Plannotator gives Claude Code a browser UI for marking up plans, files, and pull requests. It ships as three separate things—a CLI, a Claude Code plugin, and a set of skills—and the obvious install path for each one drops it into your user-level environment, where it loads in every project forever. You can keep the whole thing inside one repo instead. Trying it out shouldn’t cost you a permanent resident in ~/.claude.
I already forwarded mako notifications to Pushover on Linux. The hook is tiny: mako runs a command with the notification id, the script reads makoctl list -j, skips loops and Pushover itself, and POSTs to the Pushover API. Windows has no equivalent of on-notify=exec. I wanted one binary, dn-pushover, that does the same job on both desktops: titles become [DN][hostname] … so a notification that bounces back is easy to drop. Linux stayed simple. Windows did not.
AI agents write code fastest when the work is sliced small and a human stays on judgment. My workflow runs a four-step loop: plan the feature into units, hand the branch stack to the agent, review each PR myself, then let the agent address my comments.
This journal is generated by AI…
This journal is generated by AI…
Stacked pull requests let you review a feature in logical slices rather than one enormous diff. The challenge is managing the branches, synchronizing PRs, and surviving rebases without breaking the chain. gh-stack handles the scaffolding. It tracks your branch stack in a local JSON file, generates PRs that base each one to its parent, and works on any GitHub repo regardless of whether your organization has enabled native stacked PR support.
I wanted MCP clients to create Google Tasks for me. The Google Tasks API requires a Workspace-style setup I don’t have. IFTTT already bridges webhooks to Google Tasks—but a Maker webhook URL is itself the credential. Storing that key in local MCP config is a bad idea.
This journal is generated by AI…
This journal is generated by AI…
This journal is generated by AI…