Hacker News

Also:

suspenders, for resilience

unixbeard, for documentation

roundglasses, for observation

dnd, for chaos testing

This is one of the biggest benefits. I'm not a plugin user so I don't remember how they're different from skills. Not speaking about the tool in OP specifically but regarding skills in general: you can have essentially the entire task or some of its subtasks (which you'd ordinarily direct to the agent using the skill, the main benefits of which are clearer natural language directions) handled with assistive tools written in any language your environment supports. You can additionally supply the skill with its own config files, data files, etc., building essentially a small repo within particular skills and making these resources however closely tied to the skill as you prefer.

This is particularly useful when the agent would otherwise be doing a task that is programmable, or the agent is inconsistent or unable to do it in an efficient, performant or other preferred manner. The programmatic tool assistance means at least some parts of the task (possibly its entirety) could be handled in a well-tested and deterministic manner. How reliable the determinism, optimality, etc. are depends on how well you or the agent writes and verifies the code, tests, spec, etc. in the first place of course, but that only needs to be done correctly once.

The other great benefit is reduced token use, potentially a massive reduction. Imagine a task Claude takes 10 minutes to prepare to do because it's reading and analyzing files for the 3rd time in the last 4 minutes, then it's asking for permissions several times in between to do this and that even after you put it in auto mode, then it's "thinking" again for the thousandth time about how to approach the task even though you had it repeat the task a hundred times already...by the time it actually starts doing the task, the most recent models are likely to have churned through tens of thousands of tokens (and that's a conservative estimate for frontier models) in the first 10 minutes. But, with tool assistance, you can have Claude directly handle some parts of that same task which, for example, needs unpredictable analysis or decision-making each time, but also have it use a set of highly optimized programs to handle the bottleneck parts or the parts you want done "your way." You could potentially cut down those 10 minutes of prep time + whatever minutes to actually do the task down to seconds, with barely a couple of thousand tokens used up! Just an example of course, but I've benefited from this strategy repeatedly across various tasks, simple ones and very complex ones.

Another great thing is that the tools don't have to be tied to the skill at all, they can live anywhere in your codebase. You could even manually run the scripts like any other to handle certain tasks in their entirety or do the prep work before setting an agent loose on the remainder. There are many different approaches with different advantages. It's like actually using the agent as your...well, agent! But now you're supplying him with the latest gadgets like M/Q does for 007.

Oh so more an orchestration interface with sane defaults for an LLM to use as a reference when implementing deployment changes, especially new rollouts? It seems to be aimed at small to medium sized cloud deployments and more as a starting point to get customers up and running?

Because I'm already administratrating a large AWS environment and the networking, especially as regards route tables, transit gateways, DMZs and extensive security group rules managed in multiple distinct layers across teams (and don't even get me started on IAM and Active Directory Forest) don't seem to fit into the abstraction layer I'm seeing.

Hetzner is awesome, I prefer it to aws for personal projects, feel free to analyze my modularized instance setup with an LLM and rip out what you need, it's all hand built, most of the engineering went into cloud-init and network security - before machines could generate the same in hours lul

https://github.com/fiscalismia/fiscalismia-infrastructure/tr...

Write it in English to the best of your ability and then use it with a prompt along the lines of...

  Identify parts of the following readme that need to be looked at for consistency, tone, grammar, punctuation, and capitalization issues.
  This is to be a readme file for a project on GitHub used by technical people who are familiar with any jargon being used. 
  Suggest any changes to those by identifying the full passage the fix is in along with the correction.

I doubt it, bad grammar is better than AI-speak.