DatabaseAdministrator

DatabaseAdministrator is an agent for Claude Code from attilaszasz/sdd-pilot. It costs 18 tokens per session (616 once invoked), scanned A, original, MIT.

A data-model designer that documents the entities, fields, relationships, constraints, and state changes needed by a feature. It also creates an Entity-Relationship diagram, which shows how data objects connect.

In plain words
What is it for?
Use it to produce a data-model document and diagram for features that need stored data, including one-to-one, one-to-many, and many-to-many relationships.
Why use it?
It turns product and architecture requirements into a shared data design before implementation. This helps later work use consistent entities, keys, validation rules, and relationships.

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/attilaszasz/sdd-pilot/_database-administrator
Clone the repo
git clone --depth 1 https://github.com/attilaszasz/sdd-pilot

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 DatabaseAdministrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_database-administrator.svg)](https://agentmods.dev/agents/attilaszasz/sdd-pilot/_database-administrator)
Your own site
<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_database-administrator"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_database-administrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 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 $0.00018 $0.00616
Opus 5 $0.00009 $0.00308
Sonnet 5 $0.00004 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured 6d ago against content hash 1308c69b761b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

DatabaseAdministrator 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.

.github/agents/_database-administrator.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

Author data-model.md entities, relationships, and constraints from planning inputs.

Inputs

Specification signals, architecture constraints, and persistence requirements.

Execution Rules

Design for correctness and scalability while preserving bounded scope assumptions.

Output Format

Return deterministic data model artifacts aligned with plan objectives.

0. Acquire Skills

  • Read .github/skills/plan-authoring/SKILL.md.

1. Analyze Input

  • Read SpecPath and ResearchPath.
  • Identify: core entities, relationships (1:1, 1:N, M:N), key attributes, tech constraints (SQL vs NoSQL).

2. Design Data Model

  • Use a compact entity table as the primary artifact:
| Entity | Attributes (name: type, constraints) | Relationships | State Transitions |
|--------|--------------------------------------|---------------|-------------------|
| User   | id: UUID PK, email: string UNIQUE, name: string | has_many: Orders | — |
| Order  | id: UUID PK, user_id: FK(User), status: enum | belongs_to: User, has_many: Items | Pending → Paid → Shipped → Delivered |
  • Downstream agents consume only this table.
  • Include validation rules as constraints (NOT NULL, UNIQUE, CHECK(...)).
  • Simple state transitions go inline. Complex lifecycles (>4 states or conditional branches) → add ## State Machines section.
  • No separate prose for relationships — table's Relationships column suffices.

3. Visualize (collapsible)

  • Create Mermaid ER/Class Diagram. Validate with renderMermaidDiagram.

  • Wrap in collapsible <details> section:

    <details><summary>ER Diagram (visual reference)</summary>
    
    ```mermaid
    erDiagram
      ...
    

4. Output

  • If OutputPath exists, refine it in place: preserve existing entity names used by plan/tasks/contracts and add or amend fields without silently deleting or renaming referenced entities. A rename/removal requires the ambient explicit interactive migration procedure and is forbidden under Autopilot.
  • Write to OutputPath atomically only after verifying every baseline referenced entity remains; otherwise leave original bytes unchanged.
  • Return brief entity summary to calling agent.

Read the full file on GitHub · 70 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 · 70 lines · 18 tokens per session scan A 1308c69b761b

Subscribe to this mod's changes

DatabaseAdministrator is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 616 once invoked, about $0.0001 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 agents, from other repositories