The art of simplicity

After my posts about automations, I got some questions about other examples where I use this feature. One I like to share is a weekly check that validates my current list of installed skills. Why do we need this? Skills are easy to add and easy to forget. Over time you collect skills that overlap, skills that point to tools that changed, and skills you no longer use. I wanted a recurring check that tells me how to cleanup my skills list. Starting from an existing skill I didn't start from scratch. The ECC repository contains a skill-stocktake skill for Claude Code. It's a /skill-stocktake slash command that audits the skills in ~/.claude/skills/ and the project-level .claude/skills/ , and it has two modes: Quick Scan: re-evaluates only the skills that changed since the last run. Full Stocktake: a complete review. Under the hood it uses shell scripts, a results.json cache, and subagents that evaluate the skills in batches of about 20. That's a ...

Last week I talked about Continuous AI and how the VSCode Automation feature is one example of this vision My blog posts were just written when a new VS Code update landed on my machine with some Automation improvements included. First the automation feature is no longer in preview but enabled by default. But the feature I want to talk about is that you can start sharing automations; either by shipping automation templates through an agent plugin, or by exporting and importing automations as a file. Let's look at both. What gets shared? An automation is a saved prompt, a session configuration and a schedule. Not all of that travels well between machines, so VS Code only shares the portable part: Name and prompt Schedule (manual, hourly, daily or weekly) File format version and an identifier What is not shared: workspace, provider, model, permissions, enabled state and run history. The person who receives the automation makes those choices locally. Thi...

Yesterday I wrote about Automations in the GitHub Copilot app as a hands-on example of Continuous AI — recurring, event-triggered AI tasks running in the background instead of you kicking them off by hand every time. The inkt is not evey dry, or the same concept landed in the latest VSCode release: the VS Code Agents window now has its own Automations feature (still in preview at the moment of writing this post). Let's take it for a spin. Turning it on Automations live in the Agents window sidebar. Two prerequisites: Have the Agents window set up with an available agent. Enable the chat.automations.enabled setting. Creating one In the Agents window sidebar, select Automations , then Create Automation — or start from one of the templates under Start with a template , which pre-fills a prompt and schedule for you. Give it a Name and write the Prompt . Be specific about scope and expected output. Straight from the docs, a solid example: Review all...

In my experience as a software architect, most of what makes CI/CD valuable isn't the "integration" or the "deployment" part. It's the "continuous" part. Things happen in the background, on their own schedule, without someone needing to remember to trigger them. GitHub Next has been pushing a term for what happens when you apply that same idea to AI: Continuous AI , the use of automated AI to support software collaboration on any platform. Not a single tool, not something GitHub owns, just a category. The claim is that this will become as standard a part of software development as CI/CD is today. What Continuous AI actually covers The GitHub Next team lists a handful of recurring patterns: Continuous Triage (labeling and responding to issues), Continuous Documentation (keeping docs in sync with code), Continuous Fault Analysis (explaining failed CI runs), Continuous Summarization, Continuous Code Improvement. Different tasks, same shape. Th...

One of the first things I see people do when you hand them an AI coding agent is build what I call "micro-apps": small applications that solve one specific problem they're having. A colleague of mine built a tool that scans our servers for outdated configurations so we could follow up on the migration process. Another built his own planning tool to support the yearly planning cycle. The code itself takes an agent minutes to produce. The problem shows up right after. The app still needs to be hosted somewhere. That's typically the point where non-technical people get stuck. They don't have a place to deploy a small web app, they don't want to manage a server for something this small, and asking IT to provision infrastructure for a five-minute tool feels disproportionate. This is where the canvas feature in the GitHub Copilot app comes in. Using the /create-canvas slash command, you can turn a conversation with Copilot straight into an interactive interface...

For years, when a .NET developer said "I need the mediator pattern," the answer was almost automatically MediatR . Jimmy Bogard's library became the default so quickly that a lot of teams never really questioned it, they just added the NuGet package and moved on. That changed in 2025. MediatR moved to a commercial license, and suddenly "just add MediatR" wasn't a free decision anymore. That's a good moment to take a step back and look at what the mediator pattern actually is, and to point out something a lot of developers overlook: if you're already using MassTransit in your project, you already have a mediator implementation available. No extra package, no extra license to think about. Remark: Be aware that MassTransit switched to a commercial license as well starting from version 9. What is the mediator pattern? The mediator pattern is about decoupling the sender of a request from the thing that handles it. Instead of a controller or servi...

Recently I was watching one of my AI agents chew through a feature, and in the middle of its chain of thought it dropped: "Bribing the hamster." My first thought was that I was hallucinating instead of the AI model. My reaction was to check my coffee. My second was to find out what was actually going on. Turns out, it's not a hallucination. It's a feature. The setting behind it VS Code's Copilot Chat has a setting called chat.agent.thinking.phrases . Instead of a static "Thinking..." or "Working..." label while the agent is doing its multi-step work in the background, it rotates through a list of playful phrases. Here's what that setting looks like in practice: "chat.agent.thinking.phrases": { "mode": "replace", "phrases": [ "Bribing the hamster", "Reticulating splines", "Untangling the spaghetti" ] } Remark: "Reticulating splines" ...

As developer or architect, you make a lot of design decisions every day. You picked Redis for caching, or REST over GraphQL, ... . You move on after your decision was made, but in the back of your head a voice keeps asking "should I bother a colleague and ask for a second opinion?" , "what if I forgot something?" , "is this really the right choice?" The GitHub Copilot app can help you out with a (new) slash command: /spar . What /spar actually does /spar switches Copilot from "help me build this" to "convince me this is a bad idea." Instead of accepting your plan and generating code, it starts poking at your assumptions, asks about edge cases, and points out tradeoffs you may have skipped past. Remark: this is different from /plan , which helps you break a task down. /spar assumes you already have a plan and wants to stress-test it before you commit. How to use it Type /spar in the chat composer, followed by whatever...

Microsoft just released The Story of VS Code , an official documentary directed by Stefan Kingham that traces the editor's ten-year journey; from a small team in Zurich building a browser-based editor called Monaco, to the tool most of us now open dozens of times a day. Watching it made me think back on my own relationship with VS Code, which turns out to be more of a slow conversion than a sudden switch. Two editors, one workflow For most of my career I've been a Visual Studio guy. Full IDE, integrated debugger, the whole .NET toolchain in one window. That didn't change overnight. What did change is that VS Code quietly became my default for anything web-related — a bit of JavaScript here, a config file there, a quick edit to a YAML pipeline. For years I ran both editors side by side, each with its own job. Visual Studio for "real" application code, VS Code for everything lighter and faster. The extensions ecosystem got me curious I always liked what t...

In my previous post , I covered what Copilot Spaces are and how to set one up. Spaces live on github.com by default, but you don't have to leave your editor to use one. The GitHub MCP server exposes your Spaces as tools, so you can pull that curated context straight into VS Code. Prerequisites You'll need the remote GitHub MCP server configured for VS Code, and the copilot_spaces toolset explicitly enabled. It's not part of the default toolset. The easiest way is to install the GitHub extension in VS Code. This will also add the GitHub MCP server. But as I mentioned above, you will not find the copilot_spaces toolset out-of-the-box. You need to open up the MCP configuration and explicitly add it there. Add this to your .vscode/mcp.json (or your global MCP configuration): { "servers": { "github": { "type": "http", "url": "https://api.githubcopilot.com/mcp/", "headers"...

A lot of developers are using GitHub Copilot as their day-to-day agent harness. But most of them seem to be unaware that with a GitHub Copilot license comes more than a CLI and Visual Studio (Code) plugins. One thing you get access to are GitHub Copilot Spaces. GitHub Copilot what? Let me first explain what Spaces are and why they are useful. Why GitHub Copilot Spaces? If you've used Copilot Chat for a while, you recognize the pattern: you paste in the same background information for the third time this week. The same coding conventions, the same architecture decisions, the same "no, we don't use that library anymore" context. Close the conversation, and Copilot forgets all of it. Remark: Part of the answer can be found in building up your CONTEXT.md file and using the GitHub Memory feature but it’s not always the right solution. That's because source code lives in your repositories, requirements live in issues and pull requests, and team conventions o...

If you've built anything with the Microsoft Agent Framework (MAF), you'll notice that your tool calls can fill up the context window quite fast. A function that returns a list of 50 orders as JSON easily costs you a few hundred tokens on braces, quotes and repeated field names alone. That cost hits you twice: once on the way into the model as tool output, and again on every subsequent turn where that history gets replayed. That's where TOON (Token-Oriented Object Notation) comes in. Let's explore this. What TOON actually is TOON is a line-oriented, indentation-based encoding of the same data model JSON uses. It borrows YAML's indentation for nested objects and CSV's tabular layout for arrays of uniform objects. The trick is in that last part: if you have a list of objects that all share the same fields, TOON declares the field list once and then just streams the values, row by row, instead of repeating every key for every item. Take a small object like t...