When I stumble upon an unsolved or undocumented problem and solve it, I like to document it here.
Agents need credentials all the time, and when one needs a key, it asks me to paste it into chat. Anything pasted into chat is sent to the model provider and saved in the session log, and I don't want API keys in either place. creel is a
Every machine I set up used to be an imperative pile: a dotfiles repo with an install script, a list of brew install commands, and a few curl | sh lines that had accreted. The trouble with a pile of steps is that it only tells you what to do, never
I have written a lot of posts about individual pieces of how I work, like the terminal, the multi-repo workspaces, the coordination bus, and the harness that drives the model. What I never had was one place that put them together, so when someone asked how I actually work,
When I added OAuth to the MixCraft MCP server, the identity provider was Clerk, and Clerk did the whole job: it was the OAuth authorization server the MCP client talked to, it signed in the user, and it issued the tokens the MCP server verified. The next remote MCP server
The first consumer of my runner-set library — a CDK construct that runs GitHub Actions jobs on Lambda MicroVMs — was another of my own repos, and the migration was done by an AI agent. The Claude session that moved its nine CI jobs onto the runners filed a field report,
I've written about this setup twice: Building my Terminal Setup covered the shell, fonts, and Ghostty, and A tmux Workspace Built Around the Claude Code Autopilot covered the project launcher, worktrees, and per-project tmux servers. Since then the right side of every workspace grew a three-pane
This blog federates over ActivityPub through Ghost so Mastodon users can follow @index@subaud.io. standard.site is the counterpart for the AT Protocol side: a set of lexicons that describe a blog as records in an atproto repo, the same identity and data layer behind a Bluesky account. Anything
A deploy in one of my CDK projects passed every gate I have — CI, cdk synth, code review — and merged. The CloudFormation stack deployment to AWS failed with: InvalidRequest: Unzipped size must be smaller than 262144000 bytes 262,144,000 bytes is 250 MiB, AWS's hard limit on
The last two posts here were about the skills in this plugin — one learns my writing voice from my published posts, the other revises a draft section by section. Neither can do anything without a way to reach Ghost: to read what I've already posted, create a draft,
Fixing a draft used to mean regenerating the whole post. When a section didn't sound right, the new version would correct it and overwrite three others that were already fine, so I kept a corrected copy open in the Ghost editor, regenerated, and pasted the good paragraphs back