start

start is a skill for Claude Code, Codex from Hainrixz/claude-db. It costs 79 tokens per session (556 once invoked), scanned A, original, MIT.

A short wizard for choosing a database approach when an application has no schema or database yet. It asks about the app, the information it will store, how that information connects, expected use, scale, reliability needs, and hosting preferences.

In plain words
What is it for?
Use it when starting an app from scratch to decide what database style and engine to use. It also helps outline the first records and relationships to store.
Why use it?
It gives beginners a concrete starting recommendation without requiring database knowledge. The questions connect the application’s needs to a suitable database engine and an initial data model.

Skill for Claude CodeCodex

Part of the claude-db plugin — 36 skills, 6 agents, 1 hook shipped together

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/hainrixz/claude-db/start
Any agent
npx skills add Hainrixz/claude-db --skill start
Clone the repo
git clone --depth 1 https://github.com/Hainrixz/claude-db

Made for: Claude Code, Codex.

Or install claude-db, the plugin that ships this one along with the rest of its 36 skills, 6 agents, 1 hook.

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 start

README.md
[![agentmods](https://agentmods.dev/badge/skills/hainrixz/claude-db/start.svg)](https://agentmods.dev/skills/hainrixz/claude-db/start)
Your own site
<a href="https://agentmods.dev/skills/hainrixz/claude-db/start"><img src="https://agentmods.dev/badge/skills/hainrixz/claude-db/start.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 556 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 $0.00079 $0.00556
Opus 5 $0.00039 $0.00278
Sonnet 5 $0.00016 $0.00111
Haiku 4.5 $0.00008 $0.00056

Measured 5d ago against content hash 71b02197a1c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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 5d 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.

skills/start/SKILL.md · 32 lines

What it actually says

/claude-db:start

The front door for someone with zero artifacts — no schema, no migrations, no database. It asks a short, plain-language wizard and ends with a concrete recommendation. No jargon: no "normalization", "cardinality", or "partition key" in the questions.

$ARGUMENTS = an optional one-line description. If present, pre-fill what you can and skip questions already answered.

How to run it

Follow the 7-question wizard in references/design-wizard.md (the canonical question set and the mapping from answers → paradigm/engine). Ask the questions conversationally, one cluster at a time, in plain words — roughly:

  1. What are you building, in one sentence?
  2. What are the main things you'll store (people, orders, messages, posts…)?
  3. How do those things relate to each other?
  4. What will you do most — look one thing up, list/search many, or crunch numbers over lots of rows?
  5. How much data and how many users, roughly (a hobby project, a startup, or huge)?
  6. Any hard rules — must never lose a record, must be fast above all, has to handle money or personal data?
  7. What are you comfortable running or paying for (managed/serverless vs self-hosted)?

What to produce

  • A plain-language recommendation: which database to start with, in one sentence, and why — defaulting to the boring, safe choice (usually Postgres) unless an answer genuinely points elsewhere.
  • A starter data model for the main things named, with the obvious relationships and the few constraints/keys that keep data clean — described in words, with a simple diagram.
  • A clear next step: "Save this as your schema, then run /claude-db:audit to score it" or "Run /claude-db:design for the full technical layer."

Honesty

  • Never fabricate prices, performance numbers, or row counts; describe trade-offs in plain qualitative terms.
  • If an answer is missing, ask — don't assume. Respond in the user's language (EN/ES).
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. 5d ago First seen · 32 lines · 79 tokens per session scan A 71b02197a1c8

Subscribe to this mod's changes

start is a skill published in the GitHub repository Hainrixz/claude-db (19 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 556 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 2026-08-30.

Related

Other skills, from other repositories

dynamodb

Use when modeling or operating a DynamoDB table: deriving partition/sort keys from access patterns, single-table vs table-per-entity, adding a GSI/LSI, on-demand vs provisioned capacity, or diagnosing hot-partition throttling. NOT relational schema/SQL/EXPLAIN (that is postgresdb), NOT aggregation-pipeline document…

ericrisco/rsc-harness · 82 tokens

malloy-lookml-review

Analyze LookML files as prior art for Malloy modeling. Used during Step 1 (DISCOVER) when .lkml files are present. Coordinates reference files that extract business logic, relationships, and curation decisions. Works with or without a database connection.

malloydata/publisher · 58 tokens

convex-migrations

Schema migration strategies for evolving applications including adding new fields, backfilling data, removing deprecated fields, index migrations, and zero-downtime migration patterns.

waynesutton/convexskills · 35 tokens

database-design-patterns

Database schema design patterns and optimization strategies for relational and NoSQL databases. Use when designing database schemas, optimizing query performance, or implementing data persistence layers at scale.

NickCrew/Claude-Cortex · 37 tokens

terrabase-db-changes

Use when making Postgres schema or migration changes (CREATE/ALTER/DROP TABLE, indexes, columns, constraints, backfills) IN A PROJECT THAT DECLARES A TERRABASE TARGET (a TERRABASEDATABASEURL in its .env). Routes the change through terrabase's MCP tools for a deterministic safety analysis plus a local-Qwen plan, and…

Terrabase-in/terrabase · 98 tokens

erd-studio

Schema rules for ERD Studio data model files — the .erd-studio/ directory uses a two-file system (YAML model definitions + JSON domain diagrams) with strict format rules you must read before editing. Use this skill whenever the task touches files in .erd-studio/ (domain JSON, logical-models YAML, or .sync-plan.json)…

liam-machine/erd-studio · 162 tokens