Maybe these longer system prompts are part of the reason why we can give the models shorter AGENTS.md files? A lot of what people commonly write in their *.md instructions may be already covered.
Some tasks could take a while, especially with /goal mode. At work we often have multiple agents running on different tasks, and each could spawn subagents that you may or may not want to track. With the herdr skill you can have subagents be managed via tabs or panes, which gives them more visibility and could also explode your terminal :)
> On the flipside, this "fingerprint" approach is also what makes Shazam work poorly if you just sing into it. You're likely to generate different hashes than the original song, even if you are a very good singer! This is why newer, machine-learning-based systems are built to handle humming and singing, by matching on melody rather than exact frequencies.
So this is why singing/whistling a song to my phone never worked! I've always imagined the tech as some sort of wave pattern matching but the DFT is obviously more efficient for many scenarios. Cool article!
Been trying out [SiYuan](https://github.com/siyuan-note/siyuan) as a local alternative and love it so far. The files are single-line JSONs so not as ideal as Obsidian .md files, but it seems to be trivial to export to various human-friendly formats.
I use the two together with no issues. Micromamba works great for conda dependencies that’s not on PyPi (for many reasons), and everything else I go for uv.
