• Hard guardrails in Pi: intercept, block, and steer

    Working on a small project, trying to implement skills into an agent that does not support skills, made me realize (again) that using skills to set guardrails depends a lot on the model you're using and is non-deterministic almost by design because of the way they are implemented…

  • Pi's session branching as an alternative to sub-agents

    Most coding agents rely on sub-agents to manage complex workflows. Pi's session branching offers a different way to handle multiple lines of work in a single session, with deliberate control over context and state. This short post explains my main insight into Pi's session manage…

  • Adding `plan mode` to Pi while prioritising portability

    This article shows how I added plan mode to Pi using artefacts that stay as reusable as possible across other coding agents. Pi lacks a first-class plan mode. If you want one, you have to build it yourself, use an extension, or adapt Pi's example. I have a fairly low threshold fo…

  • Jujutsu Footer Extension for Pi Coding Agent

    I put together a Jujutsu footer extension for the Pi Coding Agent that appends jj commit context to assistant responses. If you use jj and Pi, you might find it useful. Full details: jj-footer-extension.md.

  • agentfiles, dotfiles but for agents

    Sometimes I want to refer to my agents setup or people ask me what my configuration looks like. For general system configuration dotfiles are used so I am going to share my agent configuration in what I'll just call "agentfiles". I do have a private dotfiles repository but I am n…