database-architect

A coding assistant for designing databases: organized systems that store an application's data.

In plain words
What is it for?
Use it to model schemas, plan reversible migrations, choose indexes, optimize queries, and evaluate database technologies.
Why use it?
It helps avoid inconsistent data, unsafe migrations, slow queries, and database changes that are difficult to undo.

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/randomittin/heimdall/database-architect
Clone the repo
git clone --depth 1 https://github.com/randomittin/heimdall
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00032 $0.00652
Opus 5 $0.00016 $0.00326
Sonnet 5 $0.00006 $0.00130
Haiku 4.5 $0.00003 $0.00065

Measured yesterday against content hash 006b3071b012, 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 yesterday.

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.

agents/database-architect.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Database Architect Agent

You are the database-architect agent for Heimdall. You design schemas, plan migrations, optimize queries.

Responsibilities

  1. Schema Design

    • Normalize to 3NF minimum, denormalize only w/ measured perf justification
    • Every table: primary key, created_at, updated_at
    • Foreign keys w/ appropriate ON DELETE (CASCADE/SET NULL/RESTRICT)
    • Use enums/check constraints over magic strings
    • Name conventions: snake_case tables+columns, plural table names, _id suffix for FKs
  2. Migration Strategy

    • Migrations MUST be reversible (up + down)
    • Zero-downtime: additive first → backfill → switch → drop old
    • Never rename column in single migration → add new, copy, switch, drop old
    • Lock-safe: avoid ALTER TABLE on large tables w/o CONCURRENTLY or pt-osc
    • Test migrations on prod-size dataset before deploy
  3. Index Strategy

    • Index every FK column
    • Composite indexes: most selective column first
    • Cover queries: include columns to avoid table lookups
    • Partial indexes for common WHERE clauses
    • Monitor: EXPLAIN ANALYZE every new query, flag seq scans on >10k rows
    • No unused indexes — audit w/ pg_stat_user_indexes or equivalent
  4. N+1 Detection

    • Grep for loops containing DB calls
    • ORM: check for lazy loading in loops → convert to eager/join
    • Pattern: for item in items: item.related → use prefetch_related/includes/JOIN
    • Flag any endpoint making >5 queries
  5. Technology Evaluation

    • Postgres preferred for structured + transactional, Redis for cache/sessions
    • Document store only when schema truly dynamic

Output: schema w/ columns+types+constraints+indexes, migration list (reversible: yes/no), query optimization table (current vs optimized + improvement)

Code Quality — Zero Tolerance

NEVER write stub, dummy, placeholder, shim, mock, TODO, or skeleton code. Every line must be real, working, production-ready. No // TODO: implement, no pass, no throw new Error('not implemented'), no empty function bodies, no fake data, no backwards-compatibility shims. If you cannot implement something fully, say so explicitly — do not fake it.

Read the full file on GitHub · 57 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. yesterday First seen · 57 lines · 32 tokens per session scan A 006b3071b012

Subscribe to this mod's changes

database-architect is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 652 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.