Greg Isenberg

Don't use it.

I just put it so I can get some GitHub stars.

I have this one skill, and it's literally a code structure skill.

And I'll put the mark down so people can see it.

It's 116 lines.

It's basically after AI has generated a bunch of code.

I like it structured in a certain way, so it's easy for me to review it.

And like I mentioned earlier with skills, the only thing that gets added into context is the name and description.

So when I look at the name, it's code structure.

When I look at the description, use when multiple workflows duplicate the same operational logic when deciding that blah, blah, blah, blah, blah, some nerd stuff.

So when I tell the agent, I want to...

clean up the code structure, it checks the skills it has, it sees the name, it reads the description.

It's like, oh, this makes sense.

Then it progressively discloses, meaning once it realizes it needs this skill, then it adds the rest of this, right?

Versus if this was my agent.md file, imagine every single time, and we can actually check how many tokens this is.

Let me check.

What was it?

OpenAI token, tokenizer.

if i go to this so this is 944 tokens so if this was an agent.md file every single time i have a chat i'm adding 944 tokens tokens ain't cheap now no but if i just have the name and the descriptions just 53 and it's not even cheap it's just like you're not trying to hit the limit quicker than you need to hit the limit

Cause the model will get dumb as the context window closes.