agentmods.dev

dpf-data-architecture-steward

dpf-data-architecture-steward is a skill for Claude Code from OpenDigitalProductFactory/opendigitalproductfactory. It costs 39 tokens per session (1,543 once invoked), scanned A, original, Apache-2.0.

A service for explaining and checking a database’s structure. It reads the Prisma data model, mirrors its tables and relationships in a live entity-relationship diagram (ERD), and reports differences between the model and the diagram.

In plain words
What is it for?
Use it to inspect tables, fields, foreign keys, indexes, relationships, the ERD, or changes in the data architecture over time.
Why use it?
It helps people see how data tables connect and catches schema drift, where the documented or visual structure no longer matches the database model.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the dpf-platform plugin — 68 skills, 1 hook shipped together

not rated 14repo changed 2d ago A scan 39 tokens original Apache-2.0

Good fit Use it to inspect tables, fields, foreign keys, indexes, relationships, the ERD, or changes in the data architecture over time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendigitalproductfactory/opendigitalproductfactory/dpf-data-architecture-steward
View source ↗ OpenDigitalProductFactory/opendigitalproductfactory
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.

Any agent
npx skills add OpenDigitalProductFactory/opendigitalproductfactory --skill dpf-data-architecture-steward
Clone the repo
git clone --depth 1 https://github.com/OpenDigitalProductFactory/opendigitalproductfactory

Made for: Claude Code.

Or install dpf-platform, the plugin that ships this one along with the rest of its 68 skills, 1 hook.

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 dpf-data-architecture-steward

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendigitalproductfactory/opendigitalproductfactory/dpf-data-architecture-steward/github.svg)](https://agentmods.dev/skills/opendigitalproductfactory/opendigitalproductfactory/dpf-data-architecture-steward)
Your own site
<a href="https://agentmods.dev/skills/opendigitalproductfactory/opendigitalproductfactory/dpf-data-architecture-steward"><img src="https://agentmods.dev/badge/skills/opendigitalproductfactory/opendigitalproductfactory/dpf-data-architecture-steward/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dpf-data-architecture-steward

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendigitalproductfactory/opendigitalproductfactory/dpf-data-architecture-steward"><img src="https://agentmods.dev/badge/skills/opendigitalproductfactory/opendigitalproductfactory/dpf-data-architecture-steward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00039 $0.01543
Opus 5 $0.00019 $0.00772
Sonnet 5 $0.00008 $0.00309
Haiku 4.5 $0.00004 $0.00154

Measured 2d ago against content hash b2249f14fd35, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dpf-data-architecture-steward 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 2d 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.

packages/dpf-skill-pack/skills/dpf-data-architecture-steward/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Architecture Steward

The Data Architect (AGT-BUILD-DA) owns the self-maintaining data architecture (EP-DATA-ARCH): the Prisma data model is mirrored into the EA tool as a live ERD that stays current as the schema evolves, and drift is surfaced as governed conformance findings.

Use this skill when someone — in Build Studio or on-demand in chat — asks to see, explain, or refresh the data architecture.

The loop you steward

  1. Extract — parsePrismaSchema reads schema.prisma into models, fields, relations, cardinality, and FK-index facts (apps/web/lib/build/code-graph/extractors/prisma-schema-adapter.ts).
  2. Mirror — reconcileDataModelMirror projects those facts into the EA substrate as data_object elements + associated_with relationships, idempotently, under the system-owned Data Model view; it writes an EaSnapshot on material change and stops (with a conformance issue) on duplicate identity (apps/web/lib/ea/data-model-mirror-apply.ts).
  3. View — the ERD renders at /ea/data-model (and the generic /ea/views/[id] renderer) with an evolution timeline.
  4. Steward — runDataArchitectureSteward runs deterministic drift detectors (FK-without-index, missing-inverse-relation, orphan-model, ignored-model) and reconciles them into self-healing EaConformanceIssue rows (apps/web/lib/ea/data-architecture-steward-apply.ts).

runDataModelMirror composes all of this; it runs nightly (scheduled task data-model-mirror-nightly) and on demand (the "Generate data model now" action / this skill).

How to answer

  • "Show / refresh the data architecture" → ensure the mirror is current (it may need a run if the ERD is empty), then summarize the Data Model view: model count, domain groupings, and open drift findings.
  • "What does model X relate to / what depends on it?" → use describe_model for fields, query_ontology_graph / explain_blast_radius for relationships and impact.
  • Drift questions ("which FKs lack indexes?") → read the open EaConformanceIssue rows of the relevant issueType; cite the specific models.

Read the full file on GitHub · 66 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. 2d ago Changed · +15 lines · +2 tokens per session b2249f14fd35
  2. 13d ago First seen · 51 lines · 37 tokens per session scan A ef3f322a4c71

Subscribe to this mod's changes

dpf-data-architecture-steward is a skill published in the GitHub repository OpenDigitalProductFactory/opendigitalproductfactory (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,543 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 2026-08-30.

Databasesagentic-workflowagentsaidata-stewardshipit4itmcpnextjs
Related

Other skills, from other repositories

projection-patterns

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

wshobson/agents · 36 tokens

migration-review

Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.

rohitg00/ai-engineering-from-scratch · 35 tokens

historic_sql_table_digest

Convert one changed historic-SQL table usage bucket into typed table usage evidence for deterministic schema projection.

Kaelio/ktx · 25 tokens

dsql

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…

awslabs/agent-plugins · 229 tokens

nestjs-best-practices

Provides comprehensive NestJS best practices including modular architecture, dependency injection scoping, exception filters, DTO validation with class-validator, and Drizzle ORM integration. Use when designing NestJS modules, implementing providers, creating exception filters, validating DTOs, or integrating Drizzle…

giuseppe-trisciuoglio/developer-kit · 64 tokens

multi-surface-render

Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output…

yonatangross/orchestkit · 98 tokens