Read the full article on sshh.io A breakdown of how one developer integrates Claude Code into their daily engineering workflow. Core Setup: The `CLAUDE.md` File The CLAUDE.md file acts as the repo’s operating manual for the agent. It defines the main tools, APIs, and convent...

To make a language model less predictable and more insightful, apply the following strategies: Use a negative style guideClearly state what you don’t want the model to do. Force divergence in choicePush the model to break away from default phrasing or reasoning patterns....

Overview At the start of a session Claude’s various harnesses can scan all available skill files and read a short explanation for each one from the frontmatter YAML in the Markdown file. This is very token efficient: each skill only takes up a few dozen extra tokens, with t...

1. Agent primitives are software: Your .prompt.md and .instructions.md files represent executable natural language programs that deserve professional tooling infrastructure.
2. Runtime diversity enables scale: Agent CLI runtimes provide the execution environments that bridge development to production.
3. Package management is critical: APM provides the npm-equivalent layer that makes agent primitives truly portable and shareable.
4. Production ready today: This tooling stack enables automated AI workflows in CI/CD pipelines with enterprise-grade reliability.
5. Ecosystem growth pattern: Package management infrastructure creates the foundation for thriving ecosystems of shared workflows, tools, and community libraries

How to build reliable AI workflows with agentic primitives and context engineering

Setup it's three markdown files, and it's basically three prompts. What I figured out is, okay, if you want to build something, whether it's the whole app or just a feature of the app, you of course have to create a PRD, a product requirement doc, and again, it's like, duh....

I think it is one of the most powerful ways to create clarity of thinking for yourself, because clarity of thinking is, in my view, one of the most important things. And you only can really get that by forcing yourself to write down your ideas. And so I suppose one pertinent or timely piece of advice is, if you care about this, do not use an LLM to produce text for YouTube.

Because first of all, if you're putting your name on this thing, at least today, the LLM is like, it's pretty easy to tell when somebody does that. But more importantly, you are losing the opportunity to do the thinking yourself. And that thinking that happens when you write is one of the most important types of thinking for growth.

Bobby Holley

Mitchell Hashimoto describes how he shipped Ghostty’s unobtrusive macOS update UI using agentic AI with deliberate human oversight.  Plan before you prompt Define the shape of the solution first. Hashimoto chose Sparkle’s custom UI path and a titlebar accessory concept, th...

After the release from Gemini Cli, Claude Code is now offerings plugins. It seems taylor made for the Enterprise or teams, to quickly share configurations between team members. Excited to try it out.

Source: Claude Code plugins

The co-founder of Instagram, Mike Krieger, which is now at Anthropic, mentioned that they use the Claude Agent SDK in a automated Slack channel when there is a new incident. It is name Claude Pager and it gathers all the context of the incident and can be poked to give out infromation when needed.

I have been waiting to implement something similar in our stack, once we are finally off the waiting list of the Datadog MCP waitlist...

Source: Big Technology Podcast

Following the vibe research, we now get vibe engineering from Simon Willison: Definition Vibe engineering establishes a clear distinction from vibe coding. It signals that this is a different, harder and more sophisticated way of working with AI tools to build production so...

“vibe research”. Like “vibe coding”, it’s performing a difficult technical task by relying on the model. I have a broad intuitive sense of what approaches are being tried, but I definitely don’t have a deep enough understanding to do this research unassisted. A real AI researcher would get a lot more out of the tool.

The basic loop of doing AI research with Codex (at least as an enthusiastic amateur) looks something like this:

1. Codex makes a change to the training script and does three or four runs (this takes ~20 minutes overall)
2. Based on the results, Codex suggests two or three things that you could try next
3. I pick one of them (or very occasionally suggest my own idea) and return to (1).

Source: https://www.seangoedecke.com/ai-research-with-codex/

OpenAI just announced that Codex is now generally available, and they're shipping some really practical features that make it way more useful for engineering teams. What's New The big additions are a Slack integration, the Codex SDK, and better admin tools. But honestly, the...

OpenAI just dropped AgentKit at their DevDay event, and it's basically their answer to making AI agent development way less painful. Think of it as Zapier, but specifically designed for building and orchestrating AI agents. What Is AgentKit? Until now, building AI agents mea...

Story: ⭐⭐⭐ | Narration: ⭐⭐⭐⭐⭐ Gene Kim and Steve Yegge’s audiobook on vibe coding has excellent narration, but I’d recommend checking out their YouTube channel instead. Most of the book’s examples were already covered in their promotional videos, and the high-level approach ...

Welcome to my vibe-coded blog, built on GitHub Gists. I've been following Simon Willison's excellent blog for a few months, and this post in particular sparked something for me: My approach to running a link blog. A few months later, here we are. Why? Why not? I'm preparing ...