I can't offer a definitive list. But some/all of web access, web search, sub-agents, plan, goals, looping, and maybe a to-do list.

I'd suggest the default should be anything that makes the model more efficient or effective to a reasonable current level.

I disagree on plan and todo-list, which seem relatively not needed to me. No comment on goals/looping, which I don't have much experience with.

To me it's great how minimal the system prompt and tool set is, and I doubt those features are worth the tokens for every model. (Who knows if they improve performance for SOTA models, and they probably harm performance for small local models.)

I would add "better sandbox" support, which I think should be included out of the box. Not having a very simple way to get out of "yolo" mode is kinda crazy. Sure, there are plugins, but they do have some issues.

pi-bash-approval is good, but manual approval plus allowlist is a "bad" way to run coding agents.

The "best" way in my current opinion, is where commands run by default in a sandbox, but commands can be ran unsandboxed as needed, requiring approval or allow-list in that case. Cursor was pretty good at this (when I used it). For example I don't want to configure my sandbox with access to docker, which would present easy jailbreaks, but I do want to allowlist certain docker commands or approve them to run on my host as needed. pi-sandbox is good at allowing me to configure sandbox access, but this feature where somethings can run unsandboxed is missing. I write more about this and about (hacky, but productive enough) workaround here: https://github.com/carderne/pi-sandbox/issues/50

the thing is about some of these things, like sub-agents, is that any implementation of sub-agents is going to be extremely opinionated, so it would never make sense to be in pi out of the box.

Are you sure those tools make the model more efficient?

No.

But:

web access, web search --> basically essential at this point

plan, goals, looping --> necessary if this is how you work, and working like this is probably (arguably?) more efficient

to-do list --> IME seems to help efficiency with local agents if they utilise it, but this is totally subjective

sub-agents --> who knows