Skip to main content
Matthew Deaves
Matthew Deaves
Software & Writing
  • Home
  • Blog
  • About
  • Experience
  • All Projects clog PeerTalk BomberTalk CSend Classic Mac MCP Rockport Cookie Willow CMS TextHarvest QemuMac
  • Toolkit
  • Search

Blog

Occasional thoughts on software, AI, and what I'm learning along the way.

Classic Mac 6 April 2026

BomberTalk Alpha

I played a networked Bomberman game across a Mac SE, a Performa 6200, and a Performa 6400. Three machines spanning 1987 to 1995, all talking to each other over TCP and UDP.

Read more →
Case Study - Developer Tooling 5 April 2026

My Virtual Pentest and DevOps Team

If you're building apps with AI and putting them live, you have to at least try to secure them. Here's how I did it with bash, open source tools, and Claude Code.

Read more →
Case Study - Developer Tooling 3 April 2026

Pentesting with Rook

Anthropic added a companion to Claude Code called Buddy. Mine's an axolotl named Rook. I've been running a pentest suite against Cookie and its infrastructure over the past few evenings, and Rook kept catching things I was missing.

Read more →
Case Study - Developer Tooling 29 March 2026

Guardrails for Claude Code: Hooks, Rules, and Constitutions

Claude Code hooks, rules, and a project constitution enforced via GitHub Spec Kit. A primer on each layer, with a real use case: keeping ES5 compatibility on a recipe manager that runs on iPads from 2012.

Read more →
Case Study - Infrastructure 21 March 2026

Rockport: A Self-Hosted LLM Proxy

I built a self-hosted LiteLLM proxy on EC2 behind a Cloudflare Tunnel. It routes Claude Code traffic to AWS Bedrock with per-key budgets, idle auto-stop, image generation, video generation, and image editing. The repo is public and I'd welcome feedback from anyone who works with this sort of infrastructure.

Read more →
Case Study - AI Development 15 March 2026

Building an Evaluation Harness with Claude Code

I built an evaluation harness to measure the quality of LLM-generated pixel art sprites. Five rounds of calibration, a stubborn intent-vs-reality gap, and some useful C tools for getting assets onto classic Macs.

Read more →
Case Study - Developer Tooling 8 March 2026

I Ditched My Planning System for Fully Automated GitHub Spec Kit

I built 14 custom skills, 4 hooks, and 1.2 MB of phase plans for PeerTalk. Eight phases done, real hardware tested, proper results. Then I started again from scratch with Spec Kit across three repos. Automated builds, hardware testing on Classic Macs, and a cross-platform chat app built in hours.

Read more →
Case Study - Developer Tooling 22 February 2026

Automating Performance Tests on a Performa 6200

How MCP servers and Claude Code skills turned manual hardware testing into an automated workflow. From FileZilla hell to one-command benchmarks on a 30-year-old Mac.

Read more →
Hardware - Repair 10 February 2026

Retro Mac Power Supplies and PS3 Maintenance

Two hardware projects: fixing dead power supplies in my Macintosh Performa 630 and 6200 with a cheap SFX PSU mod, and a PS3 thermal paste replacement.

Read more →
Case Study - Developer Tooling 1 February 2026

Project-Specific Claude Code Customisations

Building custom MCP servers, skills, hooks, and agents for Claude Code. A workshop with Anthropic led me to create a full development toolkit for the PeerTalk SDK project.

Read more →
Analysis - Code Quality 26 January 2026

A Code Review of the Rapid Prototype

The CI pipeline had 15 jobs tracking coverage, complexity, and security. This post examines what they measured, what they missed, and what improvements were made for future projects.

Read more →
Case Study - AI Development 11 January 2026

Rapid Prototyping with Claude Code: A 3-Day Challenge

A 3-day challenge to build a working prototype with as many features as possible, plus a day of CI/CD automation. Django backend, React frontend, ES5 interface for legacy browsers, and AI-powered features.

Read more →

No posts match your filters.

© Matthew Deaves