Loading video...

Video Failed to Load

Go Home

Sharing my opinionated setup for coding with agents. zellij + ghostty + codex, claude, pi & ∞ + lazygit Enough insight at a glance as to whats changing, but still surfing tokens. Inbuilt sensible keybindings and sane defaults. One command: ❯ sesh

almonk's profile picture

almonk

11,501 subscribers

42,353 views • 3 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Absolutely loving this setup: Claude Code + Ghostty + Lazygit + Worktree I’m writing 3 threads on X showing how you can use it: 1- Ghostty setup and SAND keybindings 2- Monitoring Claude Code changes with Lazygit 3- Parallel agents with Git worktrees + Claude Code I’ll publish one per week, using exactly the same setup and workflow I use. If you’re interested, feel free to follow along so you catch them
0:14

Absolutely loving this setup: Claude Code + Ghostty + Lazygit + Worktree I’m writing 3 threads on X showing how you can use it: 1- Ghostty setup and SAND keybindings 2- Monitoring Claude Code changes with Lazygit 3- Parallel agents with Git worktrees + Claude Code I’ll publish one per week, using exactly the same setup and workflow I use. If you’re interested, feel free to follow along so you catch them

Daniel San

161,544 views • 4 months ago

This might be my new vibe coding terminal setup: > claude / codex on the side > file explorer in middle > git and diff view on the right Tools used: > ghostty > yazi > lazygit Thanks Daniel San for the lazygit pro tip!
0:10

This might be my new vibe coding terminal setup: > claude / codex on the side > file explorer in middle > git and diff view on the right Tools used: > ghostty > yazi > lazygit Thanks Daniel San for the lazygit pro tip!

Chong-U

26,978 views • 4 months ago

Ghostty + Claude Code + Vercel statusline + Neon statusline + Lazygit How are you handling multitasking when running multiple agents? Right now it’s just two across different projects, but sometimes it’s three per project using separate worktrees.
0:14

Ghostty + Claude Code + Vercel statusline + Neon statusline + Lazygit How are you handling multitasking when running multiple agents? Right now it’s just two across different projects, but sometimes it’s three per project using separate worktrees.

Daniel San

80,743 views • 3 months ago

2 quality-of-life improvements for developers working with Codex today: Codex background agents now have stable pixel identicons. When the same agent shows up across tabs, mentions, transcripts, and the thread panel, it’s easier to recognize at a glance.
0:13

2 quality-of-life improvements for developers working with Codex today: Codex background agents now have stable pixel identicons. When the same agent shows up across tabs, mentions, transcripts, and the thread panel, it’s easier to recognize at a glance.

OpenAI Developers

170,326 views • 8 days ago

I hated how bad agents are at design I hated how Codex can't access Mobbin So I created Lazyweb - 257k+ screens (apps/web) - 6 opinionated design research skills - 1 MCP (Claude/Codex) 100% Free...AI native...no rate limits...no subscriptions.. Enjoy (and tell a friend) 🫡
0:15

I hated how bad agents are at design I hated how Codex can't access Mobbin So I created Lazyweb - 257k+ screens (apps/web) - 6 opinionated design research skills - 1 MCP (Claude/Codex) 100% Free...AI native...no rate limits...no subscriptions.. Enjoy (and tell a friend) 🫡

Ali Abouelatta

328,372 views • 1 month ago

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇
0:15

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇

EyeingAI

40,942 views • 2 months ago

You can now customize your Claude Code keybindings! /keybindings to get started
0:11

You can now customize your Claude Code keybindings! /keybindings to get started

Boris Cherny

156,509 views • 4 months ago

Ollama 0.16 just dropped & it's freaking awesome 🐑 The latest version introduces a new "ollama" command that lets you launch different AI coding tools. You can directly use Claude Code, Codex, OpenClaw, and more without any extra setup or config. Just update Ollama to the latest version and enjoy the new benefits :) Hope this helps ✅️ Follow Ram Maheshwari for more 💎 #html #ai #javascript #coding #webdevelopment #programming
0:11

Ollama 0.16 just dropped & it's freaking awesome 🐑 The latest version introduces a new "ollama" command that lets you launch different AI coding tools. You can directly use Claude Code, Codex, OpenClaw, and more without any extra setup or config. Just update Ollama to the latest version and enjoy the new benefits :) Hope this helps ✅️ Follow Ram Maheshwari for more 💎 #html #ai #javascript #coding #webdevelopment #programming

Ram Maheshwari

21,687 views • 3 months ago

21st Agents is now in Public Beta. The infra layer to ship Claude Code & Codex agents inside your product. In minutes. Comment for free credits to try 🧵
0:10

21st Agents is now in Public Beta. The infra layer to ship Claude Code & Codex agents inside your product. In minutes. Comment for free credits to try 🧵

serafim

83,351 views • 3 months ago

I used a similar technique recently to reverse engineer the beautiful tabs in OpenAI ‘s Atlas browser. Took a screen recording, had an agent describe the design, the tab metrics, the easing curves etc. Had Codex do one pass and have Claude critique it, and got this highly responsive, pretty well structured macOS component out of it
0:13

I used a similar technique recently to reverse engineer the beautiful tabs in OpenAI ‘s Atlas browser. Took a screen recording, had an agent describe the design, the tab metrics, the easing curves etc. Had Codex do one pass and have Claude critique it, and got this highly responsive, pretty well structured macOS component out of it

almonk

91,042 views • 7 days ago

I’m joining OpenAI Codex to work on the future of agentic development! At Cursor, I got to see the shift from autocomplete to agents. The next step isn’t a better IDE. It’s an Agent Development Environment (ADE): systems and tools for orchestrating agents, reasoning over their outputs, and making them autonomous enough to reliably complete ambitious work. After chatting with Alexander Embiricos and Tibo, it was clear that Codex is the best place to realize this vision. The team has consistently shipped SOTA models for agentic coding (check out gpt-5.3-codex) and I’m pumped for the future that the new Codex App points to. What I’m most excited about is the broader mission: accelerating the knowledge work economy. All agents are coding agents, and we’re already seeing Codex used across every job function within organizations. I’m extremely grateful for my time at Cursor, working with the incredible team, and I’m proud of what we built together. I’m excited to take an even bigger swing with Codex. If you’re curious to get a glimpse of where we are headed, download the Codex App! If you want to work on this mission, please apply or reach out - we are hiring across all functions! You can just build things.
0:12

I’m joining OpenAI Codex to work on the future of agentic development! At Cursor, I got to see the shift from autocomplete to agents. The next step isn’t a better IDE. It’s an Agent Development Environment (ADE): systems and tools for orchestrating agents, reasoning over their outputs, and making them autonomous enough to reliably complete ambitious work. After chatting with Alexander Embiricos and Tibo, it was clear that Codex is the best place to realize this vision. The team has consistently shipped SOTA models for agentic coding (check out gpt-5.3-codex) and I’m pumped for the future that the new Codex App points to. What I’m most excited about is the broader mission: accelerating the knowledge work economy. All agents are coding agents, and we’re already seeing Codex used across every job function within organizations. I’m extremely grateful for my time at Cursor, working with the incredible team, and I’m proud of what we built together. I’m excited to take an even bigger swing with Codex. If you’re curious to get a glimpse of where we are headed, download the Codex App! If you want to work on this mission, please apply or reach out - we are hiring across all functions! You can just build things.

Rohan Varma

759,077 views • 3 months ago

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.
0:10

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.

elvis

81,765 views • 7 months ago

Got my dog as a Codex pet, but more interestingly got Codex to add the rings to show my Codex limits. Outer ring is 5 hours, inner the weekly one
0:14

Got my dog as a Codex pet, but more interestingly got Codex to add the rings to show my Codex limits. Outer ring is 5 hours, inner the weekly one

Peter Gostev

164,795 views • 1 month ago

Claude vs Codex Day 4 of vibe-designing. Super happy with what I got from Claude and Codex. I wanted both to follow the same direction, but I got slightly different results, and I’m honestly happy with both. Which one would you pick?
0:16

Claude vs Codex Day 4 of vibe-designing. Super happy with what I got from Claude and Codex. I wanted both to follow the same direction, but I got slightly different results, and I’m honestly happy with both. Which one would you pick?

Masum

78,729 views • 2 months ago

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like
0:14

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like

Tibor Blaho

29,794 views • 3 months ago

Making OpenCode as lean as Pi agent? Just trimmed 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All in
0:11

Making OpenCode as lean as Pi agent? Just trimmed 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All in

raymel 👋

36,772 views • 10 days ago

Claude 4 just launched from Anthropic I was lucky to get early access. tl:dr from my experience: 1. It's still best in class at writing and editing 2. It's just as good at coding as Gemini 2.5 It built this full working version of Tetris in one shot - link to play below:
0:17

Claude 4 just launched from Anthropic I was lucky to get early access. tl:dr from my experience: 1. It's still best in class at writing and editing 2. It's just as good at coding as Gemini 2.5 It built this full working version of Tetris in one shot - link to play below:

Peter Yang

222,138 views • 1 year ago

Me prompting my coding agents at 3am
0:18

Me prompting my coding agents at 3am

Matthew Gallagher

473,734 views • 2 months ago

Introducing: Browser Use Desktop 🖥️ A new interface for AI browser automation. > Global shortcut to spin up agents > Run multiple agents in the background > Supports Claude Code and Codex Try it now ↓🔗
0:13

Introducing: Browser Use Desktop 🖥️ A new interface for AI browser automation. > Global shortcut to spin up agents > Run multiple agents in the background > Supports Claude Code and Codex Try it now ↓🔗

Reagan Hsu

96,301 views • 1 month ago

The W&B MCP server is officially LIVE! Coding agents could always read your code. Now they can read your experiments, monitor training, and drive their own research loops. 20 tools, hosted on every W&B deployment, plugs into Claude Code, Cursor, Codex, Gemini-CLI, and LeChat.
0:12

The W&B MCP server is officially LIVE! Coding agents could always read your code. Now they can read your experiments, monitor training, and drive their own research loops. 20 tools, hosted on every W&B deployment, plugs into Claude Code, Cursor, Codex, Gemini-CLI, and LeChat.

Weights & Biases

16,260 views • 11 days ago