Here you go. The green bar is the claude code 5 min cache expiry countdown timer (anthropic charges a fraction of cached context, I forget something like 10 or 30% of the normal price, but the cache is only 5 min for most users, 1 hr for enterprise/premium)
Have you tried analysing all your prompts, and then telling it to "figure out" what custom skills might improve your prompts?
I do actually have another project I'm working on that does this... it's been super useful for seeing how I prompt, what Skills I use and getting them to evolve and improve (I know Hermes does some of this, but it's been interesting rolling my own - will release soon!!)
I have a pretty specific workflow, I deal with live systems a lot (primarily in staging but occasionally prod) and have a really neat skill that has hooks into all the various things and then writes (&& checks in git) an investigation doc (.md) using a template into a git knowledgebase by month/quarter. That knowledgebase is really useful for frontloading the context of my new sessions as a lot of my work is iterative on previous work. It is really good at 80% of tasks, but simple stuff like using sops or modifying subcharts in helm it really struggles with. I do a lot of integration work between monorepos and Opus 4.7/4.8 really struggle with that kind of work. Opus is so bad at sops work I just outsource that to Codex/GPT5.5 now because the failure rate is so high.
The other high failure rate things is opus correctly predicting where endpoints will end up (stacked endpoints), when you have an ingress with a main monorepo but it's endpoints are the outputs (not just json regurgitated/passed forward).
I figured by having the clanker write it's own documentation about what it did, and then the next time saying "go look at invest doc 2026-06-29-TICKT_1234.md, do that again, but here's what we're doing differently and why..." and it would immediately grep the situation, but it doesn't. As alluded to earlier I've been exploring other models since the corporate blessed one is struggling to keep up.
Nice! I love Cal Newport. I've definitely found spinning up multiple Claude Code instances eats into your focus, and you can "lose yourself" quite quickly.
I find I use pomodoros more as nudges, and use the "beeps" to bring me back if I'm in the browser or something. but yeah... it's a trap for sure!
Me too. Also it’s good to get decent reports that can be used for other things. For example the logs help me fill in my time sheets. Also it forces me to take breaks
Thanks for sharing. I was stuck in a Greek hospital for 8 days with 2 fractured vertebrae, before I could get home.
It’s easy to get into a spiral, but putting your mind to build something really helps.
I do hope your ribs and collar bone is getting better?
I’ve been lucky, as it will heal but could have been really bad. Phew!
Mmm apols. You’d think I’d have learned my lesson by now, but it’s just so seductive to have it write for you.
I got burned with this very HN post for doing just that, but they kindly let me rewrite it.
Will tweak it. Thanks for the feedback!
Fantastic. I think these small productivity tools embedded in harnesses is pretty powerful.
I especially like that you can get the AI to use it and also just pop into the CLI.
Also nice to generate useful web dashboards etc
