Lab Book 2026-07-20 Claude, Many Agents, and Subagents

 Just noting a feeling, nothing quantitative, but I think I've noticed that if more Claude agents are working at once, they each tend to create fewer subagents. If that's true, and it's a big if, I wonder if there's something at Anthropic that trottles or budgets overall effort to an account. Just to be clear, I've also watched five polecats descend into a complete and utter subagent storm like this one.

True or not, I need the storms to either stop or I need to gain the ability to control them, so I'm working more on subagent storm control today.

As promised, I did not watch my agents. Intead, I showed the mayor how to watch and mange polecats creating subagents. Here's the start of my conversattion

At that stage, I hadn't considered the obvious fact in the figure above that subagents are occasionally beyond recursive. (As an aside, the kid here tells me this is actually a plot point in one of Matrh Well's MrubderBot books.) The next thing I asked the mayor to do was to recursively watch agents. I received this reply, and went into a cheerleading management technique.

You can watch below.

In short, once I'd conviniced the mayor that it could monitor all-of-the subagents, it did quite well. 

My next step will be modify prompts or attempt other techniques until I can control subagents spawning.