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 skills add kavo-labs/kavo --skill prisma-adaptergit clone --depth 1 https://github.com/kavo-labs/kavoWrote 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/skills/kavo-labs/kavo/prisma-adapter)<a href="https://agentmods.dev/skills/kavo-labs/kavo/prisma-adapter"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/prisma-adapter/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/skills/kavo-labs/kavo/prisma-adapter"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/prisma-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01187 |
| Opus 5 | $0.00044 | $0.00593 |
| Sonnet 5 | $0.00018 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
prisma-adapter 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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prisma adapter
@kavo/prisma adapts Kavo to a Prisma Client. The engine, routes, query
grammar, DTO slots, and error shapes are identical to every other adapter —
only the wiring below differs.
npm install @kavo/core @kavo/nest @kavo/prisma
@prisma/client (^5.0.0 || ^6.0.0) is a peer dependency.
The one thing that is not like TypeORM: marker classes
Prisma generates no runtime class for a model. prisma generate produces
types and a client with delegates (prisma.book), but nothing that survives
to runtime as a constructor — and @Kavo(Entity) needs a stable runtime
identity to key an entity by.
So each model needs a small marker class: an empty class whose name matches the Prisma model exactly.
// book.entity.ts
export class Book {
id!: number;
title!: string;
}
This is the shape of the trap. The natural guess — passing the delegate, the way you would pass an entity class with TypeORM — does not work:
@Kavo(prisma.book) // ✗ wrong — a delegate is not an identity
@Kavo(Book) // ✓ the marker class
Declare the fields anyway — they are what gives you type safety. At
runtime @kavo/prisma reads only .name off the class and takes all real
metadata from Prisma's DMMF, so an empty class Book {} still produces
working routes. But the declared fields are what type createCrud's generic
parameters, so an empty marker class collapses Entity to {} and every
typed surface built on it silently stops checking anything:
allowed.filterable/sortable/selectable, query.defaultSort, and the
DTO slot generics all stop rejecting misspelled field names at compile time.
Name-matching is what binds class to model, so a marker class named Books
for a model named Book will not resolve — that one fails loudly, as a
bootstrap ConfigurationException rather than a silent no-op. See ADR-0017
for the full rationale.
Wiring
// app.module.ts
import { Module } from "@nestjs/common";
import { KavoModule } from "@kavo/nest";
import { createInfrastructure } from "@kavo/prisma";
import { PrismaClient, Prisma } from "@prisma/client";
import { Book } from "./book.entity.js";
import { BookController } from "./book.controller.js";
const prisma = new PrismaClient();
@Module({
imports: [
KavoModule.forRoot({
infrastructure: createInfrastructure(prisma, {
datamodel: Prisma.dmmf.datamodel,
entities: [Book],
}),
}),
],
controllers: [BookController],
})
export class AppModule {}
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.
- 4d ago Changed 04d099bf199f
- 7d ago First seen · 135 lines · 88 tokens per session scan A f7762aeb83e6
prisma-adapter is a skill published in the GitHub repository kavo-labs/kavo (14 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,187 once invoked, about $0.0004 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 2026-09-02.
Other skills, from other repositories
servicenow-table-api
Foundational ServiceNow data access — generic Table API CRUD, Aggregate/stats roll-ups, and raw REST escape-hatch via the servicenow-api MCP server. Use when the agent must read, insert, update, patch, delete, count, or aggregate records in ANY ServiceNow table (including scoped app tables with no dedicated API), or…
prisma-8
Comprehensive guide for building with Prisma 8 (Prisma Next), the contract-first data layer. Use whenever working on Prisma code in a project that uses it — authoring or editing the data contract (contract.prisma, PSL, TypeScript builders), migrations, queries (db.orm / db.sql), runtime wiring (db.ts, middleware…
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
ocli-api
Turn any OpenAPI/Swagger API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.
db-infra-mocks
Propose minimal seams and local substitutes so tests run without real RDBMS/Redis/Mongo infrastructure.
mail-time
Use when building, wiring, reviewing, or debugging MailTime and ostrio:mailer email queues for horizontally scaled Node.js, Bun, or Meteor apps. Trigger on MailTime, MongoQueue, RedisQueue, PostgresQueue, mailTimePreset, JoSk email scheduling, Redis Cluster / KeyDB Cluster / Valkey useHashTags, KeyDB…