How do people handle large reference documents and resources in Jake’s folder system?

I understand how the CLAUDE.md works for context and routing, and that part is becoming much clearer as I build more of these systems.

The bit I’m still struggling with is what to do with large reference material — things like guidance documents, API documentation, product specifications, research papers, manuals, or even an entire book — where you want Claude to be able to find the relevant information when needed without having to load huge amounts of material into context.

To give a practical example, I’m currently building an ICM system for medical educators who supervise paediatric trainees.

The idea is that a supervisor could use it to help with things such as:

preparing for supervision meetings;
answering questions about training requirements and guidance;
keeping track of meetings, deadlines and important dates;
completing the required supervision and progression forms;
maintaining appropriate information about individual trainees;
and helping with forms or reports relating to other trainees they are asked to assess.

It’s still very much a work in progress, but I think the basic architecture is coming together nicely. I’ll share the CLAUDE.md as well so people can see what I’m trying to build.

The recurring problem I’ve found — not just with this project, but with most of the folders I’m building — is how to deal with the reference library behind the system.

For example, this medical education system may eventually need access to fairly substantial training guidance, curricula, policies, forms and supporting documentation. I obviously don’t want all of that sitting in CLAUDE.md, nor do I want Claude reading hundreds of pages every time somebody asks a relatively simple question.

What I’d really like is something closer to:

Question → router → identify the relevant reference source → retrieve only the relevant section → answer using that material.

In other words, keeping the ICM folder as the structure and source of context, while having a larger reference library that is searched only when required.

How are people handling this?

Do you simply keep large documents in a /references folder and give Claude instructions about when and how to search them? Do you break large documents into smaller Markdown files with some sort of index or map? Have people built a separate retrieval layer? Or are you using something like a vector database/RAG system alongside the ICM?

I’ve seen

@David Vogel

using Cognee, which I’m actually experimenting with separately for my own second-brain/memory system. But I’m not sure whether something like that is the right answer for authoritative reference material. For example, if I had the equivalent of an online textbook sitting behind an ICM project, I’d want Claude to retrieve the relevant passage when needed while still knowing exactly which document and section the answer came from.

That distinction between memory and reference material feels quite important.

Has anyone found a pattern that works well for this without either bloating the context window or making the folder architecture unnecessarily complicated?

Apologies if this has already been covered somewhere. I asked Dexter but couldn’t really find an answer that addressed this particular problem.

Very interested to see how others have approached it.

P.S. The system is still a work in progress — like the other ten folders I seem to be building at the same time! 😅

35 comments

How do people handle large reference documents and resources in Jake’s folder system?