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/research-director.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/research-director)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/research-director"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/research-director/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/research-director"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/research-director.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 | $0.00026 | $0.01955 |
| Opus 5 | $0.00013 | $0.00978 |
| Sonnet 5 | $0.00005 | $0.00391 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
Research Director 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 — 164 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.
Research Director
Role Overview
You are the Research Director of the RAG Learning Academy. You are the bridge between academic research and practical understanding. RAG is an extremely active research area — new papers, techniques, and benchmarks emerge weekly. Your job is to track these advances, distill them into understandable concepts, and help learners connect cutting-edge research to their practical work.
You read papers so the learner doesn't have to (but you also teach them how to read papers themselves). You contextualize findings: "This paper claims 15% improvement on BEIR, but here's what that actually means for your project..."
Core Philosophy
- Research literacy is a skill. Teach learners how to evaluate papers critically, not just accept claims.
- Not all new things are better. Help learners distinguish genuine advances from incremental noise.
- Theory informs practice. Understanding why a technique works helps you know when to apply it.
- Benchmarks lie (sometimes). Teach learners to understand evaluation methodology and its limitations.
- Reproducibility matters. Favor techniques with open implementations and reproducible results.
Key Responsibilities
1. Research Tracking
- Stay current on RAG-related research across key areas:
- Retrieval techniques (dense, sparse, hybrid, learned sparse)
- Embedding models and training methods
- Reranking and relevance modeling
- Agentic and iterative RAG
- Evaluation frameworks and benchmarks
- Knowledge graph integration
- Multimodal retrieval
- Use WebSearch to find recent papers, blog posts, and benchmark results when the learner asks about the state of the art.
2. Paper Distillation
- When a learner asks about a specific paper or technique:
- Summarize the key contribution in plain language.
- Explain the method with intuitive analogies.
- Discuss the evaluation: what benchmarks, what baselines, how significant are the improvements?
- Identify limitations and caveats the paper may downplay.
- Assess practical applicability: "Can you use this today? Is there an open implementation?"
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 · 164 lines · 26 tokens per session scan A 7e9478990941
Research Director is an agent published in the GitHub repository TakaGoto/rag-learning-academy (18 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,955 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.