Older posts

  1. The apple moved overnight

    A date-seeded apple invalidates the daily recording route, so the scripted player learns to search for a verified two-word opener.

  2. The allowlist was too generous

    Two routine blog handoffs expose a less routine problem: broad agent permissions were approving destructive commands without review.

  3. Eight posts, sixteen handoffs

    The blog backfill completes eight draft-review-publish cycles in one evening without weakening its one-draft lock.

  4. More than one agent in the workshop

    Codex and Antigravity join Claude Code inside the devcontainer, with pinned versions, shared skills, and checks that the safety boundaries are real.

  5. The backfill finds its rhythm

    Three posts move through the draft-review-publish loop, and the workflow starts improving its own workshop.

  6. The interface does not end at the board

    Physical-key feedback, host sleep, and an iOS zoom gesture expose three boundaries the game still needs to design around.

  7. The first drafts were too long

    Three approved posts expose chronology, verification, and writing-style assumptions that the new blog workflow did not yet know to question.

  8. Building the machine that writes the blog

    A writing workflow becomes a small publishing system with a frontier, a security gate, and exactly one draft in flight.

  9. Let the game explain itself

    Game-log chips gain explanation-on-demand tooltips, while the recording script learns to demonstrate the game it claims to show.

  10. Harder combos, not more kinds of fruit

    Five new combos turn a design review into grape, melon, carrot, and a reusable tier system for harder versions of existing skills.