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/use-ast-factoriesgit 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/use-ast-factories)<a href="https://agentmods.dev/rules/prisma/orm/use-ast-factories"><img src="https://agentmods.dev/badge/rules/prisma/orm/use-ast-factories.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 | $0.00731 |
| Opus 5 | $0.00000 | $0.00365 |
| Sonnet 5 | $0.00000 | $0.00146 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
use-ast-factories 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 yesterday.
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:
- use-ast-factories — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Factory Functions for AST Nodes
CRITICAL: When creating AST nodes in tests, use factory functions instead of manual object creation.
The Problem
Manual AST node creation:
- Duplicates AST structure definitions
- Is error-prone (easy to miss required fields or use wrong values)
- Makes refactoring harder (changes to AST structure require updates in many places)
- Doesn't benefit from factory function validation
The Solution
❌ WRONG: Manual AST node creation
const colRef: ColumnRef = { kind: 'col', table: 'user', column: 'id' };
const paramRef: ParamRef = { kind: 'param', index: 1, name: 'userId' };
const literalExpr: LiteralExpr = { kind: 'literal', value: 'test' };
✅ CORRECT: Use factory functions
import { createColumnRef, createParamRef, createLiteralExpr } from '@internal/sql-relational-core/ast';
const colRef: ColumnRef = createColumnRef('user', 'id');
const paramRef: ParamRef = createParamRef(1, 'userId');
const literalExpr: LiteralExpr = createLiteralExpr('test');
Available Factory Functions
From @internal/sql-relational-core/ast:
createColumnRef(table, column)- Creates aColumnRefcreateParamRef(index, name?)- Creates aParamRefcreateLiteralExpr(value)- Creates aLiteralExprcreateTableRef(name)- Creates aTableRefcreateBinaryExpr(op, left, right)- Creates aBinaryExpr(fromast/predicate)
When to Use Factory Functions
Use factory functions when:
- ✅ Creating
ColumnRef,ParamRef,LiteralExpr,TableRefin tests - ✅ Creating
BinaryExprin tests - ✅ Any AST node that has a factory function available
Exception: OperationExpr objects are complex and don't have a factory function (the createOperationExpr function just returns the operation as-is). Manual creation is acceptable for OperationExpr in tests.
Benefits
- Consistency: All AST nodes created the same way
- Type safety: Factory functions ensure correct structure
- Maintainability: Changes to AST structure only need updates in factory functions
- Less duplication: No need to repeat AST structure in tests
- Validation: Factory functions can validate inputs
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.
- yesterday First seen · 76 lines · 0 tokens per session scan A 7194153753f0
use-ast-factories is a cursor rule published in the GitHub repository prisma/orm (47,601 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 731 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 2026-09-03.
Other cursor rules, from other repositories
typescript-patterns
TypeScript and architecture patterns for this codebase.
tsdown-config-package-source-only
Keep @prisma-next/tsdown source-only exports.
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.
no-inline-imports
Prohibit inline type imports in source files.
use-hash-constructors
Use coreHash() and profileHash() constructors instead of 'as never' casts for branded hash types.
use-if-defined
Use ifDefined() for conditional object spreads.