The @openai build week is next week.
You know what to do.
Step 1: Install the official plugin:
codex plugin add convex@openai-curated
Step 2: codex "build my app with @Convex"
If you aren't yet bold enough to install the Codex app, you can stay in the presence of your orange crab and point it at GPT 5.6 Sol. Takes 5 minutes. Kudos to Theo for explaining one of the ways to get this done.
Step 1: Install CLIProxyAPI
Step 2: Connect
Step 3: Define following alias and enjoy claudex
```
alias claudex='CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol \
CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 \
CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY=3 \
ENABLE_TOOL_SEARCH=false \
claude --model gpt-5.6-sol'
```
If this gets blocked, I owe you a reset.
OpenAI’s GPT-5.6 Sol model can now run inside Claude Code.
There are two ways to do it, and both take minutes to set up, here’s how:
Option 1, the official plugin:
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins, then /codex:setup
That unlocks /codex:review, /codex:adversarial-review, and /codex:rescue. Claude writes, GPT critiques, you ship.
Option 2, the proxy. One alias makes Sol your main model:
alias claudex=‘CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 claude –model gpt-5.6-sol’
Bonus: Claude Code lets you set subagent model and effort yourself.
Sol Ultra runs can burn several times the tokens of a base run, so right-sizing delegated work saves real money.
Everyone talks about loops - but no one shows you a real one
@SToneoneX and I spent a month running loops to automate most of @SuperDesignDev - many many of them. Some worked, some didn't
Recorded a 14-min walkthrough on key learnings with the real examples we run 👇
-------
Open-sourced our internal tool to manage loops: https://t.co/zzgasUOip0
+ Skill for setup verifier: https://t.co/jnY4YXWQFz
introducing https://t.co/20es64pAqZ
a dictionary for ui things you can see but can't name
made it because i'm primarily a designer, and my biggest resistance was always knowing what things are called when prompting my agents
it learns as people use it: every search teaches the site new words, and the built-in pocket dictionary grows with it
give it a try and let me know what you think
can't find something? dm me and i'll add it
i want this to be the lowest resistance resource you have
you can just build things
Today's Hermes Agent Masterclass is the finale! Module 10 covers security, an important topic for running agents to ensure each agent can perform its tasks while minimizing exposure. Hermes has a ton of built-in security features. In this clip, I show how you can set approvals for each profile depending on your needs.
This is bigger than people realize. MUCH bigger.
Claude Code can now literally WATCH videos. YouTube, Zoom calls, Loom recordings. You paste a link and it watches the whole thing while you keep working.
An AI builder just dropped this skill and the way it works is genius:
→ Old tools grabbed 100 random frames per video, so Claude was basically reading the transcript blind
→ This one uses FFmpeg scene detection, it captures a frame every time the screen actually changes
→ Captions come straight from YouTube for free, Whisper handles Zoom and Loom
→ When it's done, it asks if you want to save the analysis into your knowledge base
I'm about to feed it every consulting call recording from this week and have the action items waiting in my second brain before I'm even off the call.
All the other skills I run inside Claude Code are in the article below.
I used Fable 5 to reverse-engineer Alex Hormozi’s entire $100M+ business funnel.
Then I built an extremely powerful Claude prompt that replicates his marketing brain (trained on all his data).
Someone is probably charging hundreds for these frameworks somewhere:
status update: the Sunday Light is indeed the closest thing to sunlight you can buy.
10/10, no regrets. absolutely bonkers. for reference, this is my actual light at 80% brightness in a room with almost zero outside light.
The best way to design and build with your repository is Cursor/Codex + MagicPath.
Watch me import components from my repo into the MagicPath canvas inside Cursor, then explore completely different variations.
All while they stay interactive and faithful to the source code 👇
You can now vibe code a language model.
From a single prompt, GPT‑5.6 built the entire training pipeline and trained a model from scratch on my iMessage history. Locally on my Mac.
It now generates replies in my writing style.
My skills repo has 160K stars, 7.5m downloads...
...and no tutorial.
So, here it is. Watch me walk through the essential skills:
- /grill-with-docs
- /to-spec
- /to-tickets
- /implement
- /code-review
It's the whole flow, end-to-end. Enjoy: