qdrant-expert

qdrant-expert is an agent for coding agents from acaprino/daodan. It costs 91 tokens per session (3,793 once invoked), scanned A, original, MIT.

An expert agent for operating Qdrant, a database that stores vectors used to find similar text or other data.

In plain words
What is it for?
Use it to set up Qdrant collections, tune HNSW indexes, configure dense or sparse hybrid search, add payload filters, manage multiple tenants, and troubleshoot performance.
Why use it?
It helps configure search collections and tune the trade-offs between search accuracy, speed, memory use, filtering, and production deployment.

Agent

Part of the rag-development plugin — 1 skill, 1 command, 2 agents shipped together

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.

agentmods
npx agentmods add agents/acaprino/daodan/qdrant-expert
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

Or install rag-development, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 agents.

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.

agentmods badge for qdrant-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/acaprino/daodan/qdrant-expert.svg)](https://agentmods.dev/agents/acaprino/daodan/qdrant-expert)
Your own site
<a href="https://agentmods.dev/agents/acaprino/daodan/qdrant-expert"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/qdrant-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,793 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00091 $0.03793
Opus 5 $0.00046 $0.01896
Sonnet 5 $0.00018 $0.00759
Haiku 4.5 $0.00009 $0.00379

Measured today against content hash 8e815f3efeb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qdrant-expert scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:6333/collections/my_collection | jq
exports/claude/plugins/rag-development/agents/qdrant-expert.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE

Qdrant vector database expert. Configure collections, tune HNSW indexing, optimize memory with quantization, design hybrid search pipelines, set up payload filtering, manage multi-tenancy, and deploy for production.

CAPABILITIES

Collection Configuration

  • Named vectors -- multiple vector types per collection (dense, sparse, multi-vector)
  • Distance metrics -- Cosine, Dot, Euclid, Manhattan
  • On-disk vectors -- on_disk=True for mmap-based storage; OS handles page caching
  • Shard configuration -- automatic or custom sharding for distributed deployments
  • Write-ahead log (WAL) -- configurable for durability vs throughput trade-offs

HNSW Index Tuning

  • m (default 16) -- connections per node; 16-32 optimal for text; higher = better recall, more memory
  • ef_construct (default 100) -- build-time beam width; higher = better index quality, slower build
  • ef (search-time) -- search beam width; tune for accuracy/speed trade-off
  • full_scan_threshold -- if filtered candidates < threshold, do brute-force instead of graph traversal
  • On-disk index -- for cost-sensitive deployments with NVMe SSDs
  • GPU-accelerated HNSW build (since v1.13) -- NVIDIA/AMD/Intel via Vulkan; build-only, up to ~10x faster than CPU at equivalent cost; multi-GPU per-segment
  • Incremental HNSW on upsert (since v1.14) -- extends graph rather than rebuilding; deletes/updates still trigger rebuild
  • ACORN filtered HNSW (since v1.16) -- per-query acorn flag; examines 2-hop neighbors when 1-hop is filtered out; improves filtered recall on low-selectivity queries, at some perf cost, no index changes needed
  • Inline storage (since v1.16) -- quantized + original vectors embedded in HNSW graph nodes for disk-based search; large QPS uplift (reported ~10x on disk benchmarks)
  • Strict Mode (since v1.13) -- per-collection limits on unindexed filters, payload size, batch size, timeout; default on for new collections
  • Storage engine: Gridstore (custom, constant-time reads/writes, no compaction spikes) replaced RocksDB as default in v1.15

Read the full file on GitHub · 345 lines

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.

  1. today First seen · 345 lines · 91 tokens per session scan A 8e815f3efeb2

Subscribe to this mod's changes

qdrant-expert is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 3,793 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other agents, from other repositories