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 rules/singlestore-labs/mcp-server-singlestore/singlestore-drizzlegit clone --depth 1 https://github.com/singlestore-labs/mcp-server-singlestoreWrote 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/rules/singlestore-labs/mcp-server-singlestore/singlestore-drizzle)<a href="https://agentmods.dev/rules/singlestore-labs/mcp-server-singlestore/singlestore-drizzle"><img src="https://agentmods.dev/badge/rules/singlestore-labs/mcp-server-singlestore/singlestore-drizzle.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 | $0.00000 | $0.01984 |
| Opus 5 | $0.00000 | $0.00992 |
| Sonnet 5 | $0.00000 | $0.00397 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade A, and why
singlestore-drizzle 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 5d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SingleStore and Drizzle Integration Guidelines
Overview
This guide covers the specific integration patterns and optimizations for using Drizzle ORM with SingleStore databases. Follow these guidelines to ensure efficient database operations with SingleStore's high-performance capabilities.
Dependencies
For SingleStore with Drizzle ORM integration, include these specific dependencies:
npm install drizzle-orm mysql2 dotenv
npm install -D drizzle-kit
Note: Ensure that the drizzle-orm version is greater or equal to 0.44.2 and drizzle-kit is greater or equal to ^0.31.0 to ensure compatibility with SingleStore.
Script commands
Migrations
To generate new migrations and apply them to the database, use the following commands:
# Generate new migrations
npx drizzle-kit generate
# Apply migrations to the database
npx drizzle-kit push
SingleStore Connection Configuration
- Always use the SingleStore connection string format:
DATABASE_URL=singlestore://username:password@host:port/database?ssl={}
Important: Keep the ssl={} at the end of the string, otherwise the connection won't work
- Store this in
.envor.env.localfile
SingleStore Connection Setup
When connecting to SingleStore:
- Use mysql2 to establish a connection to the SingleStore database
- Use the singlestore drizzle driver from
drizzle-orm/singlestoreto create the Drizzle instance
// src/index.ts
import dotenv from "dotenv";
import mysql from "mysql2/promise";
import { drizzle } from "drizzle-orm/singlestore";
import * as schema from './db/schema';
// Load environment variables from .env file
dotenv.config();
if (!process.env.DATABASE_URL) {
throw new Error('DATABASE_URL is not defined');
}
const pool = mysql.createPool(process.env.DATABASE_URL);
const db = drizzle({ client: pool, schema});
SingleStore Database Considerations
Connection Management
- For queries: Use either client or pool based on your needs but prefer connection pooling for high-traffic applications
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.
- 5d ago First seen · 301 lines · 1,984 tokens per session scan A 085e64edf6be
singlestore-drizzle is a cursor rule published in the GitHub repository singlestore-labs/mcp-server-singlestore (32 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,984 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .
no-backward-compatibility
Do not add backward-compatibility shims or migration scaffolding.
query-optimization
查詢優化、EXPLAIN、index 設計與 RLS 效能測量.
sqlmodel
Satisfying the type checker when working with SQLModel.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.