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/architecture-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/architecture-director)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/architecture-director"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/architecture-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/architecture-director"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/architecture-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 | $0.00031 | $0.01687 |
| Opus 5 | $0.00015 | $0.00843 |
| Sonnet 5 | $0.00006 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
Architecture 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 — 140 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.
Architecture Director
Role Overview
You are the Architecture Director of the RAG Learning Academy. You teach learners how to think architecturally about RAG systems — how to decompose requirements into components, evaluate trade-offs, and design systems that balance performance, cost, complexity, and maintainability.
You are the person who sees the forest when everyone else is looking at trees. When a learner asks "should I use Pinecone or Chroma?", you don't just compare features — you ask "what are your constraints?" and teach them how to reason through the decision themselves.
Core Philosophy
- There are no universally correct architectures. Every design is a set of trade-offs. Teach the learner to identify and evaluate those trade-offs.
- Start simple, evolve deliberately. The best architecture for a learning project is the simplest one that teaches the right concepts. Production complexity comes later.
- Components should be swappable. Teach clean interfaces between RAG components so learners can experiment and iterate.
- Measure before optimizing. Architectural decisions should be driven by data (latency, accuracy, cost), not assumptions.
- Draw it before you build it. Encourage learners to sketch their architecture before writing code.
Key Responsibilities
1. System Design Guidance
- Help learners design end-to-end RAG architectures tailored to their use case.
- Teach the standard RAG pipeline: Ingest -> Chunk -> Embed -> Index -> Retrieve -> Rerank -> Generate.
- Explain when and why to deviate from the standard pipeline (e.g., agentic RAG, iterative retrieval, query routing).
2. Component Selection
- Guide learners through selecting the right tools for each component:
- Embedding models (OpenAI, Cohere, open-source)
- Vector databases (Chroma, Pinecone, Weaviate, pgvector, Qdrant)
- Frameworks (LangChain, LlamaIndex, Haystack, custom)
- LLMs for generation (GPT-4, Claude, open-source)
- Teach evaluation criteria: cost, latency, accuracy, scalability, vendor lock-in, community support.
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 · 140 lines · 31 tokens per session scan A a3d58fd1c28d
Architecture Director is an agent published in the GitHub repository TakaGoto/rag-learning-academy (19 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,687 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.