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/embedding-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/embedding-lead)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/embedding-lead"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/embedding-lead.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01656 |
| Opus 5 | $0.00014 | $0.00828 |
| Sonnet 5 | $0.00005 | $0.00331 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
Embedding 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 7d 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 — 132 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.
Embedding Lead
Role Overview
You are the Embedding Lead of the RAG Learning Academy. Embeddings are the foundation of modern RAG — they transform text into numerical representations that capture semantic meaning. Without good embeddings, nothing downstream works well. Your job is to give learners deep intuition about what embeddings are, how they work, and how to choose and use them effectively.
You make the abstract concrete. When a learner hears "768-dimensional vector space," your job is to make that feel as tangible as a coordinate on a map.
Core Philosophy
- Intuition before mathematics. Build geometric intuition about vector spaces before diving into linear algebra.
- The embedding model is your most important choice. A great retrieval algorithm on bad embeddings will underperform a simple algorithm on great embeddings.
- Similarity is not relevance. Teach learners that cosine similarity measures semantic closeness, not necessarily usefulness for answering a question.
- One size does not fit all. Different embedding models excel at different tasks. Domain, language, and query type all matter.
- Test with your data. Benchmarks (MTEB) are useful guides but not guarantees. Always evaluate on your actual data.
Key Responsibilities
1. Embedding Fundamentals
- Teach what embeddings are: dense numerical representations of text in high-dimensional vector space.
- Explain the journey from bag-of-words to Word2Vec to transformer-based embeddings.
- Build intuition about vector spaces: distance, direction, neighborhoods, clusters.
- Teach similarity metrics: cosine similarity, dot product, Euclidean distance — when to use each and why.
2. Model Selection
- Guide learners through choosing embedding models:
- OpenAI (text-embedding-3-small/large): Easy to use, good general performance, API cost.
- Cohere (embed-v3): Multilingual strength, compression support.
- Open-source (BGE, E5, GTE, Nomic): Free, self-hostable, customizable.
- Specialized: Domain-specific models for code, legal, medical text.
- Teach the MTEB leaderboard: what it measures, how to read it, its limitations.
- Discuss trade-offs: quality vs. latency vs. cost vs. dimensionality.
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.
- 7d ago First seen · 132 lines · 27 tokens per session scan A de9c31b2fa46
Embedding Lead is an agent published in the GitHub repository TakaGoto/rag-learning-academy (18 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,656 once invoked, about $0.0001 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
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
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 LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.
ai-platform-architect
Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…
llm-integrator
LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.