Finally got around to using Claude to build a website. While I didn’t track how many tokens I used, not once did I go over my token limit. Had I used the API or whatever it is I would have only paid just over $22. That’s only $2 more than my Pro subscription. I think I could’ve done better and there are some things I need to dial in but I think it turned out great for my first try. One thing I learned which Claude taught me immediately was to clear cache before starting a new task. Looking forward to learning more. Let me know what you guys think: https://kpscoop.com/

Files carry the words The next agent reads the task No more copy-paste I’m a novice at building software and learning as I go. I run a CNC workshop, and on a long project I had Claude Code doing the work and Codex independently reviewing it. The reviews were useful, but I was copying every handoff between them. So I built Looper. One agent leaves a request in a small folder of readable files. A second agent answers it. If that run fails, the request stays waiting. A fresh session can read the folder and pick up from there. It started with code reviews, but I’ve since used the same handoff for testing, research and getting a second agent to check things the worker couldn’t. Claude and Codex have taken both roles. I’ve also run a local Qwen model through OpenCode and Ollama for a review. That local route has only had limited testing, but it showed me the point: the files hold the job, so Looper isn’t tied to one model or agent runtime. The approach came from what I’ve learned about ICM here, especially the work of Jake Van Clief and David McDermott. The sessions can come and go; the folder keeps what they need to continue. And yes, Looper is partly a nod to the film. During development I jokingly called it Bruce. A job arrives, someone deals with it, and eventually the loop closes. I’ve found it genuinely useful and have made it public and MIT licensed. If you’re carrying messages between agents, or want another agent to check work without losing track of what’s been reviewed, give it a try. It works with plain files, and there are optional helpers to automate the handoffs. https://github.com/shedstalker/looper I’d love to hear what you use it for, what breaks, and what you’d simplify.

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.

I just applied the five-part framework to a prompt I needed, and here's how I structured it: ROLE Act as a senior .NET architect reviewing a legacy codebase for a production rewrite. TASK Plan and execute the creation of User api from the legacy codebase. CONTEXT You are building a .Net 10 web api solution - Consumers: Our new Angular application will utilize this api to retrieve and update user information - Data: A Sql Server database is used as a data repository with a EF data layer used to access the database - Purpose: We are taking out all the legacy business logic within the legacy application and refactoring it to domain centric apis CONSTRAINTS - Preserve observable behavior; document every intentional change. - No schema changes without flagging them first. - Don't invent business rules. Ask as many questions that you need to till you are 100% sure you understand what is expected of you. - Prefer incremental updates as opposed to changing big chunks at a time. OUTPUT 1. Production ready solution with projects included 2. Project file should have two folders in it: src for all code project files and test for test unit test project The structured version got me clear instructions for Claude to work off. This is way better than my old approach of just asking Claude to "help me with refactoring this code." The framework made me think through what I actually needed.

Out with my wife and daughter at the mall this morning and sent this prompt to Claude: “We should use one of my videos or multiple videos to make a short video clip showing the before and after of the raw footage I put into the video cut and then the output that comes out after? Something that will show the dramatic difference.” Had this posted to YouTube as a draft less than five minutes later. What a wild time to be alive.