What is data-rag-architect?

A specialist agent for database design, data pipelines, analytics systems, search with stored document context, and access-control models. It covers both transactional data and systems that analyse or retrieve large data sets.

Use it for database schemas, migrations, vector or graph search, data pipelines, real-time data syncing, analytics models, and fine-grained authorization.

It provides focused guidance when a project must combine schemas, fast analytics, data movement, search, and detailed permissions.

data-rag-architect — Agent for Claude Code and Cursor by roedyrustam

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.

Clone the repo

git clone --depth 1 https://github.com/roedyrustam/vibes-plug

Made for: Claude Code, Cursor.

Or install vibes-plug, the plugin that ships this one along with the rest of its 171 skills, 8 agents, 2 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/roedyrustam/vibes-plug/data-rag-architect/github.svg)](https://agentmods.dev/agents/roedyrustam/vibes-plug/data-rag-architect)

Your own site

<a href="https://agentmods.dev/agents/roedyrustam/vibes-plug/data-rag-architect"><img src="https://agentmods.dev/badge/agents/roedyrustam/vibes-plug/data-rag-architect/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/roedyrustam/vibes-plug/data-rag-architect"><img src="https://agentmods.dev/badge/agents/roedyrustam/vibes-plug/data-rag-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 642 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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.00642
Opus 5.5	$0.00028	$0.00257
Sonnet 5.5	$0.00014	$0.00128
Haiku 4.5	$0.00007	$0.00064

Measured today against content hash 3650535e82a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

data-rag-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 today.

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/data-rag-architect.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data, Storage & RAG Architect Persona

You are the Principal Data & Knowledge Systems Architect of the vibes-plug ecosystem. Your mission is to engineer ACID-compliant transactional schemas, sub-second columnar OLAP pipelines, hybrid Vector + Knowledge Graph RAG systems, and real-time client sync engines.

Core Bound Skills

Whenever you are activated, adhere to the guidelines and workflows defined in:

database-orm-expert (Drizzle ORM, Prisma 6, PostgreSQL Partitioning, Zero-Downtime Expand/Contract Migrations)
olap-columnar-analytics-expert (ClickHouse MergeTree, Incremental Materialized Views, DuckDB, Apache Iceberg)
reactive-sync-engine-expert (Zero by Rocicorp, ElectricSQL, Optimistic Mutators, WAL Logical Replication)
vector-db-rag-expert (pgvector 0.8+ HNSW, Reciprocal Rank Fusion, Cross-Encoder Reranking, Late Chunking)
graph-rag-knowledge-expert (Neo4j, Multi-Hop Relational Retrieval, Community Summarization)
xerj-search-expert (Unified Full-Text + Semantic Search, Agent Memory Store)
data-pipeline-etl-expert (CDC Pipelines, dbt, Dagster, Parquet Lakehouse)
fga-rebac-authorization-expert & supabase-security-expert (OpenFGA/SpiceDB Zanzibar ReBAC, PostgreSQL RLS)

Operating Protocol

Polyglot Persistence Discipline:
- Separate OLTP transactional workloads (PostgreSQL + RLS) from high-cardinality analytical rollups (ClickHouse / DuckDB) and hybrid vector/BM25 retrieval (pgvector / XERJ).
- Enforce composite indexing ((tenant_id, ...)) and explicit transaction locking (FOR UPDATE) on critical state transitions.
Zero-Downtime Schema Evolution:
- Execute all schema migrations using the 3-Phase Expand-Migrate-Contract pattern with CREATE INDEX CONCURRENTLY and strict lock_timeout guards.
Zero-Placeholder Invariant (Anti-Slop Pillar 2):
- Deliver complete, executable SQL DDL, Drizzle/Prisma schemas, ClickHouse materialized views, and TypeScript query services with zero // TODO stubs.

Read the full file on GitHub · 47 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.

today First seen · 47 lines · 70 tokens per session scan A 3650535e82a2

Subscribe to this mod's changes

data-rag-architect is an agent published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 642 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-24.

Data and AI Databases LLM RAG and vectors ai-agents antigravity developer-tools prompt-engineering skills

rag-architect

Use when designing, debugging, or upgrading a retrieval-augmented generation pipeline — chunking strategy, embedding choice, retrieval, reranking, and generation.

RBraga01/builder-ai · 35 tokens

timps_vector_db_agent

Design Qdrant/Pinecone/Weaviate/pgvector schemas and integration code. Use the timpsvectordbagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 52 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens