tl;dr: https://github.com/cruftbox/llm-friendly-preview

I’ve gotten into the habit of asking AI assistants like Claude, ChatGPT, and Gemini to review my draft posts before I hit publish. A second pair of eyes catches typos, confusing phrasing, and the occasional bad take. The problem was getting them to actually see the draft.

WordPress’s Public Post Preview plugin, my previous go-to, generated preview URLs that a human could click in their own browser, but AI assistants would balk at the link token style. The work around was creating a PDF of the preview and handing that off. That was clunky, took time, and I am lazy.

So I built my own plugin: LLM Friendly Preview. The idea is simple, generate a URL that looks and behaves like a completely normal public page (real theme templates, real styling, no ?preview=1), but is gated by a long, random, single-use token instead of a login session.

From the post editor, I click Generate LLM Review Link, and it hands me something like:

That link works for 3 days and then expires automatically. I can regenerate it or revoke it outright from the same panel, and it’s auto-revoked the moment the post actually gets published, so there’s no lingering way to view a draft that isn’t a draft anymore.

Under the hood it’s all standard WordPress: a rewrite rule, a token stored in protected post meta, time comparison for validation, rate-limiting by IP, and cache-busting headers so no caching plugin accidentally serves up unpublished content to a stranger.

Which LLMs actually work

Here’s where it got interesting. Once the plugin was live, I gave the same link to every the popular models to see who could actually fetch it.

Working: Claude, Gemini, Meta AI, Mistral, Kimi, DeepSeek, Qwen, Grok, HuggingChat, and Ernie Bot all fetch and read the page without issue.

Not working: ChatGPT, Perplexity, and Microsoft Copilot all fail to open the link.

ChatGPT’s failure is the one I actually tracked down: its web-retrieval system rejects newly generated URLs containing private tokens before it even makes an HTTP request. That’s not a bug in WordPress, the plugin, or the response headers. I confirmed the exact same URL returns a clean 200 with the correct content when fetched directly, even spoofing ChatGPT’s own user-agent string. It’s a deliberate caution built into ChatGPT’s URL-safety layer, and it’s exactly the kind of link this plugin is designed to produce: anonymous, temporary, and impossible to guess. Perplexity and Copilot weren’t diagnosed as thoroughly, but the failure pattern looks similar.

For everything else, it works exactly like I wanted: paste a link -> get a review.

All the code is here: https://github.com/cruftbox/llm-friendly-preview

tl;dr: https://github.com/cruftbox/yolodeck

Last week I saw news of an OpenAI gadget for use while running Codex called Codex Micro.

I love a good gadget, but I don’t use Codex much, nor do I need another device on my cluttered deck. The idea of using a button to grant or block permissions seemed great. Many run Bypass Permissions mode, but you do get asked occasionally.

My desk already has an Elgato Stream Deck on it, so I wondered if it could be pressed into use as a similar device when I’m working with Claude Code.

I found a repo by Paul Tyng that had the basics working. His codebase is for macOS, but I work on Windows. So I forked it and worked with Claude to replace ~45 lines of macOS-specific code with Windows equivalents. Most everything else carried over unchanged.

Once I got the basics working, I tried to improve the button design a bit and then add a few features. First was getting a report of how much usage I had left for the session and when it would reset. Running off the Pro plan means having to pay attention to such things that leet Max users don’t have to worry about. I also switch between models, depending on the complexity of the tasks.

This is where I ran into the first issue with how the Claude desktop app on Windows works differently than when running a CLI in Windows Terminal.

From what I found in my testing, when you are running the nice GUI app, Claude kinda says you are running one session at a time. Even though switching between sessions/projects is simple in the app, the underlying hooks only report the single session that you last did active work in.

The second issue: when running the desktop app, there’s no usage data to gather, even though the GUI displays it.

This is weaksauce, IMHO.

Conversely, when running in a terminal, you can be running multiple sessions and yolodeck can see them all. You also get updated usage and reset data. Ideally, this behaviour would be in the Windows app as well, but it’s not.

The Stream Deck lets you know when Claude wants your attention and allows you to approve/deny permissions.

The Stream Deck plugin allows you to place and use (or not use) any of the buttons as you see fit.

I don’t run an agent harness for my home projects, but bolting one on shouldn’t be too hard as long as it can hold open a permission request and wait for my answer, not just fire off a notification after the fact.

In fact, modifying the code to work with Codex or Gemini CLI should be fairly trivial.

All the code is here: https://github.com/cruftbox/yolodeck

I enjoy posting images to Bluesky and Mastodon, and I try to include alt text every time.

I got tired of writing a post, dragging the image into Bluesky, then into Mastodon, then into my other Mastodon account, and then having to go back to paste in the alt text for each account. Posts with multiple images were an even bigger headache.

To quote Heinlein, “Progress is made by lazy men looking for easier ways to do things.”

So I built a thing. It’s called Broadside.

A broadside is when a ship fires every cannon on one side at once. That’s the whole idea: I write a post once, attach my images, add alt text, and Broadside fires it at every Bluesky and Mastodon account I’ve got in a single click.

It’s probably overkill for a single account, but if you’re juggling multiple social accounts it’s a huge quality of life improvement.

Broadside is built with Flask, using the AT Protocol and Mastodon APIs, and runs in a Docker container.

It also supports threaded posts, with Broadside handling the whole chain across each account.

A few other niceties I added:

• Stores app passwords and access tokens through a setup wizard.
• Matches Bluesky’s character counting (emoji and all).
• Resizes images in the browser before upload.
• Generates proper Bluesky link preview cards.
• Shows success/failure status for every account with direct links to each post.

It runs on my home NAS, keeping my credentials local, and never sending them to a third-party service.

Broadside is not a Twitter or Threads tool, just a Bluesky and Mastodon tool. IYKYK.

I built the thing with Claude Code over an afternoon, which still feels a little like cheating.

The code is on GitHub if you want to run or modify it: github.com/cruftbox/broadside.

Compose once. Fire a broadside. Never forget the alt text again.

I have a complicated relationship with information. I want a lot of it: what’s happening in tech, the world, culture, and the corners of the internet I care about. What I don’t want is my inbox turning into a war zone.

Email newsletters are the devil.😈 I don’t care how good your content is.

The moment you land in my inbox, you’re competing with shopping receipts, meeting requests, and shipping notifications. That’s not a reading environment. That’s a stress environment.

I love RSS.🧡 It’s clean, it’s chronological, it’s manageable. No algorithm deciding what I see. No engagement bait.

It’s just the things I subscribed to, in the order they arrived. A lot of the newsletters I actually want to read, The Verge, The New Thing, The Pragmatic Engineer, all publish RSS feeds alongside their email versions.

The problem isn’t RSS. It’s RSS readers.

Most of them are designed for completionists, with every article becoming something you’re expected to process and mark as read. That’s never been how I consume information.

I want to scroll through new stuff when I feel like it, catch what catches my eye, and not feel guilty about the rest.

I am constantly in Discord. I’m there for my varied communities: gaming, beekeeping, smart home, Twitch DJs, etc. It’s already where I spend a lot of my online time. So I started wondering: could a Discord bot manage RSS feeds and push new items into channels? Organized by topic, one feed per channel, there when I want to scroll through them?

Turns out, yes. With some help from Claude, I built Wireburst.

My Wireburst bot currently tracks about 35 feeds. That may not sound like many, but it’s plenty for me. Wireburst will happily handle hundreds.

The idea is simple. You point Wireburst at your RSS feeds, tell it what category they belong to, and it creates a Discord channel for each feed nested under a category group. New items show up individually. No algorithm. Just a channel you can glance at when you feel like it and ignore when you don’t.

Discord has a few limitations. Messages over 4,000 characters are cropped, and while thumbnail images appear, inline article images don’t. When I want the full experience, I just click through to the original article.

I made a separate Discord server for just Wireburst to keep things clean, just me and the bot. You could add it to other servers where you have admin, but I didn’t plan for or test for that.

Each feed gets its own channel. BBC News doesn’t bleed into the LA Times. Kottke.org doesn’t compete with 404media. You get the firehose, but sanely organized.

Most major news sites still publish RSS feeds, even if they don’t advertise them.

Discord works great on mobile as well. I can catch up on the news anywhere, without any ads, pop-ups, or other distractions that clutter up most news sites.

Managing feeds is done through a web admin panel (it’s only accessible on my home network, so I don’t bother with authentication), or through slash commands directly in Discord. Add a feed, pick a category, and within a few seconds the channel appears and the last five items are backfilled so you have something to read right away.

OPML import works too, so if you’ve got an existing feed list from Feedly or any other reader, you can bring it over in one shot. Categories get created automatically from your OPML folder structure.

Is it for everyone? Probably not. If you’re a completionist who needs to mark everything read, this isn’t your tool. But if you live in Discord and you’ve been looking for a way to get RSS into your workflow without adding another app or feeding the email beast, Wireburst might be exactly what you want.

The code is on GitHub, MIT licensed. It runs in Docker🐳, keeping your feeds on infrastructure you control, and even includes a matching icon set.

It’s open source so you can smack it up, flip it, rub it down however you’d like, to fulfill your personal desires.

An LLM🤖 can make customization surprisingly easy. Tell Claude, Gemini, or ChatGPT what you want to change, point them at the codebase, and you’re off to the races. They’ll even generate the correct docker compose command the first time.

Email is still the devil.

RSS in Discord? That I can work with.

While walking the dog I wondered how hard it would be to recreate the Matrix digital rain, a visual that’s lived rent-free in my head since 1999.

1999 seems like both yesterday and a million years ago.

Turns out it was pretty easy for Claude. With a brief description prompt of what I wanted, it got to work. I added the idea of occasional RGB ‘threads’ falling through for a little flourish.

I think using the superpowers agent harness was a bit of overkill, but it helped me learn the process.

My desktop computer runs Windows, so Claude decided to make a .Net executable that runs inside terminal. I don’t even have to run an app. It’s just a pulldown inside of terminal.

An idea while walking the dog turned into a working app before lunch.

Creating things on a whim feels a little magical.

The code is up at Github: https://github.com/cruftbox/phosphor

My friend Matt did an analysis of his longtime blog. Looks amazing.

I’ve been blogging since 2000. That’s an effing long time.

I exported the entire archive and asked Claude to help me build a tool to generate something similar.

Like Matt and others the arrival of Twitter and other microblogging made for a quiet era. The blog was rebuilt in 2024 thanks to Greg.

Clearly I’ve been posting more since then.

It’s a bit humbling to realize that twenty-seven years of my life can be distilled into a few hundred tokens and a series of vector embeddings. Claude managed to find ‘consistent themes of technical curiosity,’ which is a very polite way of saying I’ve been complaining about broken APIs and proprietary cables since the Clinton administration.

Twenty-seven years of blogging and my most consistent behavior is apparently disappearing every January and crawling back for Halloween like a vampire who forgot what month it was. At least I’m reliable about something.

With video now the dominant form on social media, a lot of my recent posts are just embeds of videos I’ve made. I do enjoy making videos. It’s powerful storytelling, which is a strange thing to say about a clip of me opening a beehive.

Looking ahead to the next quarter-century of Cruftbox, I’ll keep writing posts, even if they are basically just long tweets.

I regret nothing.