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/no-family-vocabulary-in-framework)<a href="https://agentmods.dev/rules/prisma/orm/no-family-vocabulary-in-framework"><img src="https://agentmods.dev/badge/rules/prisma/orm/no-family-vocabulary-in-framework/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/no-family-vocabulary-in-framework"><img src="https://agentmods.dev/badge/rules/prisma/orm/no-family-vocabulary-in-framework.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 | $0.00818 |
| Opus 5 | $0.00000 | $0.00409 |
| Sonnet 5 | $0.00000 | $0.00164 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
no-family-vocabulary-in-framework 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 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.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No family vocabulary in the framework domain
packages/1-framework is consumed by every family (SQL, Mongo) and every target. A concept may enter it only if it is genuinely family-blind.
The test for every new framework export, field, hook, or member: would Mongo populate or consume this meaningfully? If not, it belongs in the family layer (e.g. @internal/sql-contract), behind a structural interface + type predicate at the boundary.
How it is enforced
The no-family-vocabulary Biome plugin matches syntax nodes — identifiers, string literals, template chunks, import paths — carrying family/target terms (table, column, postgres, nativeType, primaryKey, …). It emits info diagnostics; pnpm lint:framework-vocabulary is the ratchet that counts them, deduplicated by file and line, against the threshold in scripts/lint-framework-vocabulary.config.json. The count may only shrink, and the threshold must be lowered whenever it does.
Comments and JSDoc are deliberately not counted. Prose that documents family-blind code correctly ("family-parameterized (SQL, Mongo, …)") is good documentation, and the previous line-scanning checker taxed it — the majority of what it flagged was prose, not surface. A leak that matters is a real type, field, identifier, string, or import path, and the plugin only sees those.
Suppress a genuinely family-blind site at the line, with a reason:
// biome-ignore lint/plugin/no-family-vocabulary: terminal grid layout, not storage
const LEFT_COLUMN_WIDTH = 20;
Then lower the threshold by one. A suppression naming the wrong plugin does not suppress and is reported as suppressions/unused, so a stale one cannot rot silently.
The forbidden terms live in the plugin, not the config — GritQL cannot read JSON, and a second copy nothing reads would drift. To add one, edit biome-plugins/no-family-vocabulary.grit and re-baseline the threshold. The config carries only the scanned path and the threshold.
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 · 42 lines · 0 tokens per session scan A 68d264c247d9
no-family-vocabulary-in-framework is a cursor rule published in the GitHub repository prisma/orm (47,599 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 818 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.
workflow
Workflow for openapi-to-cli.
server-patterns
Rules for server-side Express code.
refactoring-skill
Cursor rule "refactoring-skill" from KaelSensei/MagicAIBuilder, covering refactoring skill, principles, techniques, safety and cursor behavior.
chassis
Chassis conventions — decorator-driven Express 5 + TypeScript.