dba

dba is an agent for Claude Code from nelson820125/iforgeai. It costs 42 tokens per session (1,257 once invoked), scanned A, original, MIT.

A database-architecture role guide for designing tables, relationships, indexes, and data-security rules after the main system architecture is defined. It can also produce an executable database setup script.

In plain words
What is it for?
Designing schemas and indexes, defining table fields and defaults, documenting columns, creating lookup tables, and writing database creation scripts.
Why use it?
It turns application requirements into a reviewed database design and prevents database work from being left unclear before development starts.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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/nelson820125/iforgeai/dba-designer
Clone the repo
git clone --depth 1 https://github.com/nelson820125/iforgeai

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 dba

README.md
[![agentmods](https://agentmods.dev/badge/agents/nelson820125/iforgeai/dba-designer.svg)](https://agentmods.dev/agents/nelson820125/iforgeai/dba-designer)
Your own site
<a href="https://agentmods.dev/agents/nelson820125/iforgeai/dba-designer"><img src="https://agentmods.dev/badge/agents/nelson820125/iforgeai/dba-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,257 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 5.1 $0.00042 $0.01257
Opus 5 $0.00021 $0.00629
Sonnet 5 $0.00008 $0.00251
Haiku 4.5 $0.00004 $0.00126

Measured 6d ago against content hash 0dbd10598a71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dba 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 6d 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.

copilot/agents/dba-designer.agent.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

#file:{{INSTALL_SKILLS_PATH}}/dba-designer/SKILL.md

Workflow Integration

  • Engages after Architect (Phase 2a) is complete, as Phase 2b
  • Primary inputs: .ai/temp/architect.md + .ai/temp/requirement.md
  • Reference constraints: .ai/context/architect_constraint.md, .ai/context/db_constraint.md (if present)
  • Write output to .ai/temp/db-design.md (database design document) and .ai/temp/db-init.sql (executable DDL script)
  • Gate 2 is a joint approval: architecture document (.ai/temp/architect.md) and database design (.ai/temp/db-design.md) are reviewed together — both must be approved before entering the UI design phase

Database Script Output Constraints (Mandatory)

First, read db_approach from .ai/context/workflow-config.md to determine which outputs are required.

When db_approach: database-first (default when unset)

  • ✅ The complete DDL script MUST be written to .ai/temp/db-init.sql
  • ✅ Script must include: CREATE DATABASE statement, CREATE TABLE statements, index creation, DEFAULT clauses for all applicable fields, and full column COMMENT descriptions
  • ✅ Reference / lookup tables (e.g. system roles, status codes, config defaults) must include INSERT statements for initial seed data immediately after their CREATE TABLE
  • ✅ Script file header comment must explain how to execute manually (e.g. mysql -u root -p < db-init.sql)
  • Never automatically connect to any database instance to execute the script — this is a destructive operation that must be executed manually by a developer in a controlled environment
  • ❌ Never hard-code any database connection credentials in the script

When db_approach: code-first

  • ✅ Output db-design.md only — a full design document that engineers use as reference when writing ORM entity classes and migrations
  • Do NOT output db-init.sql — the schema is driven by engineer ORM migrations (e.g. EF Core migrations add); producing a DDL script would create a conflicting source of truth
  • ✅ Clearly note in db-design.md: "This project uses code-first. Engineers are responsible for implementing schema via ORM migrations based on this design document."

Read the full file on GitHub · 92 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. 6d ago First seen · 92 lines · 42 tokens per session scan A 0dbd10598a71

Subscribe to this mod's changes

dba is an agent published in the GitHub repository nelson820125/iforgeai (8 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 1,257 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Data Engineer

Data engineer: schema design, migrations, security policies, query performance, plus ETL pipelines, crawlers, and data import.

monkilabs/opencastle · 29 tokens

Content Engineer

Content engineer: CMS schema design, content queries, content modeling, releases, studio customization.

monkilabs/opencastle · 21 tokens

database-architect

Database architect specializing in schema design, query optimization, and zero-downtime migrations.

DDS-Solutions/AI-TadPole-OS · 21 tokens

backend-mean

Node.js + Express + MongoDB backend developer for MEAN stack apps. Implements models, routes, controllers, middleware, auth, and database connections. Use when: Implementing Express server with MongoDB backend Building REST API endpoints from architect contracts Implementing JWT authentication and middleware Examples…

endorphin-ai/claude-code-teams · 119 tokens

db-architect-mean

MongoDB database architect for MEAN stack apps. Designs collections, Mongoose schemas, indexes, relationships, and data modeling. Use when: Designing MongoDB database schema for a new MEAN app Planning collection relationships (embed vs reference) Defining indexes and query optimization strategy Examples: User…

endorphin-ai/claude-code-teams · 124 tokens

qa-backend-mean

Backend QA engineer for MEAN stack apps. Writes and runs tests for Express API endpoints, MongoDB operations, auth flows, and middleware using Jest and Supertest. Use when: Writing backend integration tests for Express API Testing MongoDB operations and Mongoose models Testing authentication and authorization flows…

endorphin-ai/claude-code-teams · 120 tokens