reverse-db-architect

reverse-db-architect is an agent for Claude Code from zekiriabd/SDD-Pro. It costs 132 tokens per session (2,588 once invoked), scanned A, original, Apache-2.0.

A database architecture agent that interprets a prepared summary of a database's tables, relationships, objects, and dependencies. It creates a business glossary, groups the database into subdomains, and identifies architectural roles and risks while separating facts from hypotheses.

In plain words
What is it for?
Use it once per database to provide context for later analysis, explain major table groups, identify likely business areas, and highlight risk zones.
Why use it?
Object-by-object analysis can miss the bigger picture of what the database represents and how its parts fit together.

Agent for Claude Code

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/zekiriabd/sdd-pro/reverse-db-architect
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

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 reverse-db-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-db-architect.svg)](https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-db-architect)
Your own site
<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-db-architect"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-db-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 132 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,588 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 $0.00132 $0.02588
Opus 5 $0.00066 $0.01294
Sonnet 5 $0.00026 $0.00518
Haiku 4.5 $0.00013 $0.00259

Measured 3d ago against content hash 5f8259b20523, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reverse-db-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 3d 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.

.claude/agents/reverse-db-architect.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reverse-DB-Architect — Phase 0.B du reverse base de données

Rôle

Tu es un architecte de bases de données. Tu interviens une seule fois par base, avant que le moindre objet SQL ne soit remonté en User Story, et tu réponds à la question que chaque analyste répondait jusqu'ici seul et mal : de quoi parle cette base, et comment ses morceaux tiennent-ils ensemble ?

Tu n'es pas un analyste d'objets. Tu ne lis aucun corps de procédure. Tu travailles à l'altitude de la base : familles de tables, sous-domaines, rôles, risques. Les objets sont lus plus tard, un par un, par les spécialistes — qui liront ton interprétation dans leur contexte.

Le contrat qui te définit : faits ≠ hypothèses

La Phase 0.A (déterministe, 0 token) a déjà produit les faits : tables, colonnes, clés, contraintes, index, objets, matrice CRUD, graphe de dépendances, plan de vagues. Ces faits sont vérifiables et portent une evidence fichier:ligne.

Tu ne produis aucun fait. Tu produis des hypothèses. Une hypothèse est une interprétation plausible que le code ne prouve pas. Elle est stockée dans une branche séparée du document, elle ne peut jamais devenir un Acceptance Criteria, et le validateur la refuse si elle tente de s'y déguiser.

Ce qui garantit cette frontière, précisément (audit 2026-08-29, M3 — la formulation « garantie par construction » qui figurait ici était plus large que le mécanisme réel) :

  1. La whitelist de fusion — tu écris un fichier distinct (db-context.hypotheses.json), et db_context.merge_architect_output ne recopie que cinq clés : glossary, subdomains, objectRoles, risks, openQuestions. Un facts ou un executionPlan présent dans ton fichier n'est pas refusé bruyamment : il est ignoré. C'est la protection réelle, et elle est totale — pour ce chemin-là.
  2. La matrice d'ownership (audit_file_ownership.py) — elle journalise désormais les fichiers que tu touches pendant ta fenêtre de dispatch, et signale tout ce qui sort de ton périmètre.
  3. Le contrôle de versioncontextVersion refuse une fusion construite sur des faits périmés ([REVERSE_DB_CONTEXT_STALE]).

Read the full file on GitHub · 181 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. 3d ago First seen · 181 lines · 132 tokens per session scan A 5f8259b20523

Subscribe to this mod's changes

reverse-db-architect is an agent published in the GitHub repository zekiriabd/SDD-Pro (189 stars, last pushed today), licensed Apache-2.0. It adds 132 tokens to every session and 2,588 once invoked, about $0.0007 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

database-monitoring

Query and manage Datadog Database Monitoring (DBM) data, including database metrics, query performance, and DBM-specific monitors.

DataDog/pup · 27 tokens

core-data-auditor

Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking. Automatically scans Core Data code for the 5 most critical safety violations - schema migration risks, thread-confinement errors, N+1 query patterns, production data loss risks, and performance issues…

CharlesWiltgen/Axiom · 261 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

django-migrations-specialist

Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…

AratKruglik/claude-sdlc · 85 tokens

database-architect

Use this agent for database design and change work: schema design, indexing strategy, query optimization, migration safety, and engine selection. Trigger on "design a schema for", "this query is slow", "is this migration safe", "add an index", "Postgres or Mongo for this", or N+1 complaints. Returns schema/DDL with…

aayushostwal/nexus · 96 tokens

db-performance-auditor

Audits a .NET data-access layer end to end for performance — EF Core query patterns (N+1, projections, tracking), indexing gaps, DbContext configuration, connection resiliency, and bulk-operation opportunities — and produces a ranked report with fixes. Use when the user wants a database/EF performance review of a…

StefanTheCode/dotnet-ai-toolkit · 88 tokens