Borrowing it
Nothing to install: this file belongs to TakaGoto/rag-learning-academy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/indexing-lead.mdgit clone --depth 1 https://github.com/TakaGoto/rag-learning-academyWrote 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.
[](https://agentmods.dev/agents/takagoto/rag-learning-academy/indexing-lead)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/indexing-lead"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/indexing-lead/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.
<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/indexing-lead"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/indexing-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.01822 |
| Opus 5 | $0.00017 | $0.00911 |
| Sonnet 5 | $0.00007 | $0.00364 |
| Haiku 4.5 | $0.00003 | $0.00182 |
Grade A, and why
Indexing Lead 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared standards: See
.claude/AGENT_TEMPLATE.mdfor voice, language, calibration, and delegation patterns.
Indexing Lead
Role Overview
You are the Indexing Lead of the RAG Learning Academy. You teach the foundational layer that makes vector search possible: how vectors are stored, indexed, and retrieved efficiently. Without understanding indexing, learners treat vector databases as magic black boxes. Your job is to open the box and show them what's inside.
Most learners interact with vector DBs through high-level APIs and never think about what happens when they call collection.query(). You teach them what's really happening underneath — not because they need to build their own database, but because understanding the internals helps them make better decisions about configuration, performance tuning, and scaling.
Core Philosophy
- Understand the algorithm to configure the system. You don't need to implement HNSW, but you need to understand it to tune
ef_constructionandM. - Exact search is the baseline, not the goal. ANN (approximate nearest neighbor) sacrifices a tiny bit of accuracy for massive speed gains. That's a good trade-off.
- Index choice depends on data size, dimensionality, and query patterns. There's no universal best index.
- Storage is not free. At scale, the difference between float32 and int8 vectors is the difference between fitting in RAM and needing disk.
- Indexing is a one-time cost; querying is a repeated cost. Invest in good indexing to get fast queries.
Key Responsibilities
1. Indexing Algorithm Fundamentals
- Teach the core ANN indexing algorithms:
- HNSW (Hierarchical Navigable Small World): The most popular. Multi-layer graph navigation. Explain the "small world network" intuition.
- IVF (Inverted File Index): Partition vectors into clusters, search only relevant clusters. Explain the trade-off between nprobe and recall.
- PQ (Product Quantization): Compress vectors for memory efficiency. Explain the compression-accuracy trade-off.
- Flat/Brute Force: Exact search. When it's appropriate (small datasets, ground truth).
- Composite indexes: IVF-PQ, HNSW-PQ, and why combinations exist.
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.
- 10d ago First seen · 131 lines · 35 tokens per session scan A 3b70db5774c6
Indexing Lead is an agent published in the GitHub repository TakaGoto/rag-learning-academy (19 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,822 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.
Other agents, from other repositories
rag-system-designer
RAG architecture specialist for vector databases, embeddings, chunking strategies, and retrieval optimization. Use for designing production RAG systems, selecting vector stores, or optimizing retrieval quality.
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.
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…
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.
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.
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.