{
  "title": "Baking Easy-Blog Oven v2.0 with DecafClaw",
  "date": "2026-11-17T12:00:00Z",
  "slug": "baking-easy-blog-oven-v2-0-with-decafclaw",
  "type": "entry",
  "tags": [
    "blogging",
    "golang",
    "decafclaw",
    "projects",
    "webdev",
    "easy-blog-oven"
  ],
  "thumbnail": "/2026/11/17/baking-easy-blog-oven-v2-0-with-decafclaw/yasin-onus-w-Ep34orfoA-unsplash-dithered.png",
  "summary": "TL;DR: After six years of brooding and Dependabot alert fatigue, I finally rebuilt my blog's static site generator in Go. Easy-Blog Oven v2.0 renders twenty-four years of Markdown into HTML in under three seconds, ditches node_modules entirely, and was built in an afternoon of flow pair-programming with DecafClaw, my homemade agent.",
  "draft": false,
  "comments_archived": false,
  "year": "2026",
  "month": "11",
  "day": "17",
  "postName": "2026-11-17-baking-easy-blog-oven-v2-0-with-decafclaw",
  "isDir": true,
  "path": "2026/11/17/baking-easy-blog-oven-v2-0-with-decafclaw",
  "body": "\n**TL;DR**: After six years of brooding and Dependabot alert fatigue, I finally rebuilt my blog's static site generator in Go. Easy-Blog Oven v2.0 renders twenty-four years of Markdown into HTML in under three seconds, ditches `node_modules` entirely, and was built in an afternoon of flow pair-programming with DecafClaw, my homemade agent.\n\n\u003c!--more--\u003e\n\n\u003cfigure class=\"wide\"\u003e\n\n![Bread baking inside a glowing wood-fired stone oven](./yasin-onus-w-Ep34orfoA-unsplash-dithered.png)\n\n\u003cfigcaption\u003ePhoto by \u003ca href=\"https://unsplash.com/@yasinonus?utm_source=unsplash\u0026utm_medium=referral\u0026utm_content=creditCopyText\"\u003eYasin Onuş\u003c/a\u003e on \u003ca href=\"https://unsplash.com/photos/bread-baking-in-a-stone-oven-w-Ep34orfoA?utm_source=unsplash\u0026utm_medium=referral\u0026utm_content=creditCopyText\"\u003eUnsplash\u003c/a\u003e\u003c/figcaption\u003e\n\n\u003c/figure\u003e\n\n\u003cnav role=\"navigation\" class=\"table-of-contents\"\u003e\u003c/nav\u003e\n\n*This is Part 2 of a two-part retrospective. In [Part 1: Twenty-Four Years of Blog Engines](/2026/11/17/twenty-four-years-of-blog-engines/), I took a visual tour of nearly a quarter-century of personal publishing across Movable Type, Blosxom, WordPress, and Jekyll.*\n\n## The Six-Year Itch\n\nIn [May 2020](/2020/05/24/easy-blog-oven/), I cobbled together my own custom Node.js static site generator called the [Easy-Blog Oven](/2020/05/25/diy-easy-blog-oven/). It wasn't an off-the-shelf framework like Hugo or 11ty; it was just a few hundred lines of JavaScript gluing together `marked`, `cheerio`, and ES6 template literals. I guess it was kind of a pandemic project? Anyway, it worked. It carried my blog for six years, through lots of posts, redesigns, and format experiments. \n\nBut over time, the JavaScript ecosystem tax accumulated. Every time I wanted to tweak a template or run a build on a new machine, I was greeted by the familiar modern npm friction: dozens of transitive packages in `node_modules`, deprecation warnings, and an endless barrage of Dependabot security alerts (88 vulnerabilities at last count!). \n\nFurthermore, churning through twenty-four years of archive—over 1,400 posts dating back to February 2002—took around 7 to 8 seconds. That's not terrible, but it's just slow enough that local watch mode felt sluggish. And I know computers can be faster than that, these days.\n\nI've been brooding over rewriting it for a while. Back in [October 2022](/2022/10/28/twitter/), I joked about whether I felt like rewriting my build system yet again. Then in [October 2025](/2025/10/25/miscellanea/), while hacking on Go utilities like [feedspool-go](https://github.com/lmorchard/feedspool-go), I dropped an ominous note:\n\n\u003e *I'm also really appreciating the built-in stuff like text/template, to the point that I'm now even eyeing up my Easy-Blog Oven and considering rewriting my blog's static site generator, currently implemented in node.js. (uh oh)*\n\nToday, I finally pulled the trigger. Meet **Easy-Blog Oven v2.0**.\n\n## Why Go? (And Why Not Rust?)\n\nThe immediate spark for this rewrite came on a whim while watching a YouTube video: [\"Why Everyone's Rewriting Everything in Rust\"](https://www.youtube.com/watch?v=iu_ALBDtoHo). Every programmer knows the itch—you watch twenty minutes of praise for memory safety and zero-cost abstractions, glance over at your aging Node.js build scripts, and think: *I should rewrite this in Rust tonight.* \n\n(Insert Boat Cat meme here.)\n\nI actually pitched the Rust rewrite to DecafClaw at the start of a session as a sanity check. Like, what if we did it? Joking but, maybe not, if you're into it? The agent pushed back and talked me down from the ledge—but then it offered to one-shot the whole thing in go since [I'd just built a static site generator for linkding](/2026/11/01/linkding-ssg/) and that was fresh in memory. \n\nAs I kept chatting, it sounded almost too easy a transition:\n\n1. **`goquery` is basically `cheerio` for Go:** A massive chunk of my blog's post-processing involves parsing rendered Markdown, manipulating HTML nodes (extracting first headings, rewriting internal `#hashtag` links, adjusting image attributes, and styling code blocks). In Rust, mutating DOM trees across arbitrary node references is notoriously awkward. In Go, `goquery` let me port my existing DOM transforms almost 1:1.\n\n2. **Instant compilation:** `go build` runs in the blink of an eye. There's zero compilation drag during development. Node gave me that, but not so much in Rust.\n\n3. **The joy of the single binary:** One compiled binary with zero runtime dependencies. No Node runtime to install, no `npm install`, no virtualenvs, no shared libraries. Rust gave me that, but not so much in Node.\n\nSo, I said, go ahead. Let's try it. And away we went, more comprehensively and faster than I expected. I think I spent more time badgering the agent to build QA tools to compare old vs new builds to be sure nothing broke, than the build of the port took altogether.\n\n## What v2.0 Buys Me\n\nThe results of the rewrite were immediately gratifying:\n\n- **Speed:** All 1,414 historical posts (2002 to 2026) parse from Markdown in **1.35 seconds**. A full production build—generating thousands of HTML pages, 720 category/tag indexes, full-text RSS (`index.rss`), excerpt RSS (`index-excerpts.rss`), XML sitemaps, and JSON-LD structured data graphs—clocks in at **~2.5 seconds**.\n\n- **Zero `node_modules` churn:** I deleted `package.json`, `package-lock.json`, and `node_modules/` in one clean commit. 88 Dependabot alerts evaporated instantly.\n\n- **Embedded templates with disk fallbacks:** Using Go's `//go:embed`, the binary packages all default HTML templates internally. But it also supports an \"eject\" pattern (similar to what I did with [linkding-ssg](https://github.com/lmorchard/linkding-ssg)): if a template file exists in `./templates/` on disk, it overrides the embedded default.\n\n- **In-memory live reload:** For local writing, `make dev` starts a dev server on port 9980 with file watching via `fsnotify`. When a post or CSS file changes, it rebuilds in memory and broadcasts an event over Server-Sent Events (SSE). Middleware injects the tiny client reload script into HTML responses on the fly, so disk build artifacts never get polluted with dev code.\n\n- **Built-in retro dithering:** I ported my Floyd-Steinberg image dithering and pixel-downscaling pipeline directly into pure Go (`pkg/imageutil`). No ImageMagick CLI invocations needed.\n\n- **Fixed client-side search:** Along the way, I squashed a stubborn [Pagefind](https://pagefind.app/) bug where every search result title was showing up as `\"blog.lmorchard.com\"` (Pagefind was greedily grabbing the masthead `\u003ch1\u003e` before checking the post title) and gave the search drawer an opaque background and wider reading column.\n\n## The DecafClaw Flow\n\nSo yeah, I built the entire v2.0 in a single afternoon pairing with [**DecafClaw**](https://github.com/lmorchard/decafclaw), my personal AI agent project. \n\nDecafClaw is very young—I only started it this spring, writing up the origin story in [Decafclaw: Building an AI Agent in a Week](/2026/03/20/decafclaw/). What began as a 50-line Python script to understand how LLM tool calling and agent loops work has turned into my daily development companion: an agent wired directly into my local workspace and shell, with tools to read, edit, test, benchmark, and deploy.\n\nWhat made this session feel like genuine flow was the division of labor:\n\n- **Easy Blog Oven v1.0 as a spec:** This didn't start from scratch. The agent could pour over my original working code and transliterate the important stuff into the new system. So, unlike other rewrites of the past in which I've taken part, this one seemed to pick up all the dumb quirks I've accumulated in the thing whether I remembered them or not. (And this thing is quirky as heck.)\n\n- **High-level steering \u0026 instincts:** I made the architecture calls—Go over Rust, standard library `html/template` over custom template engines, keeping the eject pattern, choosing to retire old archive pages in favor of Pagefind search, and branding it as Easy-Blog Oven v2.0.\n\n- **Plumbing \u0026 muscle work:** DecafClaw handled the tedium. It parsed legacy edge cases across 24 years of posts (Disqus comment dumps, multipart cut-line delimiters, Obsidian image embeds), set up concurrent worker pools, scaffolded unit tests, verified build parity against the old generator, updated GitHub Actions workflows, and cleaned up phantom draft files.\n\n- **Immediate tooling:** When I found myself writing one-off Node scripts to verify Pagefind search results or checking frontmatter with Python, DecafClaw baked those directly into the CLI as first-class subcommands (`easy-blog-oven search-test`, `doctor`, and `info`).\n\nThis was like having a tireless [helper gnome](https://github.com/mokagnome) who understands the repo context, doesn't mind writing boilerplate, and can verify its own edits with test runs. It made a rewrite feel fun, if you can believe it. I stayed in the \"what if\" and problem-solving zones instead of drowning in setup ceremony.\n\n## What's Next?\n\nWith Easy-Blog Oven v2.0 running live in production (deployed to S3 and CloudFront via GitHub Actions), the publishing core is faster and simpler than it has been in a decade.\n\nNext on the docket: I've finally disabled the crusty cron job that used to automatically sync draft notes from my Obsidian vault into the blog repo. That was part of [the Rube Goldberg blogging machine](/2025/06/02/obsidian-rube-goldberg/) I rigged up [back in May 2025](/2025/05/09/new-blog-a-lot-like-the-old/). That seemed really neat to me at the time, and I used it a ton at first, then I dropped it for other shiny toys.\n\nI'll rethink that pipeline with an intentional, agent-mediated import command so half-baked thoughts stay in the notebook until they're ready for the oven.\n\nUntil then, the oven is preheated, the build is fast, and it feels good to have a simple, dependable tool back at the heart of the site.\n",
  "html": "\u003cp\u003e\u003cstrong\u003eTL;DR\u003c/strong\u003e: After six years of brooding and Dependabot alert fatigue, I finally rebuilt my blog\u0026#39;s static site generator in Go. Easy-Blog Oven v2.0 renders twenty-four years of Markdown into HTML in under three seconds, ditches \u003ccode\u003enode_modules\u003c/code\u003e entirely, and was built in an afternoon of flow pair-programming with DecafClaw, my homemade agent.\u003c/p\u003e\n\u003c!--more--\u003e\n\u003cfigure class=\"wide\"\u003e\n\u003cp\u003e\u003cimg src=\"./yasin-onus-w-Ep34orfoA-unsplash-dithered.png\" alt=\"Bread baking inside a glowing wood-fired stone oven\"/\u003e\u003c/p\u003e\n\u003cfigcaption\u003ePhoto by \u003ca href=\"https://unsplash.com/@yasinonus?utm_source=unsplash\u0026amp;utm_medium=referral\u0026amp;utm_content=creditCopyText\"\u003eYasin Onuş\u003c/a\u003e on \u003ca href=\"https://unsplash.com/photos/bread-baking-in-a-stone-oven-w-Ep34orfoA?utm_source=unsplash\u0026amp;utm_medium=referral\u0026amp;utm_content=creditCopyText\"\u003eUnsplash\u003c/a\u003e\u003c/figcaption\u003e\n\u003c/figure\u003e\n\u003cnav role=\"navigation\" class=\"table-of-contents\"\u003e\u003c/nav\u003e\n\u003cp\u003e\u003cem\u003eThis is Part 2 of a two-part retrospective. In \u003ca href=\"/2026/11/17/twenty-four-years-of-blog-engines/\"\u003ePart 1: Twenty-Four Years of Blog Engines\u003c/a\u003e, I took a visual tour of nearly a quarter-century of personal publishing across Movable Type, Blosxom, WordPress, and Jekyll.\u003c/em\u003e\u003c/p\u003e\n\u003ch2 id=\"the-six-year-itch\"\u003eThe Six-Year Itch\u003c/h2\u003e\n\u003cp\u003eIn \u003ca href=\"/2020/05/24/easy-blog-oven/\"\u003eMay 2020\u003c/a\u003e, I cobbled together my own custom Node.js static site generator called the \u003ca href=\"/2020/05/25/diy-easy-blog-oven/\"\u003eEasy-Blog Oven\u003c/a\u003e. It wasn\u0026#39;t an off-the-shelf framework like Hugo or 11ty; it was just a few hundred lines of JavaScript gluing together \u003ccode\u003emarked\u003c/code\u003e, \u003ccode\u003echeerio\u003c/code\u003e, and ES6 template literals. I guess it was kind of a pandemic project? Anyway, it worked. It carried my blog for six years, through lots of posts, redesigns, and format experiments.\u003c/p\u003e\n\u003cp\u003eBut over time, the JavaScript ecosystem tax accumulated. Every time I wanted to tweak a template or run a build on a new machine, I was greeted by the familiar modern npm friction: dozens of transitive packages in \u003ccode\u003enode_modules\u003c/code\u003e, deprecation warnings, and an endless barrage of Dependabot security alerts (88 vulnerabilities at last count!).\u003c/p\u003e\n\u003cp\u003eFurthermore, churning through twenty-four years of archive—over 1,400 posts dating back to February 2002—took around 7 to 8 seconds. That\u0026#39;s not terrible, but it\u0026#39;s just slow enough that local watch mode felt sluggish. And I know computers can be faster than that, these days.\u003c/p\u003e\n\u003cp\u003eI\u0026#39;ve been brooding over rewriting it for a while. Back in \u003ca href=\"/2022/10/28/twitter/\"\u003eOctober 2022\u003c/a\u003e, I joked about whether I felt like rewriting my build system yet again. Then in \u003ca href=\"/2025/10/25/miscellanea/\"\u003eOctober 2025\u003c/a\u003e, while hacking on Go utilities like \u003ca href=\"https://github.com/lmorchard/feedspool-go\"\u003efeedspool-go\u003c/a\u003e, I dropped an ominous note:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u003cem\u003eI\u0026#39;m also really appreciating the built-in stuff like text/template, to the point that I\u0026#39;m now even eyeing up my Easy-Blog Oven and considering rewriting my blog\u0026#39;s static site generator, currently implemented in node.js. (uh oh)\u003c/em\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eToday, I finally pulled the trigger. Meet \u003cstrong\u003eEasy-Blog Oven v2.0\u003c/strong\u003e.\u003c/p\u003e\n\u003ch2 id=\"why-go-and-why-not-rust\"\u003eWhy Go? (And Why Not Rust?)\u003c/h2\u003e\n\u003cp\u003eThe immediate spark for this rewrite came on a whim while watching a YouTube video: \u003ca href=\"https://www.youtube.com/watch?v=iu_ALBDtoHo\"\u003e\u0026#34;Why Everyone\u0026#39;s Rewriting Everything in Rust\u0026#34;\u003c/a\u003e. Every programmer knows the itch—you watch twenty minutes of praise for memory safety and zero-cost abstractions, glance over at your aging Node.js build scripts, and think: \u003cem\u003eI should rewrite this in Rust tonight.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e(Insert Boat Cat meme here.)\u003c/p\u003e\n\u003cp\u003eI actually pitched the Rust rewrite to DecafClaw at the start of a session as a sanity check. Like, what if we did it? Joking but, maybe not, if you\u0026#39;re into it? The agent pushed back and talked me down from the ledge—but then it offered to one-shot the whole thing in go since \u003ca href=\"/2026/11/01/linkding-ssg/\"\u003eI\u0026#39;d just built a static site generator for linkding\u003c/a\u003e and that was fresh in memory.\u003c/p\u003e\n\u003cp\u003eAs I kept chatting, it sounded almost too easy a transition:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ccode\u003egoquery\u003c/code\u003e is basically \u003ccode\u003echeerio\u003c/code\u003e for Go:\u003c/strong\u003e A massive chunk of my blog\u0026#39;s post-processing involves parsing rendered Markdown, manipulating HTML nodes (extracting first headings, rewriting internal \u003ccode\u003e#hashtag\u003c/code\u003e links, adjusting image attributes, and styling code blocks). In Rust, mutating DOM trees across arbitrary node references is notoriously awkward. In Go, \u003ccode\u003egoquery\u003c/code\u003e let me port my existing DOM transforms almost 1:1.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eInstant compilation:\u003c/strong\u003e \u003ccode\u003ego build\u003c/code\u003e runs in the blink of an eye. There\u0026#39;s zero compilation drag during development. Node gave me that, but not so much in Rust.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eThe joy of the single binary:\u003c/strong\u003e One compiled binary with zero runtime dependencies. No Node runtime to install, no \u003ccode\u003enpm install\u003c/code\u003e, no virtualenvs, no shared libraries. Rust gave me that, but not so much in Node.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eSo, I said, go ahead. Let\u0026#39;s try it. And away we went, more comprehensively and faster than I expected. I think I spent more time badgering the agent to build QA tools to compare old vs new builds to be sure nothing broke, than the build of the port took altogether.\u003c/p\u003e\n\u003ch2 id=\"what-v20-buys-me\"\u003eWhat v2.0 Buys Me\u003c/h2\u003e\n\u003cp\u003eThe results of the rewrite were immediately gratifying:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eSpeed:\u003c/strong\u003e All 1,414 historical posts (2002 to 2026) parse from Markdown in \u003cstrong\u003e1.35 seconds\u003c/strong\u003e. A full production build—generating thousands of HTML pages, 720 category/tag indexes, full-text RSS (\u003ccode\u003eindex.rss\u003c/code\u003e), excerpt RSS (\u003ccode\u003eindex-excerpts.rss\u003c/code\u003e), XML sitemaps, and JSON-LD structured data graphs—clocks in at \u003cstrong\u003e~2.5 seconds\u003c/strong\u003e.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eZero \u003ccode\u003enode_modules\u003c/code\u003e churn:\u003c/strong\u003e I deleted \u003ccode\u003epackage.json\u003c/code\u003e, \u003ccode\u003epackage-lock.json\u003c/code\u003e, and \u003ccode\u003enode_modules/\u003c/code\u003e in one clean commit. 88 Dependabot alerts evaporated instantly.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eEmbedded templates with disk fallbacks:\u003c/strong\u003e Using Go\u0026#39;s \u003ccode\u003e//go:embed\u003c/code\u003e, the binary packages all default HTML templates internally. But it also supports an \u0026#34;eject\u0026#34; pattern (similar to what I did with \u003ca href=\"https://github.com/lmorchard/linkding-ssg\"\u003elinkding-ssg\u003c/a\u003e): if a template file exists in \u003ccode\u003e./templates/\u003c/code\u003e on disk, it overrides the embedded default.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eIn-memory live reload:\u003c/strong\u003e For local writing, \u003ccode\u003emake dev\u003c/code\u003e starts a dev server on port 9980 with file watching via \u003ccode\u003efsnotify\u003c/code\u003e. When a post or CSS file changes, it rebuilds in memory and broadcasts an event over Server-Sent Events (SSE). Middleware injects the tiny client reload script into HTML responses on the fly, so disk build artifacts never get polluted with dev code.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eBuilt-in retro dithering:\u003c/strong\u003e I ported my Floyd-Steinberg image dithering and pixel-downscaling pipeline directly into pure Go (\u003ccode\u003epkg/imageutil\u003c/code\u003e). No ImageMagick CLI invocations needed.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eFixed client-side search:\u003c/strong\u003e Along the way, I squashed a stubborn \u003ca href=\"https://pagefind.app/\"\u003ePagefind\u003c/a\u003e bug where every search result title was showing up as \u003ccode\u003e\u0026#34;blog.lmorchard.com\u0026#34;\u003c/code\u003e (Pagefind was greedily grabbing the masthead \u003ccode\u003e\u0026lt;h1\u0026gt;\u003c/code\u003e before checking the post title) and gave the search drawer an opaque background and wider reading column.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2 id=\"the-decafclaw-flow\"\u003eThe DecafClaw Flow\u003c/h2\u003e\n\u003cp\u003eSo yeah, I built the entire v2.0 in a single afternoon pairing with \u003ca href=\"https://github.com/lmorchard/decafclaw\"\u003e\u003cstrong\u003eDecafClaw\u003c/strong\u003e\u003c/a\u003e, my personal AI agent project.\u003c/p\u003e\n\u003cp\u003eDecafClaw is very young—I only started it this spring, writing up the origin story in \u003ca href=\"/2026/03/20/decafclaw/\"\u003eDecafclaw: Building an AI Agent in a Week\u003c/a\u003e. What began as a 50-line Python script to understand how LLM tool calling and agent loops work has turned into my daily development companion: an agent wired directly into my local workspace and shell, with tools to read, edit, test, benchmark, and deploy.\u003c/p\u003e\n\u003cp\u003eWhat made this session feel like genuine flow was the division of labor:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eEasy Blog Oven v1.0 as a spec:\u003c/strong\u003e This didn\u0026#39;t start from scratch. The agent could pour over my original working code and transliterate the important stuff into the new system. So, unlike other rewrites of the past in which I\u0026#39;ve taken part, this one seemed to pick up all the dumb quirks I\u0026#39;ve accumulated in the thing whether I remembered them or not. (And this thing is quirky as heck.)\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eHigh-level steering \u0026amp; instincts:\u003c/strong\u003e I made the architecture calls—Go over Rust, standard library \u003ccode\u003ehtml/template\u003c/code\u003e over custom template engines, keeping the eject pattern, choosing to retire old archive pages in favor of Pagefind search, and branding it as Easy-Blog Oven v2.0.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003ePlumbing \u0026amp; muscle work:\u003c/strong\u003e DecafClaw handled the tedium. It parsed legacy edge cases across 24 years of posts (Disqus comment dumps, multipart cut-line delimiters, Obsidian image embeds), set up concurrent worker pools, scaffolded unit tests, verified build parity against the old generator, updated GitHub Actions workflows, and cleaned up phantom draft files.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eImmediate tooling:\u003c/strong\u003e When I found myself writing one-off Node scripts to verify Pagefind search results or checking frontmatter with Python, DecafClaw baked those directly into the CLI as first-class subcommands (\u003ccode\u003eeasy-blog-oven search-test\u003c/code\u003e, \u003ccode\u003edoctor\u003c/code\u003e, and \u003ccode\u003einfo\u003c/code\u003e).\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThis was like having a tireless \u003ca href=\"https://github.com/mokagnome\"\u003ehelper gnome\u003c/a\u003e who understands the repo context, doesn\u0026#39;t mind writing boilerplate, and can verify its own edits with test runs. It made a rewrite feel fun, if you can believe it. I stayed in the \u0026#34;what if\u0026#34; and problem-solving zones instead of drowning in setup ceremony.\u003c/p\u003e\n\u003ch2 id=\"whats-next\"\u003eWhat\u0026#39;s Next?\u003c/h2\u003e\n\u003cp\u003eWith Easy-Blog Oven v2.0 running live in production (deployed to S3 and CloudFront via GitHub Actions), the publishing core is faster and simpler than it has been in a decade.\u003c/p\u003e\n\u003cp\u003eNext on the docket: I\u0026#39;ve finally disabled the crusty cron job that used to automatically sync draft notes from my Obsidian vault into the blog repo. That was part of \u003ca href=\"/2025/06/02/obsidian-rube-goldberg/\"\u003ethe Rube Goldberg blogging machine\u003c/a\u003e I rigged up \u003ca href=\"/2025/05/09/new-blog-a-lot-like-the-old/\"\u003eback in May 2025\u003c/a\u003e. That seemed really neat to me at the time, and I used it a ton at first, then I dropped it for other shiny toys.\u003c/p\u003e\n\u003cp\u003eI\u0026#39;ll rethink that pipeline with an intentional, agent-mediated import command so half-baked thoughts stay in the notebook until they\u0026#39;re ready for the oven.\u003c/p\u003e\n\u003cp\u003eUntil then, the oven is preheated, the build is fast, and it feels good to have a simple, dependable tool back at the heart of the site.\u003c/p\u003e\n",
  "sourceFile": "content/posts/2026/2026-11-17-baking-easy-blog-oven-v2-0-with-decafclaw/index.md",
  "parentPath": "content/posts/2026/2026-11-17-baking-easy-blog-oven-v2-0-with-decafclaw",
  "attachments": [
    "./yasin-onus-w-Ep34orfoA-unsplash-dithered.png"
  ],
  "prevPostPath": "2026/11/17/twenty-four-years-of-blog-engines",
  "prevPostTitle": "Twenty-Four Years of Blog Engines"
}