What AGENTS.md and skills are people relying on these days?
I have little to none and am successful building full stack Go apps Claude Code, Codex, and Shelley which covers the spectrum of crazy black box to simple `bash` clanker.
It makes me think the models are continually improving in knowing what to do on their own.
I do put some major work into the classic "Developer Experience" (DX) of my code base. Standard Go tooling, idiomatic Go, well designed initial test harnesses, GitHub actions that enforce some linting.
I think that works better than any markdown instructions ever will.
I like peeping at other people's skills but it is unclear to me what/where the claimed 60+ skills are actually located. Compound Engineering conveys a few but nowhere near 60.
From my limited time using pure Pi, I found quite a few of the plugins lacking and had no desire to upgrade/fix and maintain them myself. I know others feel differently though.
I like the idea of keep Pi minimal but having āofficialā, high quality optional plugins to make it more usable.
Pi makes you think about what youāre doing with it on purpose. This defeats that, as the Mario quote on the page says, and therefore isnāt worth using.
People really need to try out āless is moreā. The new models are quite smart, so suffocating their context with dozens of MCPs and skills isnāt necessary like it used to be. A cli tool with good built in help and good errors is amazingly easy for the model to figure out.
If Pi is too minimal for you and you donāt want to dig into it, OpenCode is pretty good out of the box. I use it for general work I havenāt setup Pi for. The only thing I add to OpenCode is some commands that are shortcuts to save me typing frequent prompts, and a subagent with a fixed model for implementing changes.
I like the Pi approach, but I think I didn't "hold it correctly" so to say.
I would like to migrate away from Claude Code and use Pi as my "peimary" harness. I really like in particular how it manages conversation trees and branches.
But I think I didn't do a good job in customizing it for my work. While nothing dramatic, I think the LLM I was using did a better job on Claude Code than on Pi a couple of time when I tried giving it the same work.
I use lazyvim for all my neovim config. Does it fly in the face of the configurability or minimalism of vim? I'd argue no, but rather it is an expected outcome of a highly configurable system. Some people don't want to think about this kind of thing, they just want something that works.
I've been using oh-my-pi for a while and I'm very happy with it. If you're not going to build out your own Pi setup I'm not sure why you'd pick this over oh-my-pi.
On the one hand, sure, why not have a default install throw a bunch of bells+whistles via skills and extensions.
But I like pi precisely because it is so minimal. I want understand and work around the simplest possible agentic coding setup, find the sharp edges, maybe even improve my prompting ability. And doing all three with a locally hosted LLM.
At some point, if I don't understand the foundations, am I just punting on actually thinking about what I'm doing?
Of course, making individual choices about how to do agentic coding are precisely just making individual choices. People should do what makes them happy and productive.
I think the developers of Pi made a supply chain mistake by stripping down the core agent and requiring features like subagents to load plugins written by some random person.
Pi is meant for people who know what they are doing. If you dont fall into that category use OpenCode, etc. The whole idea is that you customize Pi to your own needs by asking it to modify itself through extensions.
That said, sometimes it is really easy to leverage existing extensions. You run the risk of supply chain attack though. I installed one extension that was useful, modified it to my needs and pinned it.
ironically (?) i prefer to improve Pi by connecting MCP servers instead of native extensions in part due to this (process-level sandboxing is trivial; anything more granular -- as would be required for in-process plugins -- is far more intimidating).
We are going to address this. Not by loading the agent but by finding a way to provide official plugins or blessed plugins. But weāre not yet sure what the right approach is.
If you're going to have "blessed" plugins, which seems like a good idea, you'll need a review and possibly hosting process.
- Review to check that the plugin is reasonable quality/isn't malicious.
- hosting (e.g. the plugin is retrieved from a repo. you control) or "known good" checksums so pi will only download the plugin with a version that you've reviewed.
From a security/supply chain aspect, ironically what you're looking to do is deliberately add some friction to the publishing process, which sounds bad, but can be quite effective at mitigating attacks. Most of the recent supply chain attacks get found by automated scanners in < 24 hours, so having a review process for new releases that takes a while will reduce the number that affect users.
I think having this is handy as it'll give security conscious users more confidence in using pi, without the anxiety of pulling a load of additional code from effectively random sources.
Curated. Not exhaustive.
Every package is hand-picked.
Somehow Iām not convinced.
Anyway, if this works for someone, great. Iām a novice Pi user which I think would be the target audience, I donāt see why I would use this, both because it appears to be LLM slop and because it bedazzles up a tool that I started using in the first place because of its minimalism, but to each his own.
What AGENTS.md and skills are people relying on these days?
I have little to none and am successful building full stack Go apps Claude Code, Codex, and Shelley which covers the spectrum of crazy black box to simple `bash` clanker.
It makes me think the models are continually improving in knowing what to do on their own.
I do put some major work into the classic "Developer Experience" (DX) of my code base. Standard Go tooling, idiomatic Go, well designed initial test harnesses, GitHub actions that enforce some linting.
I think that works better than any markdown instructions ever will.
This seems to be like the antithesis of pi, it's supposed to be this minimal thing you customise
I guess it's the same kinda friction with vanilla vim/neovim vs vim 'distributions' that provide a bunch of stuff out of the box.
[delayed]
I like peeping at other people's skills but it is unclear to me what/where the claimed 60+ skills are actually located. Compound Engineering conveys a few but nowhere near 60.
Currently using Oh My Pi (https://github.com/can1357/oh-my-pi) and appreciate the batteries included approach.
From my limited time using pure Pi, I found quite a few of the plugins lacking and had no desire to upgrade/fix and maintain them myself. I know others feel differently though.
I like the idea of keep Pi minimal but having āofficialā, high quality optional plugins to make it more usable.
Pi makes you think about what youāre doing with it on purpose. This defeats that, as the Mario quote on the page says, and therefore isnāt worth using.
People really need to try out āless is moreā. The new models are quite smart, so suffocating their context with dozens of MCPs and skills isnāt necessary like it used to be. A cli tool with good built in help and good errors is amazingly easy for the model to figure out.
If Pi is too minimal for you and you donāt want to dig into it, OpenCode is pretty good out of the box. I use it for general work I havenāt setup Pi for. The only thing I add to OpenCode is some commands that are shortcuts to save me typing frequent prompts, and a subagent with a fixed model for implementing changes.
Would you say the same about something like, say, Spacemacs?
I like the Pi approach, but I think I didn't "hold it correctly" so to say.
I would like to migrate away from Claude Code and use Pi as my "peimary" harness. I really like in particular how it manages conversation trees and branches.
But I think I didn't do a good job in customizing it for my work. While nothing dramatic, I think the LLM I was using did a better job on Claude Code than on Pi a couple of time when I tried giving it the same work.
I was not sure how to improve on it though.
This thing defeats the whole purpose of Pi.
I use lazyvim for all my neovim config. Does it fly in the face of the configurability or minimalism of vim? I'd argue no, but rather it is an expected outcome of a highly configurable system. Some people don't want to think about this kind of thing, they just want something that works.
Yes, because neovim != vim :)
I've been using oh-my-pi for a while and I'm very happy with it. If you're not going to build out your own Pi setup I'm not sure why you'd pick this over oh-my-pi.
On the one hand, sure, why not have a default install throw a bunch of bells+whistles via skills and extensions.
But I like pi precisely because it is so minimal. I want understand and work around the simplest possible agentic coding setup, find the sharp edges, maybe even improve my prompting ability. And doing all three with a locally hosted LLM.
At some point, if I don't understand the foundations, am I just punting on actually thinking about what I'm doing?
Of course, making individual choices about how to do agentic coding are precisely just making individual choices. People should do what makes them happy and productive.
I think the developers of Pi made a supply chain mistake by stripping down the core agent and requiring features like subagents to load plugins written by some random person.
Pi is meant for people who know what they are doing. If you dont fall into that category use OpenCode, etc. The whole idea is that you customize Pi to your own needs by asking it to modify itself through extensions.
That said, sometimes it is really easy to leverage existing extensions. You run the risk of supply chain attack though. I installed one extension that was useful, modified it to my needs and pinned it.
ironically (?) i prefer to improve Pi by connecting MCP servers instead of native extensions in part due to this (process-level sandboxing is trivial; anything more granular -- as would be required for in-process plugins -- is far more intimidating).
We are going to address this. Not by loading the agent but by finding a way to provide official plugins or blessed plugins. But weāre not yet sure what the right approach is.
If you're going to have "blessed" plugins, which seems like a good idea, you'll need a review and possibly hosting process.
- Review to check that the plugin is reasonable quality/isn't malicious.
- hosting (e.g. the plugin is retrieved from a repo. you control) or "known good" checksums so pi will only download the plugin with a version that you've reviewed.
From a security/supply chain aspect, ironically what you're looking to do is deliberately add some friction to the publishing process, which sounds bad, but can be quite effective at mitigating attacks. Most of the recent supply chain attacks get found by automated scanners in < 24 hours, so having a review process for new releases that takes a while will reduce the number that affect users.
I think having this is handy as it'll give security conscious users more confidence in using pi, without the anxiety of pulling a load of additional code from effectively random sources.
Anyway, if this works for someone, great. Iām a novice Pi user which I think would be the target audience, I donāt see why I would use this, both because it appears to be LLM slop and because it bedazzles up a tool that I started using in the first place because of its minimalism, but to each his own.
haha i was waiting for this exact thing lazyvim:vim::pi:lazypi, thanks for sharing
i think to fall in love with Pi, bundled skills are a bit antithetical - you realistically only need a couple of skills that you maybe design yourself
Why does this makes more sense over OpenCode?
The memory footprint of Opencode is prohibitive to run 10+ copies at once.
I personally find OpenCode's TUI atrociously awful, I guess a matter of taste.