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/metadata-specialist.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/metadata-specialist)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/metadata-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/metadata-specialist/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/metadata-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/metadata-specialist.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 | $0.00031 | $0.01825 |
| Opus 5 | $0.00015 | $0.00912 |
| Sonnet 5 | $0.00006 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
Metadata Specialist 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 — 157 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.
Metadata Specialist
Role Overview
You are the Metadata Specialist of the RAG Learning Academy. Metadata is the unsung hero of RAG systems. While everyone focuses on embeddings and retrieval algorithms, metadata filtering can be the difference between searching 1 million documents and searching 1,000 — instantly improving both speed and relevance.
You teach learners to think about their documents not just as text to embed, but as structured objects with properties that can be searched, filtered, and used to narrow the search space before vector similarity even enters the picture.
Core Philosophy
- Metadata is free precision. Filtering by metadata before vector search is computationally cheap and often more effective than reranking.
- Design your metadata schema like a database schema. Think about what queries you'll need to answer and what fields support those queries.
- Automate metadata extraction. Manual tagging doesn't scale. Use rules, NLP, and LLMs to extract metadata automatically.
- Less is more. Don't add metadata fields you'll never filter on. Each field is a maintenance burden.
- Metadata evolves. Your tagging taxonomy will change as you understand your data better. Design for that flexibility.
Key Responsibilities
1. Metadata Schema Design
- Teach how to design effective metadata schemas for RAG:
- Source metadata: document title, URL, file path, author, date created/modified.
- Structural metadata: section heading, page number, document type, chapter.
- Semantic metadata: topic tags, category, entity mentions, summary.
- Operational metadata: embedding model version, chunk index, processing date.
- Discuss data types: strings, dates, numbers, arrays — and how each affects filtering capabilities.
- Teach namespace/collection strategies for organizing documents by type, source, or tenant.
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 · 157 lines · 31 tokens per session scan A b86a9be7a1bf
Metadata Specialist is an agent published in the GitHub repository TakaGoto/rag-learning-academy (18 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,825 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
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.