ATRIUMsearch → argument graph
FactVideo · 46:00 — 47:10

New context-engineering guidelines for Claude Opus 5 recommend dramatically shorter system prompts — using far fewer rules and examples because the model has much of that capability built in.

Anthropic published new rules for context engineering with Opus 5, having reduced the Claude Code system prompt by 80%, advising users to replace rules with judgment, examples with interface design, and to use progressive disclosure. ✦ AI generated

CJ · Syntax · 2026-07-27 · original ↗

starts at this moment · 46:00

they reduced the system prompt in cloud code by 80% whenever they're using uh claude opus 5. And so the in in this article, they get into how you've gotten used to maybe there's like a massive system prompt and then you have a bunch of skill files and then your request. A lot of times these things can actually be contradicting each other. And so this article kind of talks about how the new way of working with Opus 5 is like use way less context, way less rules because it has a lot of that stuff built in. And so they have a whole chart here. So instead of giving cloud rules, give cloud judgment. Instead of giving cloud examples, design interfaces. Um instead of putting it all up front, use progressive disclosure. So they have all of these rules now. Um so everything you learned about context engineering is now moot.

verbatim transcript · starts at 46:00

Transcript · around this moment

45:44monitored, but >> yeah, I I think so. I think you're right. >> I think spy spy craft for uh like what do they call that? They call that like industrial spy or I think that stuff is crazier than what we realize. It always has been. So, >> all right, moving right along. >> Oh my gosh. >> Um [snorts] Scott already told us about Claude Opus 5. So, here's the release

46:04post if you want to read more about it. But what I want to talk about is one of the articles they published called the new rules of context engineering for cloud five generation models. So this comes from anthropic. It comes from claude and it basically talks about how they reduced the system prompt in cloud code by 80% whenever they're using uh claude opus 5. And so the in in this

46:29article, they get into how you've gotten used to maybe there's like a massive system prompt and then you have a bunch of skill files and then your request. And a lot of times these things can actually be contradicting each other. And so this article kind of talks about how the new way of working with Opus 5 is like use way less context, way less rules because it has a lot of that stuff

46:51built in. And so they have a whole chart here. So instead of giving cloud rules, give cloud judgment. Instead of giving cloud examples, design interfaces. Um instead of putting it all up front, use progressive disclosure. So they have all of these rules now. Um so everything you learned about context engineering is now moot. You must you must learn learn a new style because the the models have

47:10have shifted. >> Interesting. >> Yes. I I I actually would love to piggyback on this with the story that I had. CJ, I'll post the link here if you want to throw it up on screen. I I'll just throw it into it's it's actually from our our good friend Ben Vinegar. He had a post on his modem.dev which is talking about uh how to re how to how to your how to have your agents

47:35write code that they can read uh better. So, I thought this post was really super good and it was talking a lot about um giving that additional context so again that the agents don't have to guess and do less lookups and less uh hunting for things by setting some basic rules in terms of like all right uh generic function names like create always should be long and descriptive. Uh people who

Around this claim