HN
login
Agents.md speaks Unix, and you should toofmind.dev

Unix gives coding agents the tools. AGENTS.md explains where to edit, how to check, and what to preserve. Lessons from my dotfiles and human review.

16 points•fmind-dev•6 days ago•9 comments•
#agents#unix#speaks#speaks unix#explains#edit#tools#coding

9 comments

applfanboysbgon6 days ago
Not convinced this is an authentic human story rather than LLM-generated marketing blogspam, but if it is real, it's rather sad. All this mention of discovering CLI tools, tools, tools, configuration, configuration, configuration, AI, AI, AI. Not one mention of programming. You know you can program your computer to do what you want it to do? You don't have to scour "Github Trending like a madman, looking for the next thing that would make [you] more productive". You can just write the code that will make you more productive.
fmind-dev6 days ago
I'm a geek, a perfectionist, and I like to have the best tools when I work. If you take my previous dotfiles (100% human made): https://github.com/fmind/dotfiles-ansible, it had more than 1293 commits from all the tools and configs I tested. But this was draining my energy. I'm glad we now have LLM to automatically find the best tools/configs for you, and test if the settings are working.

My new dotfiles are much more powerful and efficient than ever before thanks to LLMs. For instance, I did not know about Zellij, mise, dprint, lazyvim or git-cliff before updating them. Having them is your toolbet helps me and my agents build better tools.

axeldunkel6 days ago
Lets assume this real - for humans these condensed tools make sense. For an agent I'd argue it takes him more tokens to understand these condensed infos since he most probably knows the right tools anyways and does not need the shortcuts.
fmind-dev6 days ago
Indeed, you need to invest some tokens in configuring the tools, configs and skills. But once it's done, tools and configs do not consume more tokens, as they are automatically used by your AI Agents. Moreover, skills support progressive disclosure, and I try to keep a budget of max 5000 tokens for global + 5000 tokens for local setups (= Skills + AGENTS.md).

But yes, I burned too many tokens on this project. That's why I'll be happy if it can help others.

OJFord6 days ago
This is a lot of words to say 'let your AI tools configure their own environment'.
fmind-dev6 days ago
The article is more about justifing the investment. Dotfiles is the foundation for all your other AI projects. If you have good dotfiles, you can automatically steer all your other projects in the right direction.
dingdongditchme6 days ago
lul what? As a linux fanboy who "speaks unix" (presumably, do I? not sure...). I find it humorous that we have gone full circle. The newest tech shit is recommending I learn almost 50 year old technology? Time for me to log off.
fmind-dev6 days ago
I know several teams and big org struggling to leverage AI agents. One of the easiest path is to use UNIX (e.g., your laptop + a shell). All the tools are available, shared between humans and agents, and compose infinitively.

The point is exactly what you say: Not to have the latest tech product (e.g., grok bot, instinct, ...), but to just use powerful tools whose flexibility have been battle tested other the ages.

Arnt6 days ago
It's even worse, you can learn 2000+ years old math on Youtube.

Read the full thread on Hacker News →

Related stories