quickstart

An interactive setup guide for Weaviate Cloud, a hosted service for storing and searching data by meaning as well as by words. It walks a new user through credentials, data loading, and available commands.

In plain words
What is it for?
Use it to create or prepare a Weaviate Cloud setup, load CSV or JSON data, manage collections, and learn how to query the stored data.
Why use it?
It removes the need to know how Weaviate is structured before trying the plugin. It adapts the setup to whether the user has no account, an empty cluster, or existing data.

Command

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 commands/weaviate/agent-skills/quickstart
Clone the repo
git clone --depth 1 https://github.com/weaviate/agent-skills
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,514 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. 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 $0.00021 $0.03514
Opus 5 $0.00010 $0.01757
Sonnet 5 $0.00004 $0.00703
Haiku 4.5 $0.00002 $0.00351

Measured 2d ago against content hash 8548c9264cf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

quickstart scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

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

curl -LsSf https://astral.sh/uv/install.sh | sh
commands/quickstart.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weaviate Plugin Quickstart

Welcome the user and walk them through the full setup of the Weaviate plugin, step by step. Be friendly, patient, and thorough — assume the user has never used Weaviate before.

Welcome & Orientation

Greet the user and give a brief overview of what this plugin can do:

  • Search & Query: Ask questions and get AI-generated answers with citations, or run hybrid/semantic/keyword searches across your data.
  • Collection Management: Create, list, explore, and inspect collections (like tables in a database, but for vector data).
  • Data Operations: Import your own data from local CSV/JSON/JSONL files, fetch and filter objects, or load ready-made sample datasets to experiment with.
  • Build Full-Stack Apps: Use cookbooks to build chatbots, data explorers, RAG pipelines, and AI agents — all powered by Weaviate.

Then ask the user where they are in their journey:

Use AskUserQuestion with these options:

  • "Brand new to Weaviate" — I don't have an account or cluster yet.
  • "I have a cluster but it's empty" — I have a Weaviate Cloud account but no data in it yet.
  • "I have a cluster with data" — I'm ready to start querying.

Route them accordingly:

  • Brand new → Continue to Step 2
  • Cluster but empty → Skip to Step 3
  • Cluster with data → Skip to Step 5

Sign Up for Weaviate Cloud

Guide the user through creating a Weaviate Cloud account:

  1. Direct them to Weaviate Cloud Console to register.
  2. Tell them to click either "Sign in with Google" or "Sign in with GitHub" to sign up.
  3. Once registered and logged into the dashboard, guide them to create a free Sandbox cluster:
    • Click "+ Create cluster"
    • Choose Sandbox
    • Enter a cluster name and select a region
    • Click "Create cluster" and wait for it to be ready (usually a few minute)
  4. Once the cluster is ready, they need two environment variables:
    • WEAVIATE_URL: Copy the "REST Endpoint" URL shown under the "Endpoints" section in the cluster dashboard (ends with .weaviate.cloud)
    • WEAVIATE_API_KEY: Go to "API Keys" section and click "+ New key", once the Create API Key popup appears, add an API key name and select "admin" in the "Role(s)" dropdown. Click on "Create Key" and copy it as you will not be able to see it again.

Read the full file on GitHub · 322 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 · 322 lines · 21 tokens per session scan C 8548c9264cf5

Subscribe to this mod's changes

quickstart is a command published in the GitHub repository weaviate/agent-skills (103 stars, last pushed 2mo ago), licensed BSD-3-Clause. It adds 21 tokens to every session and 3,514 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.