npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@alexeiled/pi-plan-exec

v0.3.0

Published

A discoverable /exec command and exec-plan skill for reliable, resumable ralphex-style plan execution in Pi

Readme

pi-plan-exec

npm version CI Release node license: MIT

Turn a Markdown execution plan into an isolated, resumable Pi run.

pi-plan-exec solves the control problem of long-running AI implementation. A capable agent can lose context, repeat work, skip verification, or start a second writer after a restart. This extension moves task order, retry limits, worktree checks, and recovery out of prompt prose into durable controller state. It has been exercised in runs lasting a few hours; the controller keeps polling instead of asking one chat prompt to remember the whole job.

It executes one checked-list task at a time in a Git checkout you choose, then runs review and fix stages with fresh Pi subagents and Fusion. A worker saying “done” is not enough: the plan’s checked items are the implementation record.

Experimental. Start with disposable repositories or reviewable worktrees.

What it does

  • Keeps one writer in one checkout. /exec always asks whether to use an isolated Git worktree or work in place. Isolated runs move the interactive Pi session into that worktree, so its tools and footer use the execution branch.
  • Executes plans deterministically. It selects the first incomplete task, starts a fresh worker, and verifies completion from the plan checkboxes.
  • Recovers deliberately. A reload reattaches a matching run owned by the returning session. /exec adopt takes over a stale cross-session run. Compare-and-set records, operation IDs, controller locks, and leases avoid intentionally starting another writer or losing a pause or cancellation.
  • Reviews before it finishes. It runs comprehensive, smells, Fusion, and critical review/fix phases. Unresolved findings remain visible in the final completed_with_findings state.

Install and run

Install the prerequisites, then plan-exec:

pi install npm:pi-subagents
pi install npm:@tintinweb/pi-tasks
pi install npm:@alexeiled/pi-subagents-bridge@^0.2.0
pi install npm:@alexeiled/pi-fusion
pi install npm:@alexeiled/pi-plan-exec

The providers remain independent Pi packages. pi-plan-exec requires Bridge 0.2.0 or later for safe operation lookup, probes Bridge and Fusion capabilities before it creates a run, and tells you how to recover if they are unavailable.

Reload Pi. From an interactive session in a Git repository, run an executable plan:

/reload
/exec help
/exec docs/plans/20260713-add-greeting.md

While it runs, Pi shows the execution-worktree path, branch, stage, and worker. /exec status only observes the run; it does not interrupt or restart it. Use it without a run ID for the current repository, and use /exec runs when several runs need disambiguation. /exec pause stops after the active child; /exec resume continues paused work or recovers a recorded failure in the same stage and preserved worktree. When a provider operation may still exist, plan-exec keeps its identity and adopts it before any retry. The installed exec-plan skill is also available as /skill:exec-plan for the plan format and recovery rules.

The Guide defines the accepted plan format, including the exact heading and checkbox rules. Omit the path to select an eligible Markdown plan below docs/plans/.

Runtime model

flowchart LR
    plan["Markdown plan"] --> controller["durable controller"]
    controller --> bridge["pi-subagents-bridge"]
    bridge --> worker["fresh worker / reviewer"]
    worker --> worktree["Git worktree"]
    worktree --> checks["plan checkboxes"]
    checks --> controller
    controller --> fusion["pi-fusion panel + judge"]
    fusion --> controller
    controller --> result["completed or completed_with_findings"]

pi-plan-exec owns plan-specific control flow. Existing Pi packages retain ownership of subagent execution, task UI, and multi-model review.

Read next

  • Guide — requirements, executable-plan format, commands, lifecycle, recovery, and safety limits.
  • Architecture — component ownership, state, RPC contracts, stages, and trust boundaries.
  • Development — local verification and release process.
  • Changelog — release history and compatibility changes.
  • Original design record — design decisions and intended behavior.

License

MIT