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/import-validationgit clone --depth 1 https://github.com/prisma/ormWhat 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 | $0.01067 |
| Opus 5 | $0.00000 | $0.00534 |
| Sonnet 5 | $0.00000 | $0.00213 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
import-validation 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 2d 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:
- import-validation — 100% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import Validation
The repo uses a domain/layer/plane package layering architecture with unidirectional dependencies
enforced by Dependency Cruiser, driven by data from architecture.config.json.
Domain/Layer/Plane Structure
Packages are organized by:
- Domains: framework (target-agnostic) and target families (sql, document, etc.).
- Layers: dependencies flow inward (toward core) within a domain —
core → authoring → targets → lanes → runtime → adapters. - Planes: migration (authoring, tooling, targets), runtime (lanes, runtime, adapters), and shared (cross-plane code and prebuilt artifacts safe for both).
Configuration (architecture.config.json)
dependency-cruiser.config.mjs reads data-driven config:
- Package configs map a glob to domain/layer/plane:
{ "glob": "packages/framework/core-plan/**", "domain": "framework", "layer": "core", "plane": "shared" } - Layer order defines dependency direction per domain:
{ "layerOrder": { "sql": ["core", "authoring", "targets", "lanes", "runtime", "adapters"] } } - Rules define allowed/denied patterns:
{ "rules": { "sameLayer": "allow", "downward": "allow", "upward": "deny", "crossDomain": "denyExceptFramework", "migrationToRuntime": "deny", "runtimeToMigration": "allowArtifactsOnly" } } - Plane rules declare per-plane
allow/forbidplusexceptions:{ "planeRules": { "shared": { "allow": ["shared"], "forbid": ["migration", "runtime"], "exceptions": [] }, "migration": { "allow": ["shared", "migration"], "forbid": ["runtime"], "exceptions": [] }, "runtime": { "allow": ["shared", "runtime"], "forbid": ["migration"], "exceptions": [] } } }
Rules
- Same-layer imports allowed — e.g.
orm-lanemay importsql-relational-core(bothlanes):import { schema } from '@internal/sql-relational-core/schema'; - Cross-layer: import only from inner layers (closer to core). Outer layers cannot be imported
by inner ones:
// ✅ lanes importing core import { planInvalid } from '@internal/plan'; // ❌ core importing lanes import { sql } from '@internal/sql-lane';
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.
- 2d ago First seen · 102 lines · 0 tokens per session scan A 8bdfedb5e69d
import-validation is a cursor rule published in the GitHub repository prisma/orm (47,579 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,067 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
config-validation-and-normalization
Patterns for config validation and normalization using Arktype.
contract-space-package-layout
On-disk layout for packages that expose a contract space (extensions, internal monorepo packages, aggregate-root apps).
cli-package-exports
CLI package export patterns and import conventions.
resolving-cyclic-dependencies
How to resolve cyclic dependencies when moving types or refactoring packages.
no-family-vocabulary-in-framework
The framework domain (packages/1-framework) carries no family- or target-specific vocabulary — types, fields, hooks, or strategy values. Enforced by lint:framework-vocabulary.
review-scope-overrides
Honor explicitly provided base branches in review artifacts.