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 skills/hainrixz/claude-db/startnpx skills add Hainrixz/claude-db --skill startgit clone --depth 1 https://github.com/Hainrixz/claude-dbWrote 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/hainrixz/claude-db/start)<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>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 | $0.00079 | $0.00556 |
| Opus 5 | $0.00039 | $0.00278 |
| Sonnet 5 | $0.00016 | $0.00111 |
| Haiku 4.5 | $0.00008 | $0.00056 |
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.
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:
- What are you building, in one sentence?
- What are the main things you'll store (people, orders, messages, posts…)?
- How do those things relate to each other?
- What will you do most — look one thing up, list/search many, or crunch numbers over lots of rows?
- How much data and how many users, roughly (a hobby project, a startup, or huge)?
- Any hard rules — must never lose a record, must be fast above all, has to handle money or personal data?
- 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:auditto score it" or "Run/claude-db:designfor 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).
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.
- 5d ago First seen · 32 lines · 79 tokens per session scan A 71b02197a1c8
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.
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…
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.
convex-migrations
Schema migration strategies for evolving applications including adding new fields, backfilling data, removing deprecated fields, index migrations, and zero-downtime migration patterns.
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.
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…
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)…