mk:database

mk:database is a skill for Claude Code, Codex from ngocsangyem/MeowKit. It costs 56 tokens per session (2,315 once invoked), scanned A, original, MIT.

A workflow for designing and safely changing databases, including data models, schemas, migrations, queries, indexes, and ORM access boundaries. An ORM is a tool that connects application code to database records.

In plain words
What is it for?
Use it for schema design, migrations, query and index work, recovery planning, datastore selection, and database access-layer changes.
Why use it?
It reduces the risk of breaking stored data or making changes that do not fit the database engine already used by the project.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ngocsangyem/meowkit/database
Any agent
npx skills add ngocsangyem/MeowKit --skill database
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code, Codex.

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 mk:database

README.md
[![agentmods](https://agentmods.dev/badge/skills/ngocsangyem/meowkit/database.svg)](https://agentmods.dev/skills/ngocsangyem/meowkit/database)
Your own site
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/database"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/database.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.02315
Opus 5 $0.00028 $0.01157
Sonnet 5 $0.00011 $0.00463
Haiku 4.5 $0.00006 $0.00231

Measured yesterday against content hash 830625ba2964, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mk:database 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.

.claude/skills/database/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Database

Data invariants first, engine syntax second. Discover what the repository already runs before proposing anything.

Ownership

Owner Owns Does NOT own
mk:api-design-principles Interface contract: resource/type/message shape, error and authorization requirements, compatibility and deprecation, consumer discovery Implementation, persistence, security verdict, release
mk:backend-development End-to-end backend change: discovery, classification, service/handler/integration work Contract authorship, schema/SQL, security verdict, deploy
mk:database Data invariants, schema, migration and recovery, query/index evidence, ORM data-access boundary API contract, authorization verdict, infrastructure execution
mk:devops Infrastructure-as-code, containers, CI, runtime config, deployment safety design, rollback, incident diagnosis Deploy approval and execution, security verdict, code root-cause, schema semantics

Routing rules — identical in all four skills:

  • Contract-only API question → mk:api-design-principles, even in the middle of a task owned by another skill. "Contract" means what a consumer can observe: field set, error shape, status semantics, pagination, versioning. Extending an endpoint without changing any of those is not a contract change.
  • End-to-end backend change → mk:backend-development, which invokes the API skill only when a new, public, or breaking contract is in scope.
  • A message-based change (event, webhook, RPC) splits: the message contract belongs to mk:api-design-principles; the producer or consumer implementation belongs to mk:backend-development.
  • Schema, migration, query, index, or ORM work → mk:database. No other skill writes a migration or generic SQL.
  • Infrastructure, containers, delivery, or deployment safety → mk:devops.
  • An unscoped performance request is triaged by evidence, never by guess: mk:backend-development locates where the time actually goes, then hands a query or index question to mk:database and a capacity or runtime question to mk:devops. No skill invents the target.
  • Code root cause → mk:investigate. mk:devops owns the operational picture — what changed, where it fails, which signal proves it — and hands the defect over.
  • An auth-sensitive change: the owning skill states the requirement; the security workflow owns the verdict.
  • Any production effect → mk:ship or a human.

Read the full file on GitHub · 197 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 197 lines · 56 tokens per session scan A 830625ba2964

Subscribe to this mod's changes

mk:database is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,315 once invoked, about $0.0003 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 2026-09-03.