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 skills add saskinosie/weaviate-claude-skills --skill weaviate-connectiongit clone --depth 1 https://github.com/saskinosie/weaviate-claude-skillsWrote 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/saskinosie/weaviate-claude-skills/weaviate-connection)<a href="https://agentmods.dev/skills/saskinosie/weaviate-claude-skills/weaviate-connection"><img src="https://agentmods.dev/badge/skills/saskinosie/weaviate-claude-skills/weaviate-connection/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/saskinosie/weaviate-claude-skills/weaviate-connection"><img src="https://agentmods.dev/badge/skills/saskinosie/weaviate-claude-skills/weaviate-connection.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.02346 |
| Opus 5 | $0.00009 | $0.01173 |
| Sonnet 5 | $0.00004 | $0.00469 |
| Haiku 4.5 | $0.00002 | $0.00235 |
Grade A, and why
weaviate-connection scanned grade A 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 12d 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.
curl http://localhost:8080/v1/.well-known/ready Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([sys.executable, "-m", "venv", ".venv"]) How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weaviate Connection Skill
This skill helps you connect to a local Weaviate database instance running in Docker and verify the connection is healthy.
Important Note
This skill is designed for LOCAL Weaviate instances only. Claude Desktop and Claude Web have network restrictions that prevent connections to external services like Weaviate Cloud.
To use these skills, you must run Weaviate locally using Docker. See the weaviate-local-setup skill first.
Purpose
Establish and test connections to local Weaviate vector databases running on localhost.
When to Use This Skill
- User wants to connect to their local Weaviate database
- User needs to verify their Weaviate connection is working
- User asks to check Weaviate health or status
- After starting Weaviate with Docker
Prerequisites Check
BEFORE proceeding, Claude should verify:
-
Python environment is set up (from
weaviate-local-setupskill)- Virtual environment exists at
.venv/ - Dependencies are installed
- Virtual environment exists at
-
Weaviate Docker container is running
- Check with
docker ps | grep weaviate - If not running, guide user to start it
- Check with
-
Environment file exists
.envfile is present- Has required variables set
Automated Prerequisites Check
import subprocess
import sys
import os
from pathlib import Path
def check_prerequisites():
"""Check all prerequisites before connecting to Weaviate"""
print("🔍 Checking prerequisites...\n")
all_checks_passed = True
# Check 1: Virtual environment
venv_path = Path(".venv")
if venv_path.exists():
print("✅ Virtual environment found")
else:
print("⚠️ No virtual environment found")
print(" Creating virtual environment...")
subprocess.run([sys.executable, "-m", "venv", ".venv"])
print("✅ Virtual environment created")
# Check 2: Dependencies
try:
import weaviate
from dotenv import load_dotenv
print("✅ Python dependencies installed")
except ImportError:
print("⚠️ Missing dependencies")
print(" Installing weaviate-client and python-dotenv...")
subprocess.check_call([sys.executable, "-m", "pip", "install", "-q",
"weaviate-client", "python-dotenv"])
print("✅ Dependencies installed")
# Check 3: Docker container
result = subprocess.run(["docker", "ps"], capture_output=True, text=True)
if "weaviate" in result.stdout:
print("✅ Weaviate Docker container is running")
else:
print("❌ Weaviate Docker container not found")
print(" Please start Weaviate first:")
print(" cd weaviate-local-setup && docker-compose up -d")
all_checks_passed = False
# Check 4: .env file
if Path(".env").exists():
print("✅ .env file found")
else:
print("⚠️ .env file not found")
print(" Creating .env from template...")
if Path(".env.example").exists():
import shutil
shutil.copy(".env.example", ".env")
print("✅ .env file created")
print(" Please edit .env and add your API keys if needed")
else:
print("❌ No .env.example found")
all_checks_passed = False
print("\n" + "="*50)
if all_checks_passed:
print("✅ All prerequisites met! Ready to connect.")
else:
print("❌ Some prerequisites missing. Please resolve them first.")
print("="*50 + "\n")
return all_checks_passed
# Run the check
if __name__ == "__main__":
check_prerequisites()
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.
- 12d ago First seen · 350 lines · 18 tokens per session scan A 09724adcd597
weaviate-connection is a skill published in the GitHub repository saskinosie/weaviate-claude-skills (39 stars, last pushed 10mo ago), licensed MIT. It adds 18 tokens to every session and 2,346 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…
laravel-vector-search
Use when implementing semantic/vector search in Laravel 13 with PostgreSQL + pgvector.
RAG Workflow Planner
Designs a complete Retrieval-Augmented Generation (RAG) pipeline for a given use case, including chunking strategy, embedding model selection, and retrieval approach.
AgentDB Performance Optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.