qdrant

A guide for managing Qdrant, a database that stores number-based representations of text or other data so similar items can be found. It uses Qdrant’s REST API to work with collections and stored points.

In plain words
What is it for?
Create or delete collections, add, find, count, inspect, filter, scroll through, or delete points, manage snapshots, and check cluster health.
Why use it?
It removes the need to remember Qdrant’s API addresses and request formats when managing stored vectors or investigating search problems.

Skill for Claude CodeCodex

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 skills/bug-ops/zeph/qdrant
Any agent
npx skills add bug-ops/zeph --skill qdrant
Clone the repo
git clone --depth 1 https://github.com/bug-ops/zeph

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,722 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 $0.00088 $0.03722
Opus 5 $0.00044 $0.01861
Sonnet 5 $0.00018 $0.00744
Haiku 4.5 $0.00009 $0.00372

Measured 2d ago against content hash 97088b67bff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qdrant 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 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.

Makes network callslowCapability

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

compatibility: Requires curl and a running Qdrant instance (default http://localhost:6333)
.zeph/skills/qdrant/SKILL.md · 499 lines

How it starts

The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qdrant Vector Database

Base URL: http://localhost:6333 (default). Override with QDRANT_URL env var.

All examples use curl. Replace localhost:6333 with the actual Qdrant endpoint.

Quick Reference

Task Endpoint
List collections GET /collections
Create collection PUT /collections/{name}
Delete collection DELETE /collections/{name}
Collection info GET /collections/{name}
Upsert points PUT /collections/{name}/points
Search POST /collections/{name}/points/search
Scroll (paginate) POST /collections/{name}/points/scroll
Get point GET /collections/{name}/points/{id}
Delete points POST /collections/{name}/points/delete
Count points POST /collections/{name}/points/count
Health check GET /healthz

Collections

List all collections

curl -s http://localhost:6333/collections | jq

Create collection

curl -s -X PUT http://localhost:6333/collections/my_collection \
  -H "Content-Type: application/json" \
  -d '{
    "vectors": {
      "size": 384,
      "distance": "Cosine"
    }
  }' | jq

Distance metrics: Cosine, Euclid, Dot, Manhattan.

Create collection with named vectors

curl -s -X PUT http://localhost:6333/collections/my_collection \
  -H "Content-Type: application/json" \
  -d '{
    "vectors": {
      "content": {"size": 384, "distance": "Cosine"},
      "title": {"size": 128, "distance": "Cosine"}
    }
  }' | jq

Collection info

curl -s http://localhost:6333/collections/my_collection | jq

Key fields: vectors_count, points_count, segments_count, status (green/yellow/red).

Delete collection

curl -s -X DELETE http://localhost:6333/collections/my_collection | jq

Check collection exists

curl -sI http://localhost:6333/collections/my_collection -o /dev/null -w "%{http_code}"
# 200 = exists, 404 = not found

Points

Upsert points (insert or update)

Read the full file on GitHub · 499 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. 2d ago First seen · 499 lines · 88 tokens per session scan A 97088b67bff5

Subscribe to this mod's changes

qdrant is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 8d ago), licensed MIT. It adds 88 tokens to every session and 3,722 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

session-rag-eval

Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.

chatboxai/chatbox · 25 tokens

data_analyst

Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.

siddsachar/row-bot · 26 tokens

openmaic-classroom

将 RAG 检索结果、文档块或知识图谱概念转换为 OpenMAIC 互动课程。当用户要求将知识库内容、检索到的文档片段、上传的文档、或知识图谱中的概念批量转换为教学课件/互动课堂时使用此技能。支持纯需求生成、基于 PDF 内容的课程生成、和基于概念图遍历的批量课堂生成。.

Tencent/WeKnora · 102 tokens

weknora-shared

Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.

Tencent/WeKnora · 68 tokens

weknora-rag-search

Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.

Tencent/WeKnora · 54 tokens

nodetool-rag-indexing

Set up RAG pipelines, vector indexing, document ingestion, vector search, and knowledge base creation in NodeTool. Use when user asks about RAG, document indexing, vector search, chat with documents, knowledge base, embeddings, or collection management.

nodetool-ai/nodetool · 58 tokens