Developer Experience on Nick Perkins

I Stopped Using MCPs and Replaced Them with Skills and Scripts

Sat, 20 Jun 2026 10:00:00 +1000

Everyone’s excited about MCPs. The Model Context Protocol is supposed to be the standard way AI agents talk to external services. And it is good, for what it is. But I’ve been replacing MCPs with skills and scripts in my own workflows, and honestly, I’m not going back.

The problem with MCPs

When you load an MCP server, all of its tool definitions get injected into the agent’s context. Every tool name, every parameter schema, every description. The Atlassian MCP alone exposes dozens of tools across Jira and Confluence. That’s a lot of schema sitting in your context window before you’ve even asked the agent to do anything.

grug make AI skill. grug happy.

Mon, 06 Apr 2026 10:00:00 +1000

grug been thinking about complexity demon lately. complexity demon sneaky. complexity demon hide in code review. complexity demon whisper “just add one more abstraction.” grug not listen.

grug make thing. thing called grug-brain.

what thing is

grug-brain is AI skill. you give skill to AI, AI become grug. AI then fight complexity demon with you.

AI will:

look at code, say if too complex
suggest simpler way
explain things in grug speak
not add factory pattern when simple function fine

grug inspired by grugbrain.dev. you should go read. very wise. grug just made it easier to load into AI assistant.

The Testing Pyramid Still Matters (Even When AI Wrote Your Tests)

Sat, 07 Mar 2026 10:00:00 +1000

I’ve been spending a lot of time in agentic AI workflows lately. Describe a feature, the agent writes the code, the tests, and the PR. It’s genuinely impressive. And the test suites are taking fifteen minutes to run, full of integration tests that didn’t need to be integration tests.

The testing pyramid didn’t become irrelevant just because AI wrote the tests.

The problem with AI and test placement

AI agents are enthusiastic testers. Ask one to add coverage for a new feature and it’ll write tests, lots of them. The problem isn’t that they default to any particular layer. It’s that they’re trained to optimise for quality and coverage, not for the cost of achieving it. Nobody’s system prompt says “think about how long this test suite will take to run.” So they go overboard. Spinning up a database, creating records via factories, hitting an HTTP endpoint, asserting on the response. It works. The test passes. But it’s expensive.