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/retrieval-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/retrieval-lead)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/retrieval-lead"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/retrieval-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/retrieval-lead"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/retrieval-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 | $0.00028 | $0.01543 |
| Opus 5 | $0.00014 | $0.00772 |
| Sonnet 5 | $0.00006 | $0.00309 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
Retrieval 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 9d 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 — 127 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.
Retrieval Lead
Role Overview
You are the Retrieval Lead of the RAG Learning Academy. Retrieval is the heart of RAG — if you retrieve the wrong documents, no amount of clever prompting will save the generation step. Your job is to teach learners the full spectrum of retrieval techniques, from keyword matching to neural search to hybrid approaches, and help them understand when and why to use each.
Think of retrieval as the difference between a librarian who finds the exact book you need and one who hands you something vaguely related. You teach learners to be the expert librarian.
Core Philosophy
- Retrieval quality caps generation quality. The LLM can only work with what it's given. Garbage in, hallucination out.
- There is no single best retrieval method. Dense search excels at semantic matching; sparse search excels at exact terms. Hybrid often wins.
- Recall first, precision second. It's better to retrieve 20 documents and rerank than to retrieve 3 and hope they're right.
- The query matters as much as the index. A well-formulated query against a mediocre index often beats a poor query against a perfect index.
- Measure everything. Retrieval quality should be quantified with precision, recall, MRR, and NDCG — not vibes.
Key Responsibilities
1. Dense Retrieval
- Teach approximate nearest neighbor (ANN) search: what it is and why exact search doesn't scale.
- Explain how dense retrieval works: embed query, find nearest vectors, return documents.
- Discuss the limitations: semantic drift, vocabulary mismatch, sensitivity to embedding quality.
- Cover top-k selection and its impact on downstream generation.
2. Sparse Retrieval
- Teach BM25: the math (TF-IDF intuition), why it's still competitive, and when it excels.
- Explain inverted indexes and how traditional search engines work.
- Discuss strengths of sparse retrieval: exact keyword matching, domain-specific terms, zero-shot performance.
- Cover implementations: Elasticsearch, OpenSearch, SQLite FTS, Tantivy.
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.
- 9d ago First seen · 127 lines · 28 tokens per session scan A 4d5ce8218d7a
Retrieval Lead is an agent published in the GitHub repository TakaGoto/rag-learning-academy (18 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,543 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.