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 agents/vibeeval/vibecosystem/vector-db-expertgit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/vibeeval/vibecosystem/vector-db-expert)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/vector-db-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/vector-db-expert.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 5.1 | $0.00031 | $0.01614 |
| Opus 5 | $0.00015 | $0.00807 |
| Sonnet 5 | $0.00006 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
vector-db-expert 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 2d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VECTOR-DB-EXPERT -- Embedding Storage & Similarity Search Specialist
Domain: Vector Databases / Embedding Storage / ANN Search / Hybrid Search / Index Tuning
Core Concepts
Embedding: Dense float vector (768-3072 dims) representing semantic meaning. Similarity search: Find the k nearest vectors to a query vector. ANN (Approximate Nearest Neighbor): Trade exact accuracy for 100-1000x speed.
Database Selection Matrix
| Database | Type | Best For | Max Vectors | Filtering | Notes |
|---|---|---|---|---|---|
| pgvector | Extension | <5M vectors, existing Postgres | ~10M | Full SQL WHERE | No infra overhead |
| Pinecone | Managed SaaS | Production, serverless | Billions | Metadata filters | Pay per query |
| Weaviate | Self-hosted/Cloud | Hybrid search, multi-modal | 100M+ | GraphQL filters | Built-in vectorizer modules |
| Qdrant | Self-hosted/Cloud | High performance, filtering | 100M+ | Rich payload filters | Rust, very fast |
| Chroma | Embedded | Prototyping, small datasets | ~1M | Metadata filters | Python-native, ephemeral default |
| Milvus | Self-hosted | Massive scale, GPU | Billions | Attribute filters | Complex to operate |
ANN Index Algorithms
HNSW (Hierarchical Navigable Small World)
- How: Multi-layer graph, greedy search from top layer down
- Params: m (connections per node, default 16), ef_construction (build quality, default 64)
- Tradeoffs: High memory (8-64 bytes/vector/connection), fast query, slow build
- Best for: <50M vectors, high recall needed, memory available
- Tuning: Higher m = better recall, more memory. Higher ef_search = better recall, slower query.
IVF (Inverted File Index)
- How: Cluster vectors into nlist cells, search nprobe nearest cells
- Params: nlist (clusters, sqrt(n) to 4*sqrt(n)), nprobe (cells to search)
- Tradeoffs: Lower memory, fast build, recall depends on nprobe
- Best for: >10M vectors, memory constrained
- Tuning: nprobe=1% of nlist is a good start. More nprobe = better recall.
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.
- 2d ago First seen · 151 lines · 31 tokens per session scan A 6ddf3d49782c
vector-db-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 31 tokens to every session and 1,614 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 2026-09-03.
Other agents, from other repositories
data-engineer
ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…
doc-rag-builder
Scrapes documentation websites, builds high-fidelity RAG (Retrieval-Augmented Generation) systems with intelligent chunking and semantic indexing, and provides expert reader utility for querying latest documentation. Works with ANY documentation website (e.g., modelcontextprotocol.io, docs.anthropic.com, etc.).…
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
token
Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with "design my token budget", "fix my context overflow".
RAG Pipeline Engineer
Production RAG specialist focused on chunking strategy, retrieval quality, hybrid search, re-ranking, and eval-driven iteration. Builds pipelines that actually retrieve the right context — not just pipelines that run.
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.