How heavy on tokens is this? I don't use these style workflows and am fairly new to claude code, so I assume it's better than 3x tokens when doing 3 passes?
vadepaysa 3 hours ago [-]
I did a Show HN[0] a few days back with my CLI agent called cook[1] and for a moment I was ecstatic my tool made it to the front page. haha.
Can someone explain what this is to my n00b brain. I don't get what claude-cli is missing that this adds in?
beshrkayali 4 hours ago [-]
IMO the raw Claude CLI is great for one-off interactive sessions, but as soon as you want repeatable multi-step workflows you’re either copy-pasting prompts forever or hacking your own solution manually. That’s exactly the gap these tools fill.
My take on a solution for this is https://ossature.dev — .smd spec markdown files + ossature audit / build that gives you DAG orchestration, SHA-traced increments, and tiny focused contexts.
je42 2 hours ago [-]
Had a quick look. Stumbled upon the markdown format smd.
Was wondering if using front-matter instead of a "custom" encoding for parseble data was considered?
isodev 2 hours ago [-]
I use bash scripts. Both Claude and Vibe support all kinds of arguments if you need a prompt to “become a task”. Bash is also deterministic and easy to read and debug.
Yiin 4 minutes ago [-]
can you elaborate on "easy to read and debug", because in my experience it is anything but
isodev 3 minutes ago [-]
Compared to a random tool someone vibecoded?
eloisius 3 hours ago [-]
Isn’t a repeatable, multi-step workflow exactly what a script or Makefile does?
sghiassy 3 hours ago [-]
As a prerequisite you’d want to understand the purpose of Ralph Wiggum Loops
But in general this is meta to the CLI agent.
So if you were to use the CLI to perform a review of some code. This tool would allow you to loop the output of the code review 5 times onto itself.
exolab 2 minutes ago [-]
> So if you were to use the CLI to perform a review of some code. This tool would allow you to loop the output of the code review 5 times onto itself.
Claude already does that if you ask nicely.
transitorykris 4 hours ago [-]
Maybe not adds in, but wraps around. You could accomplish much of this with fairly simply bash scripts.
esperent 4 hours ago [-]
You could accomplish all of it with claude -p (headless mode).
transitorykris 3 hours ago [-]
Admittedly I might be missing a flag or two with claude, but how are multiple loops and comparisons of solutions done with just headless mode?
esperent 3 hours ago [-]
Via skills.
brcmthrowaway 3 hours ago [-]
Indeed.
Where are people finding time for these sort of projects.
sbinnee 3 hours ago [-]
There is a skill installation option. The skill markdown has 180 lines [1].
My take? I like it. It's concise enough for me to try it out. And I love the webpage.
Given that subagents have different thinking/effort behavior from the main agent and very limited control on that front (I’m not completely sure about this but see https://github.com/anthropics/claude-code/issues/14321 and I’ve also noticed very different behavior when the same prompt is used in the main agent or passed to a subagent), I’m not sure this skill will be the same.
Looks pretty nice. I think a lot of devs have been making similar tools, I've written my own thing that does a work review loop. I like the interface you've made. I'll probably give it a go, but I'm also reluctant to relinquish the control I have when it's my own code doing orchestration.
35 minutes ago [-]
NetOpWibby 1 hours ago [-]
Dull colors and a display font used for copy makes this website incredibly unpleasant to read.
khazhoux 3 hours ago [-]
How does this handle when Claude needs user input? To choose an option, grant tool permission, clarify questions…
facorreia 2 hours ago [-]
It seems to be in the spirit of automated vibecoding. I assume it skips all permission checks.
nurettin 2 hours ago [-]
claude> "We want to add a title section that shows what page we are currently on, use cook to manage the development process"
* coolers whirring, gpus on fire, tokens flying, investors happy, developer goes for 6th break of the day
eddie-wang 3 hours ago [-]
[dead]
perfmode 3 hours ago [-]
[dead]
shablulman 4 hours ago [-]
[dead]
fortylove 4 hours ago [-]
[dead]
NikitaCometa65 2 hours ago [-]
[dead]
panditaditya21 3 hours ago [-]
[dead]
pissedoffadmin 3 hours ago [-]
[dead]
rafaamaral 4 hours ago [-]
[flagged]
cheriot 3 hours ago [-]
If this was human written sarcasm, bravo.
Yiin 4 hours ago [-]
just use 200usd plan, I forgot what limits are.
tmatsuzaki 3 hours ago [-]
Do you hit the limit pretty quickly on the Pro plan these days?
Im thinking about subscribing for video editing, but Im still not sure.
croes 4 hours ago [-]
You'll remember it soon
weird-eye-issue 4 hours ago [-]
Do you often hit the limits recently on the $200 plan? I don't even come close
dionian 3 hours ago [-]
i used to, its much better now. opus 4.6 has been great on tokens
weird-eye-issue 3 hours ago [-]
Yes, quite a while back, they used to charge a lot more for the Opus tokens
anonzzzies 3 hours ago [-]
Have not hit limits for 2 months now and I use it a lot. I have 200 max as well.
xiaolu627 3 hours ago [-]
[flagged]
Rendered at 07:14:46 GMT+0000 (Coordinated Universal Time) with Vercel.
[0]: https://news.ycombinator.com/item?id=47262711 [1]: https://getcook.dev
My take on a solution for this is https://ossature.dev — .smd spec markdown files + ossature audit / build that gives you DAG orchestration, SHA-traced increments, and tiny focused contexts.
Was wondering if using front-matter instead of a "custom" encoding for parseble data was considered?
But in general this is meta to the CLI agent.
So if you were to use the CLI to perform a review of some code. This tool would allow you to loop the output of the code review 5 times onto itself.
Claude already does that if you ask nicely.
Where are people finding time for these sort of projects.
My take? I like it. It's concise enough for me to try it out. And I love the webpage.
[1] https://github.com/rjcorwin/cook/blob/main/no-code/SKILL.md
Might work out fine on codex.
* coolers whirring, gpus on fire, tokens flying, investors happy, developer goes for 6th break of the day