At the request of many, I've put together a "Claude Code Power User" 🤓workshop on Aug 1st. We'll cover:
- Automated workflows (cron, pr, keyboard shortcuts, etc)
- Claude Hooks
- The SDK
- Subagents
- Containers
- Orchestration
Want ULTIMATE POWER? Sign-up here 👇
I broke my "1-2 projects at a time" rule with Fable
Got a lot of exposure in a short amount of time and somehow burned through 15k requests 😅
What surprised me wasn't the benchmarks. A lot of benchmarks feel like noise tbh
It was watching it take a greenfield idea to ~90% complete on its own
And the output was actually good
The weirdest part was how each iteration felt. I'd throw an idea at it, wait a bit and then get to see what came back. Every time felt like opening a present
I'd have other models review the code and most of the time they found nothing
You could absolutely get to the same place with really good loops or by writing everything yourself
But it'd take way longer
What felt different was how I wasn't getting prototypes. I was getting products
It genuinely felt like the future
modernizing egghead, removing 13 years of cruft, final killing rails for good, fixing all the perf issues, failed experiments, broken dreams lol 🥚 beta.egghead.io/
~Once a month I take an afternoon to completely revisit my Codex setup in light of new features and/or an improved model
What I landed on yesterday is really exciting. I feel like I'm actually getting >50% out of Codex what is possible
Working on a blog, but it includes:
- a home thread that manages a todo list that is always open
- a home thread that manages other threads
- heartbeats on almost all of them
Still WIP, but the vision is to simplify everything: show what matters to uniquely me (because an agent can't do it), show me what my agents are up to, and convert my provided goals/tasks/intentions to the right threads who are responsible for those workstreams
In essence, this "home thread" has become my context manager
(context: most my work is not coding)
I've found Fable really understands the intent/vision of my projects.
To the point where I'm trusting it to "do the next right thing".
I can't imagine what I could build with this if I could let it run for a week straight.
💡 Codex Tip: Just ask Codex for automations
Codex can schedule for itself and also update those automations.
- Ask it to do something later in the same thread
- Have it do the same thing it just did but on a regular basis
- Have it review your existing automations and improve them
- Clean up unnecessary / ineffective automations
In my case I still had some automations running on GPT-5.4 so I had Codex update them
ALT Screenshot asking Codex "Update all of my automations to use gpt-5.5" and a confirmation that the automations were updated
📣 Open call to agent builders: Let's read agent skills from `.agents/skills`, so people don't have to manage separate folders per agent.
Today we pulled the trigger for Codex to read `.agents/skills`. Goal is to deprecate `.codex/skills`.
Pls like/tag/RT for momentum.