Blog posts by Matt Fehrenbachhttps://m4t.tf/en-gbhttps://m4t.tf/posts/20260615-1-why-i-built-yab/https://m4t.tf/posts/20260615-1-why-i-built-yab/The story behind making this blog.Mon, 15 Jun 2026 00:00:00 GMThttps://m4t.tf/posts/20260615-2-lazy-commit-messages/https://m4t.tf/posts/20260615-2-lazy-commit-messages/I wrote an agent skill to reduce hassle.Mon, 15 Jun 2026 00:00:00 GMThttps://m4t.tf/posts/20260618-1-ogle-at-logs/https://m4t.tf/posts/20260618-1-ogle-at-logs/A terminal dashboard for Docker Compose projects.Thu, 18 Jun 2026 00:00:00 GMThttps://m4t.tf/posts/20260623-1-fractal-renders-on-jwildfire/https://m4t.tf/posts/20260623-1-fractal-renders-on-jwildfire/JWildfire, a free tool for making generative art.Tue, 23 Jun 2026 00:00:00 GMThttps://m4t.tf/posts/20260626-1-orchestrating-ai-coding-agents-with-sandcastle/https://m4t.tf/posts/20260626-1-orchestrating-ai-coding-agents-with-sandcastle/Sandcastle is a TypeScript library and CLI for orchestrating AI coding agents across 6 providers and 4 sandbox runtimes.Fri, 26 Jun 2026 00:00:00 GMThttps://m4t.tf/posts/20260626-2-how-i-tailored-sandcastle-for-ogle/https://m4t.tf/posts/20260626-2-how-i-tailored-sandcastle-for-ogle/Taking Sandcastle's parallel-planner-with-review template and tailoring it to a Go project's specific needs - custom Docker image, phase-specific models, Go-specific prompts, and the scrivener documentation audit.Fri, 26 Jun 2026 00:00:00 GMThttps://m4t.tf/posts/20260630-1-plan-iterate-implement-with-opencode/https://m4t.tf/posts/20260630-1-plan-iterate-implement-with-opencode/A three-phase loop that gets better code out of AI coding agents.Tue, 30 Jun 2026 00:00:00 GMThttps://m4t.tf/posts/20260716-1-grill-me-skill/https://m4t.tf/posts/20260716-1-grill-me-skill/Stress-test your plans and designs before writing code, with a Socratic agent that grills you one question at a time.Thu, 16 Jul 2026 00:00:00 GMThttps://m4t.tf/posts/20260908-1-llms-are-tactical-programmers/https://m4t.tf/posts/20260908-1-llms-are-tactical-programmers/LLMs are very good at making changes. They are less good at deciding which changes should exist in the first place.Tue, 08 Sep 2026 00:00:00 GMThttps://m4t.tf/posts/20260908-2-humanize-skill/https://m4t.tf/posts/20260908-2-humanize-skill/The humanize skill removes language that performs importance while preserving meaning, voice, and useful detail.Tue, 08 Sep 2026 00:00:00 GMThttps://m4t.tf/posts/20260921-1-failing-cheaply/https://m4t.tf/posts/20260921-1-failing-cheaply/Ordering your checks by how expensive it is to ignore them.Mon, 21 Sep 2026 00:00:00 GMT