Oleg Kope

Tradeoff: it eats more tokens. But honestly, tokens are cheaper than fighting the framework. github.com/procoders/supe…

Tired of Claude Code Superpowers being too rigid? We built V-Compound to make them more flexible. It solves most of the pain: → better skill composition → easier customization → less workflow rigidity → more room for real dev work

发现个宝藏项目 再也不愁你的SEO和google ads了 github.com/nowork-studio/…

I love asking Claude: “Find my competitors’ backlinks, rank the best link opportunities, and explain why they’re worth going after.” The CrawlConsole MCP makes this possible by giving your AI agent the backlink data to answer Sign up for free to connect your AI agent:

Astrology Vedic just hit 5 subscribers on @mcpize. Wild. mcpize.com/mcp/astrology-…

Claude Code weekly limits are increasing 50%, now through July 13. Live now for all Pro, Max, Team, and seat-based Enterprise users.

How do you keep Claude working until the job is done? Claude Code helps with this in a few ways, including one we shipped recently: /goal.

Nice way to visualise flows in your product

Family of Claws: - OpenClaw is like WordPress with a bunch of plugins. - NanoClaw is like a microframe with Docker sandbox. - Nanobot is like a training/hacking minimal core. - ZeroClaw is like an nginx/Go/Rust-style small binary. - NemoClaw is like an enterprise security wrapper around an agent system.

Claude Code 2.1.139 added /goal You set a completion condition and Claude keeps working across turns until it's met Works in interactive, -p, and Remote Control 👏

@levelsio @Cloudflare Yesterday Codex was able to setup Cloudflare email for me: setup a new email address and send a transactional email. All from the CLI. I might also try this agentic Cloudflare email repo 🔜 github.com/cloudflare/age…

Oh I forgot to add, Cloudflare email is $5/mo (for Workers) but then includes 3000 free emails per month

A good way to bypass Claude Design quote github.com/nexu-io/open-d…

Usage limits are up, effective today we're: 1) Doubling Claude Code's 5-hour limits for Pro, Max, Team and seat-based Enterprise plans 2) Removing peak hours limit reduction on Claude Code for Pro and Max plans 3) Substantially raising our API rate limits for Opus models

Grok 4.3 is now live on the xAI API. It’s our fastest, most intelligent model to date. It tops the @ArtificialAnlys leaderboards in agentic tool calling and instruction following, and ranks #1 in @ValsAI enterprise domains like case law and corporate finance. Grok 4.3 supports a 1 million token context window and is priced at $1.25/m input and $2.50/m output. Create an API key and start building: console.x.ai/team/default/a…

lets one-shot an ios app with the new goal feature in codex. what is codex /goal? use goal when the task will take many turns or long-running work, like shipping a release, fixing CI until green, auditing a repo, or one shot an app. you can enable it with [features] goals = true 1. the plan i started with gpt thinking (discussion) & switched to pro for the complete spec. basically I described the app i wanted to build. i knew i needed a proper app spec first, so the long run would actually be worth it. (i'll share the templates in the comments). then i downloaded the spec (gpt pro creates a .zip file for you) with a handoff to codex. 2. context and skills to give codex more context about the ios app ecosystem, i used these skills/mcp: → xcodebuildmcp a bridge that lets codex control xcode and the ios simulator. created by @camsoft2000 → ios/swiftui ios app implementation loop (swiftui, simulator debugging, best practices). created by @Dimillian → asc (App Store Connector CLI) app store connector skill which helps with submissions, release and distribution. shoutout to @rudrank 3. build it the next part was up to codex. i just told it: "/goal read all the files in docs/*.md, implement everything production ready and don't stop until its landed in testflight". after ~3 hours the app was ready and it stopped at testflight submission. my fault, since i still had to do the setup and paperwork before. but i did it all with the browser use skill, and it filled most of the fields and connected the asc cli with the correct permissions. 4. fine tune. there is a second new command called /side, which lets you chat in the same window in a fresh context about ideas or follow-up plans. i asked there about some app connect store stuff, the design system used, and how we could improve it. with the ESC key, you can always go back to the main thread. 5. summary yeah finally the app landed in testflight and i already do some testing on my phone. in the video below you can see the result. i didn't touch any code and just let codex run for 2-3 hours alone. during the last 2 hours, i did visual adjustments and some input changes. testing and controlling the app was also done automatically by codex. it just inspects → implements → tests live → reviews and fixes. that’s the loop.

The biggest advancement in AI coding this year has been /goal And it isn't even close It allows your AI agent to quite literally work for days without stopping. You give a mission. It works until the mission is complete Here's the thing though: /goal is useless if you don't use it properly You NEED a good prompt for it I found basically any prompt I hand write after /goal is never good enough. It produces results that might as well have been a normal prompt Meta prompting is the answer Go to any AI that has context around the project you're working on Say "I'm working with Codex and I want to use their new /goal feature. Please research their /goal feature. Then, take a look at our project and give me 3 options for how we could use /goal to be maximally productive. Then give me a highly detailed /goal prompt for each" Take one of the prompts then go into the Codex CLI and type /goal then give the new prompt I 100% guarantee the AI does better work than you've ever seen before

x.ai/news/grok-cust… @elonmusk good job!

SAM ALTMAN: “People talk about how much energy it takes to train an AI model … But it also takes a lot of energy to train a human." "It takes like 20 years of life and all of the food you eat during that time before you get smart.”