Skip to content
All tool news

Tool desk · Updated daily

Tool news·Supabase·

Supabase Releases 30-Rule Plugin to Help AI Agents Write Better Postgres Code.

Supabase launches a Claude Code plugin with 30 rules across 8 categories to teach AI agents how to write correct Postgres code.

CW

Create With tool desk

1 source checked · 2 min read · 3 sections

ShareLinkedIn
Supabase Releases 30-Rule Plugin to Help AI Agents Write Better Postgres Code

Supabase has released a new plugin for Claude Code that aims to improve how AI agents generate Postgres database code. The plugin packages 30 rules across eight categories, providing structured guidance to help AI coding assistants write more accurate and idiomatic Postgres queries.

The move addresses a common pain point for developers using AI coding tools: while these assistants excel at boilerplate and general syntax, they often struggle with database-specific conventions, security patterns, and performance optimization. Supabase's rule set is designed to teach AI agents the nuances of Postgres development, from proper indexing strategies to secure query construction.

What the Plugin Covers

The 30 rules span eight core areas of Postgres development. While Supabase hasn't published the full list publicly, the categories likely include schema design, query optimization, security best practices, indexing strategies, data type selection, transaction handling, and common anti-patterns to avoid.

For teams building on Supabase, this means AI assistants like Claude Code can now suggest code that aligns with platform best practices out of the box. The plugin works by injecting these rules into the AI's context when generating database-related code, similar to how linters enforce style guides.

Why This Matters for AI-Assisted Development

AI coding tools have rapidly become standard in software development workflows, but database code remains one of their weaker areas. Generic language models weren't trained specifically on Postgres internals or platform-specific patterns. They might generate syntactically valid SQL that performs poorly, misses security considerations, or doesn't leverage Postgres-specific features.

Supabase's approach is part of a broader trend of platform vendors creating AI-specific guidance. The plugin model allows developers to benefit from AI speed while maintaining code quality and security standards. This is particularly valuable for small teams and solo builders who may not have deep database expertise in-house.

The timing aligns with growing interest in AI-powered development tools. Tools like Cursor, Windsurf, and Replit have seen rapid adoption, and platforms are racing to ensure AI agents understand their specific conventions and limitations.

Installation and Availability

The plugin is available now for Claude Code users. Developers can install it directly through Claude's plugin system, and the rules will automatically apply when the AI generates Postgres-related code within Supabase projects.

Supabase continues to expand its developer tooling ecosystem, recently introducing features like missing index detection and private network connectivity to AWS resources. The plugin represents another step in making Postgres more accessible to developers at all skill levels, particularly those leveraging AI assistance in their workflow.

For teams already using AI coding tools on Supabase projects, the plugin offers immediate value with no code changes required. The rules guide the AI toward better patterns automatically, reducing the review burden on human developers and potentially catching issues before they reach production.

Sources

1 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Go deeper on Supabase

Related reading, watching and going.

Everything on Supabase →

The briefing

13 Oct 2026

Jev - The System One AI That Never Writes a Word, Explained

Deep dive into Jev - TypeSafe's 'System One' model that outputs decisions, not text. Read how it works, real demos (driving), what it's good for and its limits.

Read →

The briefing

30 Sept 2026

Solo Consultant's AI Operating System Built on Markdown

London solo consultant uses an AI personal OS of markdown files—saving ~45% delivery time, boosting revenue 2.4×, and powering 33 community events for ~£250/mo.

Read →

The briefing

15 Sept 2026

€300k Business on 4 Hours/Week with AI — Case Study

Read how a one-man Dutch company scaled to €300k/yr and runs on 4 hours/week by rebuilding ops with Claude Code. Submit your AI case study to be featured.

Read →
36 min

Podcast

55. We're Back! Conference Recap, Running Events with AI & Self-Healing Apps

James and Kieran return to the Create With Podcast after their summer break to recap the 2026 Create With Conference in Brighton. They discuss how 550 attendees experienced workshops, a charity hackathon where functional apps were built in 30 minutes, and an innovative conference operating system built entirely with AI. The episode covers the latest developments in AI development tools including Anthropic's Fable model, scheduled tasks in Codex, and self-healing applications using PostHog.

Watch now ↗
34 min

Podcast

My Daughter Built a Website Business, Claude Design First Look & Going All-In on Cloudflare

James and Kieran discuss practical AI-powered development through real-world examples, including a seven-year-old building a website business with Claude Code voice mode, Anthropic's new Claude Design tool, API security challenges in the AI agent era, and Cloudflare's expanding AI infrastructure offerings. The episode covers hands-on experiences with vibe coding, emerging design tools, and the evolving landscape of AI-assisted development.

Watch now ↗

Podcast

53. Why Your Vibe Code Needs Tests, Ditching SaaS & AI Agents That Work While You Sleep

James and Kieran discuss the practical realities of building AI-powered software, emphasizing the importance of testing in vibe-coded applications, exploring alternatives to traditional SaaS tools, and implementing autonomous AI agents for business operations. The episode covers technical topics like Convex databases, app store bottlenecks from AI-generated submissions, and using OpenClaw as a marketing automation agent.

Watch now ↗

Latest tool news

What else changed this week.

All tool news
VercelDigest

What Vercel Shipped in Late October

Vercel shipped quicker static deployments, four AI Gateway models, more free domain choices and new CLI controls in late October. The changes cover developers testing sites…

Vercel

Vercel Adds Submit_feedback to Its MCP

submitfeedback is a new Vercel MCP tool that lets agents and harnesses send bug reports, friction reports and feature requests directly to the Vercel team. Feedback can include…

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.