
◉ Product Engineer ◉ DX Enthusiast Prev: @_BuildBear @JohnMorrisGroup @amplifynhq
Sri Lanka 🇱🇰
Joined June 2013
- Tweets1.7K
- Following1.9K
- Followers748
- Likes9.5K
Kasun Peiris retweeted
Rex demo time: magical and automatic remote copy/paste, drag/drop, and port forwarding (e.g. open web servers running on remote machines in your local browser). Plus, showcasing some of the internal plumbing that powers this and how you can hook into it with Lua scripting.
Our goal with Superlogical and Rex is for everything to feel local. I've said before: the moment any UI shows a selector between "local" and "cloud", the product has failed. The lines should blur, and we should build the foundational technology that makes it happen performantly, securely, and beautifully.
Hey @paper, Why don't we have a `delete_page` option from the MCP, so the agents are able to delete unwanted pages?
I have about 200+ pages to delete and agent was only able to mark the unwanted pages with (delete) prefix.
I'm too impatient to delete all by hand 🥲
1
33
I'm not against touchscreens on laptop. I can see how they'd be useful.
But In a world where we are touching the keyboard less and buttons are being removed from interfaces, the time for this Macbook has passed.
I could be wrong. I don't think I am.
NEW VIDEO - Apple decided to drop a touchscreen Macbook Pro today. Let's talk about it: youtu.be/2reQut8WNGc
Introducing shadcn/lint. An agent-first linter for Tailwind design systems.
You define what’s allowed. When an agent breaks a rule, the error explains what’s wrong and how to fix it using your components, variants and theme.
There’s a lot you can do with this. Let me show you ↓
github.com/shadcn-ui/lint
We are open sourcing `cn`, a new engine for Tailwind class merging and conflict resolution. It is a drop-in replacement for tailwind-merge and clsx.
It works with all frameworks, runs everywhere and is 30x faster.
Brought to you by @aidenybai and me.
github.com/shadcn-ui/cn
This is very true. and people shouldn’t tolerate this scam in the name of “Speed + productivity”
We need laws for AI companies.
1. Subscriptions must clearly say what we're paying for, and the limits shouldn't magically change.
If you advertise 20x usage, you can't hide in small letters that it's 20x for the 5-hour limit but NOT the weekly limit.
2. Once a model is released and benchmarked, those benchmarks should be continuously verified.
You shouldn't be able to release the "best model", slowly make it worse over time, then release the next "best model" and push everyone toward it.
We need transparency.
1
86
Kasun Peiris retweeted
One command to prevent this using my skill set:
echo "Tautological tests considered harmful." >> CODING_STANDARDS.md
From then on, /code-review will pick this up
Introducing Token-Cost plugin for Claude Code
While preparing an invoice for a project I completed, I got curious about what my actual Claude Code cost was for the project.
Sadly, there’s no official way to check this on a subscription. Claude Code only keeps the last 30 days of history per project by default, and there’s no built-in way to see costs at the task level. Raw session logs exist, but nothing ties tokens back to individual tasks, and there’s no UI to view them.
So I vibe-coded a little Claude Code plugin to keep records of all task information per project locally, including the cost per task. The result was so good that I went a little overboard and vibe-coded a TUI version and an HTML version of the same thing.
Since @AnthropicAI hasn’t published how token pricing works on subscriptions, I used their published API token rates to estimate the costs.
At least now I can keep a complete task log for each project, with a clear way to view everything and get an idea of the real cost per project, task by task.
github.com/peiris/token-cost
Kasun Peiris retweeted
The thing I miss the most about coding by hand is the clarity.
You knew exactly what lives in which file, why you wrote a specific line, why you rewrote the other one, why you used this library.
You still can have such awareness, but it’s harder since everything happens faster
Kasun Peiris retweeted
There will be 3 types of people in the future:
The Purists - reject AI and become new-age hippies
The Automatons - outsource every decision and become machines
The New Renaissance Man - maintains humanity and leverages tech to do what used to be impossible
.@thsottiaux @sama Please give your frontend devs some widescreen monitors to test UIs 😅
1
79
Kasun Peiris retweeted
mattpocock/skills v1.2 is out!
We're now the 19th most-starred repo of all time. 13.5m downloads on skills.sh. Thanks for your support!
Here's what's new:
- Docs: the community's biggest ask. Every skill documented, with explanations of the main flows + troubleshooting
- Claude Plugin: install via Claude's official marketplace
- Codex Support: full Codex support via agents/openai.yaml files
Updated Skills:
- /grilling now asks you questions in rounds, not one-by-one
- /prototype now uses HTML instead of a TUI for building logic prototypes - easier to share and far richer
- /writing-for-agents renamed from /writing-great-skills, use it for ANYTHING your agents read (AGENTS.md, system prompts, docs)
New Skills:
- /wizard: tired of provisioning infra? Get your agent to build you a TUI to walk you through it
- /to-questionnaire: hit a grilling question you can't answer? Turn the session into a doc you can walk through on a call with a colleague
- /wait-what: no idea what the model said? Refocus it in your domain language and simplify with ASD-STE100
Full changelog + docs below. Video soon!

















