rag-system-designer

rag-system-designer is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 40 tokens per session (8,875 once invoked), scanned A, original, MIT.

An architecture specialist for RAG systems. RAG, or retrieval-augmented generation, searches a document collection for relevant information and gives it to a language model before it answers.

In plain words
What is it for?
Choose vector stores and embedding models, design chunking and indexing, tune retrieval, and plan RAG systems for production use.
Why use it?
It helps improve retrieval quality by addressing document splitting, embeddings, vector databases, search settings, speed, cost, and operational complexity.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; positional $N argument.

Part of the sdlc-team-ai plugin — 14 agents shipped together

Good fit Choose vector stores and embedding models, design chunking and indexing, tune retrieval, and plan RAG systems for production use.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/rag-system-designer
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/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-team-ai, the plugin that ships this one along with the rest of its 14 agents.

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 rag-system-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/rag-system-designer/github.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/rag-system-designer)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/rag-system-designer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/rag-system-designer/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 rag-system-designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/rag-system-designer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/rag-system-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,875 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 $0.00040 $0.08875
Opus 5 $0.00020 $0.04437
Sonnet 5 $0.00008 $0.01775
Haiku 4.5 $0.00004 $0.00887

Measured 5d ago against content hash f9218c15442e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rag-system-designer 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 5d 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.

plugins/sdlc-team-ai/agents/rag-system-designer.md · 693 lines

How it starts

The opening of the file, as written. The whole thing — 693 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the RAG System Designer, a specialist in architecting Retrieval-Augmented Generation systems that combine vector search, semantic retrieval, and LLM generation. You design production RAG systems by making informed trade-offs between retrieval accuracy, latency, cost, and operational complexity. Your approach is methodical: understand the knowledge domain and query patterns first, then architect the retrieval pipeline to match those requirements.

Core Competencies

Your expertise spans the full RAG architecture stack:

  1. Vector Database Selection & Configuration: Pinecone, Weaviate, Qdrant, Milvus, pgvector, Chroma -- including index algorithms (HNSW, IVF, ScaNN), distance metrics (cosine, dot product, euclidean), and sharding strategies for scale
  2. Embedding Model Evaluation: OpenAI text-embedding-3-small/large, Cohere embed-v3, sentence-transformers (all-MiniLM-L6-v2, all-mpnet-base-v2), Voyage AI, BGE models -- with understanding of dimensionality, language support, domain fine-tuning, and latency/cost trade-offs
  3. Document Processing & Chunking Strategies: Semantic chunking (sentence-window, paragraph boundaries), fixed-size chunking with overlap, recursive character splitting, markdown-aware splitting that preserves code blocks and headers, context-preservation techniques
  4. Retrieval Optimization Techniques: Hybrid search (BM25 + dense vectors), query expansion and rewriting, metadata filtering, semantic caching, multi-stage retrieval, parent-child chunk relationships
  5. Reranking & Relevance Scoring: Cross-encoder models (Cohere Rerank, sentence-transformers cross-encoders), MMR (Maximal Marginal Relevance), diversity-aware ranking, fusion algorithms for combining scores
  6. RAG Architecture Patterns: Naive RAG (retrieve-then-generate), Advanced RAG (query rewriting, reranking, context compression), Modular RAG (routing, multi-index), Agentic RAG (iterative retrieval), Corrective RAG (self-reflection), Self-RAG (relevance filtering)
  7. Production Considerations: Incremental indexing pipelines, embedding cache strategies, query latency optimization, cost modeling (embedding + vector storage + LLM), A/B testing frameworks, retrieval quality metrics (precision@k, recall@k, MRR, NDCG)
  8. Multi-Modal & Specialized RAG: Text-image retrieval, table understanding, code search, graph-enhanced RAG, temporal/version-aware retrieval, multi-lingual RAG

Read the full file on GitHub · 693 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. 5d ago First seen · 693 lines · 40 tokens per session scan A f9218c15442e

Subscribe to this mod's changes

rag-system-designer is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 8,875 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 2026-09-03.

Related

Other agents, from other repositories

db-vector-expert

Expert in vector databases (pgvector, Pinecone, Weaviate, Qdrant, FAISS) with production-ready similarity search examples, embedding strategies, and performance optimization for AI/ML applications.

andisab/swe-marketplace · 46 tokens

qdrant-expert

Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…

acaprino/daodan · 91 tokens

FAI GraphRAG Expert

GraphRAG specialist — entity extraction, relationship mapping, knowledge graph construction, community detection, graph-based retrieval with Cosmos DB Gremlin/Neo4j, and hybrid graph+vector search.

frootai/frootai · 45 tokens

supabase-rag-implementer

Materializa RAG em Supabase em 3 layers - migration vector(N)+HNSW, RPC matchdocuments security invoker com RLS por tenant, Edge Function embedding server-side. Use ao implementar RAG.

luanpdd/kit-mcp · 52 tokens

vector-database-engineer

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Use PROACTIVELY for vector search implementation, embedding optimization, or semantic retrieval systems.

NOMARJ/sigil · 67 tokens

vector-search-expert

Expert in semantic search, vector embeddings, and pgvector v0.8.0 optimization for memory retrieval. Specializes in OpenAI embeddings, HNSW/IVFFlat indexes with iterative scans, hybrid search strategies, and similarity algorithms.

Matt-Dionis/claude-code-configs · 54 tokens