Prisma ORM is a Node.js and TypeScript database toolkit that lets applications work with databases through a programming interface instead of writing every query directly in SQL. Developers use it with databases including PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB, and CockroachDB. The catalogue add-ons provide agent rules, skills, hooks, agents, and other workflows for using Prisma.
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.
git clone --depth 1 https://github.com/prisma/ormWrote 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/prisma/orm/multi-plane-packages)<a href="https://agentmods.dev/rules/prisma/orm/multi-plane-packages"><img src="https://agentmods.dev/badge/rules/prisma/orm/multi-plane-packages/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/rules/prisma/orm/multi-plane-packages"><img src="https://agentmods.dev/badge/rules/prisma/orm/multi-plane-packages.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 | $0.00000 | $0.00901 |
| Opus 5.5 | $0.00000 | $0.00360 |
| Sonnet 5.5 | $0.00000 | $0.00180 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
multi-plane-packages 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- multi-plane-packages — 95% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Plane Packages
Overview
Some packages need to span multiple planes (shared, migration, runtime) to provide both CLI entry points and runtime implementations. These packages use a structured directory layout to separate code by plane.
Structure
Multi-plane packages use the following structure:
packages/{domain}/{package-name}/
├── src/
│ ├── core/ # Shared plane code
│ │ ├── adapter.ts # Core implementation
│ │ ├── codecs.ts # Codec definitions
│ │ └── types.ts # Type definitions
│ └── exports/ # Entry points
│ ├── control.ts # Migration plane (control plane descriptors)
│ ├── runtime.ts # Runtime plane (runtime factories)
│ ├── adapter.ts # Re-export from core
│ ├── codec-types.ts # Re-export from core
│ └── types.ts # Re-export from core
Architecture Config
Multi-plane packages require multiple globs in architecture.config.json, one for each plane:
{
"glob": "packages/targets/postgres-adapter/src/core/**",
"domain": "targets",
"layer": "adapters",
"plane": "shared"
},
{
"glob": "packages/targets/postgres-adapter/src/exports/control.ts",
"domain": "targets",
"layer": "adapters",
"plane": "migration"
},
{
"glob": "packages/targets/postgres-adapter/src/exports/runtime.ts",
"domain": "targets",
"layer": "adapters",
"plane": "runtime"
}
Plane Separation
-
src/core/**: Shared plane code that can be imported by both migration and runtime planes- Core implementation (e.g., adapter, codecs, types)
- No CLI-specific or runtime-specific dependencies
- Can import from shared plane packages only
-
src/exports/control.ts: Migration plane entry point (control plane)- Exports control plane descriptors (
ControlAdapterDescriptor,ControlTargetDescriptor,ControlDriverDescriptor, etc.) - Can import from migration plane packages (e.g.,
@internal/cli,@internal/core-control-plane) - Can import from core (
../core/...) - Naming convention: Use
control.ts(notcli.ts) and export as./control(not./cli)
- Exports control plane descriptors (
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.
- 1mo ago First seen · 115 lines · 0 tokens per session scan A 4c014ae18cd0
multi-plane-packages is a cursor rule published in the GitHub repository prisma/orm (47,693 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 901 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
prisma
Prisma database patterns and conventions for Next.js and TypeScript projects.
typescript-style
TypeScript style — prefer arrow functions and consistent callbacks.
drizzle-patterns
Drizzle ORM patterns and database conventions.
react-typescript
Rules for writing frontend code at PostHog (mostly React + Typescript with Kea).
windsurfrules
Node.js ESM + EloquentJS ORM + PostgreSQL/MongoDB + Express/Fastify.
code-validation-workflow
Code validation workflow (format, lint, test, coverage, typecheck).