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.
npx agentmods add rules/prisma/orm/prefer-psl-in-design-docsgit 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/prefer-psl-in-design-docs)<a href="https://agentmods.dev/rules/prisma/orm/prefer-psl-in-design-docs"><img src="https://agentmods.dev/badge/rules/prisma/orm/prefer-psl-in-design-docs.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 | $0.00437 | $0.00437 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
prefer-psl-in-design-docs 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- prefer-psl-in-design-docs — 100% identical, 0 lines differ
What it actually says
Prefer PSL examples in design docs
PSL is the default authoring surface (most users come from Prisma 1.x/2.x); the TS contract builder is secondary. Design docs (specs, ADRs, architecture docs, READMEs) should reflect that ordering.
- Lead with PSL when illustrating a feature that exists in both surfaces.
- Use TS only when the content is about the TS surface itself — model-handle brands, function-form predicates with
ref(modelHandle), type-level inference, or any capability PSL's grammar cannot express. - A TS example that just restates the PSL one is noise — drop it; equivalence is implied.
- Surface-neutral prose should avoid TS-only or PSL-only phrasing where the capability exists in both.
PSL code blocks must use the prisma language tag, never psl — only prisma is registered with the highlighters (GitHub, VSCode, docs site); psl renders as plain text. (The surface is colloquially "PSL" in prose, but the fence says prisma.)
Why it matters for design
The TS surface is by design a superset of PSL: it can express everything PSL can, plus TS-only capabilities (function-form using/withCheck, richer constraint overrides, closure-scoped helpers). It is never a subset. So PSL is where the difficult limitations bite — a static text parser constrains the grammar, and new design pressure surfaces in PSL first. Design a new authoring capability against PSL first; the TS surface follows by mirroring or extending. A design doc that only shows TS also fails to surface the harder design problem.
Runtime code (db.asUser(jwt), session.sql.from(...), middleware, config objects) has no PSL form and stays in TS — this rule covers authoring examples (contracts, models, fields, relations, policies), not runtime usage.
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 · 22 lines · 437 tokens per session scan A 461179db4a01
prefer-psl-in-design-docs is a cursor rule published in the GitHub repository prisma/orm (47,594 stars, last pushed 2d ago), licensed Apache-2.0. It adds 437 tokens to every session, about $0.0022 per session on Opus 5. 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
sql-types-imports
Canonical import paths for SQL types.
directory-layout
Directory layout rules for SQL family vs concrete targets.
no-bare-casts
No bare as casts in production TypeScript. Use blindCast (value) from @prisma-next/utils/casts as the auditable escape hatch, castAs (value) for declarative-only assertions, or rewrite to eliminate the cast. as const is exempt. Test files are exempt.
test-database-limitations
Test databases created via withDevDatabase() from @prisma-next/test-utils use pglite (an in-memory PostgreSQL implementation via @prisma/dev). Pglite does not support PostgreSQL extensions like pgvector, pgtrgm, etc.
sql-orm-client-whole-shape-assertions
Prefer whole-result-shape assertions with explicit select projections in sql-orm-client tests.
postgres-lateral-patterns
PostgreSQL LATERAL and jsonagg rendering patterns.