Ian Nuttall's banner
Ian Nuttall's profile picture

Ian Nuttall

@iannuttall • 77,451 subscribers

TLDR; I make software with AI for fun and profit.

Shorts

added fart open/close myself using the factory cli now to move the app to a toolbar so I can covertly install this while my wife is out 😂

added fart open/close myself using the factory cli now to move the app to a toolbar so I can covertly install this while my wife is out 😂

489,050 просмотров

pro tip for vps servers on hetzner: use eu-central and you get 10x more bandwidth: 20TB vs 1TB then just put cloudflare in front of it!

pro tip for vps servers on hetzner: use eu-central and you get 10x more bandwidth: 20TB vs 1TB then just put cloudflare in front of it!

124,174 просмотров

Anthropic recommend you source AGENTS.⁠md in CLAUDE.⁠md, so I built a tool to do just that, no more symlinks (so you can have Claude-specific rules too)

Anthropic recommend you source AGENTS.⁠md in CLAUDE.⁠md, so I built a tool to do just that, no more symlinks (so you can have Claude-specific rules too)

144,538 просмотров

Looks like Cursor 1.2 is rolling out, now with: - Todo items that stick right by the chat box 😍 - Ability to queue up messages (or interrupt) - Faster Tab - Resolve merge conflicts with Agent - Background Agent improvements - VS Code upgrade to 1.99

Looks like Cursor 1.2 is rolling out, now with: - Todo items that stick right by the chat box 😍 - Ability to queue up messages (or interrupt) - Faster Tab - Resolve merge conflicts with Agent - Background Agent improvements - VS Code upgrade to 1.99

135,648 просмотров

babe, come to bed i can't, i'm vibe coding

babe, come to bed i can't, i'm vibe coding

167,142 просмотров

if you're vibe coding and don't know code (and even if you do) your app can get bloated and have security issues i got claude to write a checklist of items i can add to cursor as context to help vibe apps stay lean and secure prompt in first reply below...

if you're vibe coding and don't know code (and even if you do) your app can get bloated and have security issues i got claude to write a checklist of items i can add to cursor as context to help vibe apps stay lean and secure prompt in first reply below...

143,345 просмотров

In the latest version of Keep, you can now turn an entire 𝕏 thread into markdown by bookmarking any post in it Then you can actually *do something* with your bookmarked content ;)

In the latest version of Keep, you can now turn an entire 𝕏 thread into markdown by bookmarking any post in it Then you can actually *do something* with your bookmarked content ;)

32,811 просмотров

Claude Code pro tip: Hit Esc twice to undo, you can pick a point in the conversation to revert to, and it'll fork the conversation. This is basically checkpoints and lets you rollback and try a new prompt.

Claude Code pro tip: Hit Esc twice to undo, you can pick a point in the conversation to revert to, and it'll fork the conversation. This is basically checkpoints and lets you rollback and try a new prompt.

73,139 просмотров

Claude Code pro tip: use Ctrl+W to delete full words instead of backspacing like a caveman hat tip to Ray Fernando for the tip on his stream

Claude Code pro tip: use Ctrl+W to delete full words instead of backspacing like a caveman hat tip to Ray Fernando for the tip on his stream

69,768 просмотров

"why didn't you just use {insert_email_marketing_tool} instead?" this is why. i can build shit my way and feel proud that i did something!

"why didn't you just use {insert_email_marketing_tool} instead?" this is why. i can build shit my way and feel proud that i did something!

66,999 просмотров

Ok, GPT-5-Codex just dropped in Factory CLI, time to get some work shipped! 🫡

Ok, GPT-5-Codex just dropped in Factory CLI, time to get some work shipped! 🫡

51,514 просмотров

Introducing the playbooks skill security scanner. Checks all agent skill files for possible security risks before you install it. To try it out grab any GitHub URL to a SKILL.⁠md or skill folder, pop it in, hit enter:

Introducing the playbooks skill security scanner. Checks all agent skill files for possible security risks before you install it. To try it out grab any GitHub URL to a SKILL.⁠md or skill folder, pop it in, hit enter:

26,057 просмотров

A bunch of people mentioned bolt.new (cc Eric Simons) so I thought I'd try it out and see how the SEO compares for vibe coders prompt: --- create a directory with mock items, each with its own URL IMPORTANT: the entire project MUST be server side rendered for SEO --- result: It one-shot a full Astro app, complete with breadcrumbs, category links, images, and importantly... all of the content is visible in the source, which is much better for getting crawled, indexed, and ranked in google and LLMs I've been sleeping on Bolt, but damn this was a smooth process

A bunch of people mentioned bolt.new (cc Eric Simons) so I thought I'd try it out and see how the SEO compares for vibe coders prompt: --- create a directory with mock items, each with its own URL IMPORTANT: the entire project MUST be server side rendered for SEO --- result: It one-shot a full Astro app, complete with breadcrumbs, category links, images, and importantly... all of the content is visible in the source, which is much better for getting crawled, indexed, and ranked in google and LLMs I've been sleeping on Bolt, but damn this was a smooth process

63,570 просмотров

Claude Code pro tip: use the new /rewind command to roll back code changes instantly. Model messes up? no biggie, just rewind it back to when it worked!

Claude Code pro tip: use the new /rewind command to roll back code changes instantly. Model messes up? no biggie, just rewind it back to when it worked!

40,662 просмотров

I built an mcp server to have Cursor agent find and add cursor rules to your project no more manual search or commands needed! just ask the agent and get back to vibe coding in your language of choice who wants to test this out for me? lemme know

I built an mcp server to have Cursor agent find and add cursor rules to your project no more manual search or commands needed! just ask the agent and get back to vibe coding in your language of choice who wants to test this out for me? lemme know

62,239 просмотров

Run a security check on all of your locally installed agent skills with this command: npx playbooks scan skills - check why they got flagged - remove any that look dodgy - profit??

Run a security check on all of your locally installed agent skills with this command: npx playbooks scan skills - check why they got flagged - remove any that look dodgy - profit??

21,077 просмотров

Now you can run a swarm of droids, or claudes, or codexes in parallel using the open source emdash app congrats on shipping fast Arne Strickmann (and you didn't need to raise $200m to do it 😉)

Now you can run a swarm of droids, or claudes, or codexes in parallel using the open source emdash app congrats on shipping fast Arne Strickmann (and you didn't need to raise $200m to do it 😉)

35,344 просмотров

Claude Code has turned me into a command line junkie! Here's how I send my email newsletters now:

Claude Code has turned me into a command line junkie! Here's how I send my email newsletters now:

38,705 просмотров

warp code feels like a combination of a cli agent and cursor-style ux design it's a cli that looks like an ide because it gives you: - editor code view - project explorer - one-click to view command output - switch between agent/cli - context/credit spend tracking - task lists - shared context with warp drive there is a learning curve because it's a different workflow, but the agent was top of terminal bench until recently and i can see why would love to see them add: - subagents - an agent sdk - sidebar fonts increasing with cmd +/- not being paid to post this, btw (feel like i have to add that these days 😉) i have been using warp for a long while as a terminal and sometimes agent on the $15/mo plan

warp code feels like a combination of a cli agent and cursor-style ux design it's a cli that looks like an ide because it gives you: - editor code view - project explorer - one-click to view command output - switch between agent/cli - context/credit spend tracking - task lists - shared context with warp drive there is a learning curve because it's a different workflow, but the agent was top of terminal bench until recently and i can see why would love to see them add: - subagents - an agent sdk - sidebar fonts increasing with cmd +/- not being paid to post this, btw (feel like i have to add that these days 😉) i have been using warp for a long while as a terminal and sometimes agent on the $15/mo plan

32,665 просмотров

cursor pro tip: if the agent just won't read your .cursor/rules/{rule}.mdc file even when set to "always" try this instead ↓ add a line to the old .cursorrules file telling it to always read and follow your mdc file hopefully cursor fix this soon

cursor pro tip: if the agent just won't read your .cursor/rules/{rule}.mdc file even when set to "always" try this instead ↓ add a line to the old .cursorrules file telling it to always read and follow your mdc file hopefully cursor fix this soon

42,115 просмотров

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

How to use Claude Code for beginners (This too way too long to edit!) Watch the 15m video covering: - Setting it up in Cursor - How to add a lot of context (hint: not by copy/pasting) - Covering lots of slash commands - How to paste images + lots more 🔥 YT link in replies ↓
15:32
iannuttall's profile picture

How to use Claude Code for beginners (This too way too long to edit!) Watch the 15m video covering: - Setting it up in Cursor - How to add a lot of context (hint: not by copy/pasting) - Covering lots of slash commands - How to paste images + lots more 🔥 YT link in replies ↓

Ian Nuttall

231,608 просмотров • 11 месяцев назад

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)
1:18
iannuttall's profile picture

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,803 просмотров • 9 месяцев назад

Somebody hooked up Claude Code to pair program with o3 and Gemini 2.5 via MCP for an all-star coding lineup 🤯 - Claude controls the work - Can call out to Gemini and o3 for tasks and input - Works around MCP limit by using prompt files Check out Zen MCP (link below)
0:28
iannuttall's profile picture

Somebody hooked up Claude Code to pair program with o3 and Gemini 2.5 via MCP for an all-star coding lineup 🤯 - Claude controls the work - Can call out to Gemini and o3 for tasks and input - Works around MCP limit by using prompt files Check out Zen MCP (link below)

Ian Nuttall

216,423 просмотров • 11 месяцев назад

I put the Codex CLI into a Ralph Wiggum loop and it built AIM (Agent Instant Messenger) then I ran ralph in multiple tabs at the same time and they all used AIM to chat/collab and design the UI look more like the classic AOL messenger (while I was at the gym for 2 hours!)
1:32
iannuttall's profile picture

I put the Codex CLI into a Ralph Wiggum loop and it built AIM (Agent Instant Messenger) then I ran ralph in multiple tabs at the same time and they all used AIM to chat/collab and design the UI look more like the classic AOL messenger (while I was at the gym for 2 hours!)

Ian Nuttall

94,732 просмотров • 4 месяцев назад

cursor pro tip: create a global agent rule to run a bash script every time new files are created your file structure will always be up-to-date so claude knows the hierarchy of your app 🔥
1:03
iannuttall's profile picture

cursor pro tip: create a global agent rule to run a bash script every time new files are created your file structure will always be up-to-date so claude knows the hierarchy of your app 🔥

Ian Nuttall

248,161 просмотров • 1 год назад

i use the terminal a lot now and miss cmd+k in cursor to find out what command i need to run so i built a super simple alias using `droid exec` and now i can run stuff like: $ d kill anything on port 3000 $ d clear all laravel caches uses glm 4.6 but i'd love a faster model!
0:26
iannuttall's profile picture

i use the terminal a lot now and miss cmd+k in cursor to find out what command i need to run so i built a super simple alias using `droid exec` and now i can run stuff like: $ d kill anything on port 3000 $ d clear all laravel caches uses glm 4.6 but i'd love a faster model!

Ian Nuttall

107,579 просмотров • 7 месяцев назад

I built an MCP server boilerplate* for vibe coders to launch paid tools in less than 20 minutes - hosted free on cloudflare - stripe for payments - google or github user login - easy to set up * it's $25 if you want it: mcpboilerplate.⁠com
13:36
iannuttall's profile picture

I built an MCP server boilerplate* for vibe coders to launch paid tools in less than 20 minutes - hosted free on cloudflare - stripe for payments - google or github user login - easy to set up * it's $25 if you want it: mcpboilerplate.⁠com

Ian Nuttall

143,227 просмотров • 1 год назад

Very nice Claude Code dashboard for power users to track every request. - Use multiple subscriptions with load balance to switch accounts - Set models for subagents - Track latency, token usage, and costs in real-time - Full request logging and error traces (Link below!)
0:57
iannuttall's profile picture

Very nice Claude Code dashboard for power users to track every request. - Use multiple subscriptions with load balance to switch accounts - Set models for subagents - Track latency, token usage, and costs in real-time - Full request logging and error traces (Link below!)

Ian Nuttall

109,221 просмотров • 10 месяцев назад

I built a chrome extension to stash my many (many!) tabs so I can read them later 😰 (and get to tab zero!) Agent: factory droids Model: gpt-5-codex-medium Logo: chatgpt Install it here: Code here:
0:54
iannuttall's profile picture

I built a chrome extension to stash my many (many!) tabs so I can read them later 😰 (and get to tab zero!) Agent: factory droids Model: gpt-5-codex-medium Logo: chatgpt Install it here: Code here:

Ian Nuttall

71,286 просмотров • 7 месяцев назад

I built a simple SES email wrapper using Claude Code in less than 5 hours (and would have been less if I didn't try to host on Cloudflare!) @levelsio inspired me to try again after failing to build something like this for myself a while back. VERY rough right now but it works!
4:25
iannuttall's profile picture

I built a simple SES email wrapper using Claude Code in less than 5 hours (and would have been less if I didn't try to host on Cloudflare!) @levelsio inspired me to try again after failing to build something like this for myself a while back. VERY rough right now but it works!

Ian Nuttall

101,989 просмотров • 11 месяцев назад

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)
0:45
iannuttall's profile picture

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)

Ian Nuttall

116,923 просмотров • 1 год назад

okay my free cursor rule builder is live, built by 3.7 sonnet max and $6/hour cost (link in replies) compose your own cursor rules starter kit and export to mdc, legacy, windsurf and cline! should i do this for prompts too and build a huge open source library of prompts?
0:30
iannuttall's profile picture

okay my free cursor rule builder is live, built by 3.7 sonnet max and $6/hour cost (link in replies) compose your own cursor rules starter kit and export to mdc, legacy, windsurf and cline! should i do this for prompts too and build a huge open source library of prompts?

Ian Nuttall

116,859 просмотров • 1 год назад

holy shit i just built an mcp server that sets up other mcp servers in cursor in seconds 🤯 literally asked it to set up stripe mcp and it just... worked!
0:36
iannuttall's profile picture

holy shit i just built an mcp server that sets up other mcp servers in cursor in seconds 🤯 literally asked it to set up stripe mcp and it just... worked!

Ian Nuttall

90,591 просмотров • 1 год назад

CURSOR IS ON YOUR PHONE!1 Watch this 7min video for a first look at how I fixed my broken React app without ever leaving my phone using the Cursor background agent web app
7:12
iannuttall's profile picture

CURSOR IS ON YOUR PHONE!1 Watch this 7min video for a first look at how I fixed my broken React app without ever leaving my phone using the Cursor background agent web app

Ian Nuttall

67,911 просмотров • 11 месяцев назад

YES! This desktop app gives you checkpoints and reverts in Claude Code (needed it soo badly!) - Interactive UI for vibe coders - No code setup of MCP servers - Creating custom agents - Usage tracking - (and lots more) Watch the 2m demo and grab link in replies ↓
1:59
iannuttall's profile picture

YES! This desktop app gives you checkpoints and reverts in Claude Code (needed it soo badly!) - Interactive UI for vibe coders - No code setup of MCP servers - Creating custom agents - Usage tracking - (and lots more) Watch the 2m demo and grab link in replies ↓

Ian Nuttall

68,766 просмотров • 11 месяцев назад

codex cli pro tip: get early access to plan mode by adding collaboration modes under features in ~/.codex/config.toml: [features] collaboration_modes = true it's a bit rough around the edges right now, but asks good questions!
0:30
iannuttall's profile picture

codex cli pro tip: get early access to plan mode by adding collaboration modes under features in ~/.codex/config.toml: [features] collaboration_modes = true it's a bit rough around the edges right now, but asks good questions!

Ian Nuttall

28,450 просмотров • 4 месяцев назад

I have a few more beta invites for my context7 alternative and looking for power users willing to test and tell me if it's worth launching this currently an mcp server but I plan to make it a cli too
0:22
iannuttall's profile picture

I have a few more beta invites for my context7 alternative and looking for power users willing to test and tell me if it's worth launching this currently an mcp server but I plan to make it a cli too

Ian Nuttall

33,410 просмотров • 5 месяцев назад

I open-sourced changes, my TUI to track changes to web pages, feeds, and APIs with readable diffs and optional AI summaries. Just give it a Hetzner API key and it'll set the whole thing up for you. Perfect for non-technical users! feedback + PRs welcome
0:28
iannuttall's profile picture

I open-sourced changes, my TUI to track changes to web pages, feeds, and APIs with readable diffs and optional AI summaries. Just give it a Hetzner API key and it'll set the whole thing up for you. Perfect for non-technical users! feedback + PRs welcome

Ian Nuttall

31,747 просмотров • 5 месяцев назад

I built a Next.js boilerplate to sell access to private GitHub repos using Gumroad in less than an hour with Cursor and v0 (and I don't know Next.js... AT ALL!)
1:02
iannuttall's profile picture

I built a Next.js boilerplate to sell access to private GitHub repos using Gumroad in less than an hour with Cursor and v0 (and I don't know Next.js... AT ALL!)

Ian Nuttall

95,551 просмотров • 1 год назад

Want to run Claude Code in yolo mode but don't want it to potentially cripple your system? Easy 🔥 Install Docker to run it in a sandbox w/ this script: curl -sSL | bash Script below:
0:39
iannuttall's profile picture

Want to run Claude Code in yolo mode but don't want it to potentially cripple your system? Easy 🔥 Install Docker to run it in a sandbox w/ this script: curl -sSL | bash Script below:

Ian Nuttall

47,948 просмотров • 11 месяцев назад