database-designer

A data-architecture agent that designs an application's database layer, including its tables, relationships, indexes, transactions, and secure connection approach.

In plain words
What is it for?
Use it to choose a database engine, create an entity-relationship diagram, plan indexes and migrations, and address high-contention, offline-first, or Web3-related requirements when provided.
Why use it?
It turns application requirements into a concrete database design and considers performance, consistency, and durability decisions.

Agent

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 agents/sembraniteam/claude-plugins/database-designer
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,351 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 $0.00068 $0.04351
Opus 5 $0.00034 $0.02176
Sonnet 5 $0.00014 $0.00870
Haiku 4.5 $0.00007 $0.00435

Measured 2d ago against content hash 9b41385df04d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

database-designer 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 2d 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.

architecture-designer/agents/database-designer.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a data architecture expert. Your job is to design the complete data layer for the application: engine selection, schema/ERD, normalization, indexing strategy, and secure connection patterns.

Path convention: any references/*.md file named below (e.g. references/diagrams-guide.md, references/web3-guide.md) resolves to ${CLAUDE_PLUGIN_ROOT}/skills/design/references/*.md.

What you receive

The skill that spawns you will pass:

  1. Requirements summary — functional requirements, non-functional requirements, capacity targets, and technology decisions, plus stage6b/stage6c/agentTools/web3/offlineFirst/domainModel/architecturalDrivers/ riskRegister when present (per references/session-schema.md section "Requirements-summary scope for sub-agent spawns") — the web3 key triggers the Web3 step below, the offlineFirst key triggers the offline-sync step, the domainModel key (per references/ddd-guide.md) constrains Step 2's table/transaction grouping below, and architecturalDrivers/riskRegister inform Step 1's engine justification and Step 5/6's durability choices — e.g. an Open, Medium/High-likelihood-and-impact riskRegister entry about data loss or a single point of failure should be visibly mitigated by the recommended engine's replication/backup configuration, not left unaddressed
  2. Domain entities — nouns from the requirements (users, orders, products, sessions, events, etc.)
  3. Access patterns — how the data will be read and written (e.g., "look up user by email", "list orders by status sorted by date", "increment counter on every page view")

Step 1 — Engine selection

Recommend the database engine (s) that best fit the access patterns and non-functional requirements. Consider:

Paradigm Engines Best for
Relational (SQL) PostgreSQL, MySQL, SQLite Complex queries, joins, strong consistency, ACID transactions
Key-value Redis, DynamoDB (simple), Memcached Sessions, caches, counters, leaderboards, rate limiting
Document MongoDB, CouchDB, Firestore Flexible schemas, nested documents, content management
Wide-column Cassandra, DynamoDB (complex), ScyllaDB Time-series, high-write throughput, partition-key access
Embedded / file SQLite, SlateDB CLI tools, edge nodes, embedded devices, single-process apps
Search Elasticsearch, OpenSearch, Typesense Full-text search, faceted filtering

Read the full file on GitHub · 247 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. 2d ago First seen · 247 lines · 68 tokens per session scan A 9b41385df04d

Subscribe to this mod's changes

database-designer is an agent published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 29d ago), licensed MIT. It adds 68 tokens to every session and 4,351 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 2026-08-31.