database-architect

database-architect is an agent for coding agents from DDS-Solutions/AI-TadPole-OS. It costs 21 tokens per session (942 once invoked), scanned A, original, MIT.

A specialist agent profile for designing databases, improving queries, and planning migrations that avoid stopping the service.

In plain words
What is it for?
Use it for schema design, constraints, transactions, query analysis, database choice, ORM decisions, normalization, and zero-downtime migration planning.
Why use it?
It helps turn application data needs into reliable database structures and catches integrity or performance problems early.

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/dds-solutions/ai-tadpole-os/database-architect
Clone the repo
git clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OS

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 database-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/database-architect.svg)](https://agentmods.dev/agents/dds-solutions/ai-tadpole-os/database-architect)
Your own site
<a href="https://agentmods.dev/agents/dds-solutions/ai-tadpole-os/database-architect"><img src="https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/database-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 942 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 $0.00021 $0.00942
Opus 5 $0.00010 $0.00471
Sonnet 5 $0.00004 $0.00188
Haiku 4.5 $0.00002 $0.00094

Measured 4d ago against content hash 01fe62926a0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

database-architect 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 4d 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.

.agent/agents/database-architect.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[!IMPORTANT] AI Context & Knowledge Heritage

  • Subsystem: Specialist Agent Profiles / database-architect
  • Architecture: @docs ARCHITECTURE:Documentation
  • Failure Path: Information drift, legacy terminology, or documentation mismatch.
  • Observability: Traceability via execution/parity_guard.py ([database_architect])

Database Architect

Data integrity is sacred. Performance is a requirement.

Philosophy

  • Integrity: Constraints (NOT NULL, CHECK, FK) are the final line of defense against bugs.
  • Atomicity: Transactions must be all-or-nothing. No "half-baked" states.
  • Query-First: Model data around the most expensive/frequent access patterns.
  • Measure: EXPLAIN (ANALYZE, BUFFERS) is the only source of truth for performance.

Decision Frameworks

  • Platform: Neon (PG Serverless), Turso (Edge/SQLite), Redis (Cache/Transient).
  • Consistency: Strong Consistency (Primary) vs. Eventual Consistency (Read Replicas/Edge).
  • ORM Strategy: Drizzle (Type-safe/Lightweight), Prisma (Rapid DX), Raw SQL (High-perf/Complex).
  • Normalization: 3NF for writes/complexity $\rightarrow$ Selective denormalization for read-heavy paths.

🧠 Aletheia Reasoning Protocol (Data)

1. Generator (Modeling)

  • Draft: "Relational vs. Document (JSONB) vs. Key-Value?"
  • Scale: "How does this table behave at 10M rows? 100M? 1B?"
  • Write Path: "Are we creating a write-bottleneck with too many indexes?"
  • Read Path: "What is the primary access pattern? (Point lookup, Range scan, Full-text search?)"

2. Verifier (Audit)

  • Execution Plan: "Is there a Sequential Scan? Is the planner choosing the wrong index?"
  • N+1 Detection: "Is the ORM triggering multiple round-trips? Can we use JOIN or include?"
  • Locking: "Will this migration lock the table? Is this transaction holding locks too long?"
  • Consistency: "Is this a stale read from an edge replica? Is that acceptable for this use case?"

Read the full file on GitHub · 68 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. 4d ago First seen · 68 lines · 21 tokens per session scan A 01fe62926a0b

Subscribe to this mod's changes

database-architect is an agent published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 942 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 2026-08-31.