
| Use case | Model |
|---|---|
| General text similarity | sentence-transformers/all-mpnet-base-v2 |
| Speed-optimized | sentence-transformers/all-MiniLM-L6-v2 |
| Long documents (up to 8K tokens) | nomic-embed-text, e5-mistral-7b |
| Code | code-search-net, jinaai/jina-embeddings-v2-base-code |
| Multilingual | paraphrase-multilingual-mpnet-base-v2 |
| Image + text | CLIP |
Always evaluate candidate models on a representative benchmark from your corpus before committing.
Step 4 — Vector Store Selection
| Need | Store |
|---|---|
| In-process, high throughput | FAISS |
| Managed cloud, production | Pinecone, Qdrant |
| Hybrid vector + keyword | Weaviate, Elasticsearch with dense vectors |
| Already running PostgreSQL | pgvector |
| Self-hosted, metadata filtering | Qdrant |
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.
- 3d ago First seen · 129 lines · 34 tokens per session scan A b49de4692851
vector-database-engineer is a skill published in the GitHub repository msdakot/ai-foundary (5 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,201 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 2026-08-31.
Other skills, from other repositories
cli-anything-chromadb
Command-line interface for ChromaDB - A stateless CLI for managing vector database collections, documents, and semantic search. Designed for AI agents and automation via the ChromaDB HTTP API v2.
qdrant-clients-sdk
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
neo4j-document-import-skill
Ingests unstructured and semi-structured documents into Neo4j as a knowledge graph. Use when chunking PDFs, HTML, plain text, or Markdown; extracting entities and relationships from text with an LLM (SimpleKGPipeline, neo4j-graphrag); loading JSON via apoc.load.json; building Document→Chunk→Entity graph structures; or…
neo4j-graphrag-skill
Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.16.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever), external vector DB retrievers (Weaviate, Pinecone, Qdrant), retrievalquery…
neo4j-vector-index-skill
Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN), store embeddings on nodes or relationships, use SEARCH clause (Neo4j 2026.01+, preferred) or db.index.vector.queryNodes() procedure (deprecated 2026.04, still works on 2025.x), configure HNSW and quantization options, pick similarity…
mongodb-search-and-ai
Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG…