effect-ontology: Skill for Claude Code

.claude/skills/effect-sql-db/SKILL.md

effect-sql-db is a skill for Claude Code from mepuka/effect-ontology. It costs 32 tokens per session (1,558 once invoked), scanned A, original, MIT.

Patterns for using SQL databases such as those accessed through Drizzle, Kysely, or Prisma with Effect, a TypeScript library for composing reliable asynchronous programs.

In plain words
What is it for?
Use it to wrap a SQL client as a service, define typed database errors, manage transactions and retries, and add database observability.
Why use it?
It helps keep database configuration, errors, retries, transactions, streaming, and monitoring in consistent, typed code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is mepuka/effect-ontology's own configuration. It tells Claude Code how to work on effect-ontology itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything effect-ontology configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mepuka/effect-ontology. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mepuka/effect-ontology/main/.claude/skills/effect-sql-db/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mepuka/effect-ontology

Made for: Claude Code.

Wrote 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.

agentmods badge for effect-sql-db

README.md
[![agentmods](https://agentmods.dev/badge/skills/mepuka/effect-ontology/effect-sql-db/github.svg)](https://agentmods.dev/skills/mepuka/effect-ontology/effect-sql-db)
Your own site
<a href="https://agentmods.dev/skills/mepuka/effect-ontology/effect-sql-db"><img src="https://agentmods.dev/badge/skills/mepuka/effect-ontology/effect-sql-db/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.

agentmods 80×15 button for effect-sql-db

Your own site · 80×15
<a href="https://agentmods.dev/skills/mepuka/effect-ontology/effect-sql-db"><img src="https://agentmods.dev/badge/skills/mepuka/effect-ontology/effect-sql-db.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,558 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01558
Opus 5.5 $0.00013 $0.00623
Sonnet 5.5 $0.00006 $0.00312
Haiku 4.5 $0.00003 $0.00156

Measured 2mo ago against content hash f9070e7292ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

effect-sql-db 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 2mo 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.

.claude/skills/effect-sql-db/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SQL & Databases

When to use

  • You are integrating a SQL client (Drizzle, Kysely, Prisma, mysql2/pg) with Effect
  • You want typed errors, retries, transactions, and observability

Provide DB config via Layer

import { Config, Effect, Layer } from "effect"

class DbConfig extends Effect.Service<DbConfig>()("DbConfig", {
  sync: () => ({
    url: process.env.DATABASE_URL ?? ""
  })
}){}

// Provide once at app boundary
export const DbConfigLive = DbConfig.Default

Wrap a client in a Service (typed errors)

import { Effect } from "effect"

class DatabaseError extends Data.TaggedError("DatabaseError")<{ cause: unknown }>{}

export class Database extends Effect.Service<Database>()("Database", {
  effect: Effect.gen(function* () {
    // drizzle() / new PrismaClient() / kysely instance
    const client = makeDbClient() // your factory (validated url)
    return {
      // use-pattern ensures client is passed from a single place
      use: <A>(cb: (c: typeof client) => Promise<A>) =>
        Effect.tryPromise({ try: () => cb(client), catch: (cause) => new DatabaseError({ cause }) })
    }
  })
}){}

Real-world snippet: Drizzle wrapper with use(cb)

// Pattern adapted from Cap
export class Database extends Effect.Service<Database>()("Database", {
  effect: Effect.gen(function* () {
    return {
      use: <T>(cb: (_: DbClient) => Promise<T>) =>
        Effect.tryPromise({ try: () => cb(db()), catch: (cause) => new DatabaseError({ cause }) })
    }
  })
}){}

Transactions with retry-on-deadlock

// Generic transactional helper with selective retry
const isDeadlock = (e: unknown) => typeof e === "object" && e !== null && (e as any).code === "1213" // MySQL

export const transactional = <A>(eff: Effect.Effect<A, DatabaseError, Database>) =>
  Effect.gen(function* () {
    const db = yield* Database
    return yield* Effect.tryPromise({
      try: () => db.use((c) => c.transaction(async (tx) => await Effect.runPromise(eff))),
      catch: (cause) => new DatabaseError({ cause })
    })
  }).pipe(
    Effect.retry({ schedule: Schedule.exponential("100 millis"), times: 3, while: isDeadlock })
  )

Read the full file on GitHub · 179 lines

Changes

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.

  1. 2mo ago First seen · 179 lines · 0 tokens per session scan A f9070e7292ac

Subscribe to this mod's changes

effect-sql-db is a skill published in the GitHub repository mepuka/effect-ontology (5 stars, last pushed 10mo ago), licensed MIT. It adds 32 tokens to every session and 1,558 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Related

effect-sql-db compared with skills from other repositories

effect-sql-db next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
effect-sql-dbmepuka/effect-ontologySkill510mo agoMITA32Claude Code
create-prprisma/ormSkill48kyesterdayApache-2.0A48Claude Code, Codex
schema-explorationlangchain-ai/deepagentsSkill31kyesterdayMITA57Claude Code, Codex
atlas-mssqlariga/atlasSkill8.8kyesterdayApache-2.0A163Claude Code
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex
nornicdb-cypher-queriesorneryd/NornicDBSkill923yesterdayMITA79Claude Code, Codex
volcengine-rds-postgresqlbytedance/agentkit-samplesSkill484todayApache-2.0A63Claude Code, Codex