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

pi-super-dev

v0.1.2

Published

Self-contained, modular development pipeline for the Pi coding agent, built on a composable control-flow node algebra (branch/parallel/loop/retry/gate/map/wait). Spawns specialist pi subagents directly — no external workflow engine required.

Readme

pi-super-dev

A self-contained, modular development pipeline for the Pi coding agent, built on a composable control-flow node algebra (branch / parallel / loop / retry / gate / map / wait).

Runs the 13-stage super-dev workflow — requirements → BDD → research → [debug] → assessment → design → [prototype] → spec → spec-review → TDD implementation → parallel code review → docs → cleanup → merge — by spawning 21 specialist pi subagents directly. No dependency on @agwab/pi-workflow or any other external workflow engine.

Install

pi install npm:pi-super-dev
# or try it without installing:
pi -e npm:pi-super-dev
# or, from a local checkout:
pi -e /path/to/pi-super-dev

Use

# From the pi TUI:
/super-dev implement user authentication with OAuth2

# Or directly via the tool call the agent will make:
super_dev({ task: "fix the crash on large file upload" })

Tool options: skipWorktree, skipStages, model, maxAgents.

Architecture

extension.ts  ──►  registers  super_dev tool + /super-dev command
      │
      ▼
pipeline.ts / workflow.ts  ──►  runs a tree of Nodes
      │
      ▼
stages/index.ts            ──►  the pipeline expressed with control nodes
      │
      ├─ nodes.ts        the control-flow algebra
      ├─ helpers.ts      12 deterministic helpers (classify, gates, routing)
      ├─ prompts.ts      prompt builders for every specialist
      ├─ agents.ts       loads agents/<name>.md (21 specialists)
      ├─ pi-spawn.ts     spawns `pi` subprocesses (self-contained)
      └─ control.ts      tolerant <control> JSON extractor

Control-flow node algebra (src/nodes.ts)

| Node | Purpose | |-----------------------------------|--------------------------------------------------------------------| | task(stage) | Leaf — runs a Stage, stores return value at state[stage.id] | | sequence([...], {tolerant?}) | Ordered composition — fail-fast by default, tolerant continues | | branch(pred, {yes, no?}) | Conditional — take one path or skip | | choose([{when, run}, ...]) | Multi-way switch — first matching case | | parallel([...], {into?, join?}) | Fork-join — run branches concurrently, merge results | | loop({while?, until?, times?}) | Iterate a body until a condition holds | | retry({attempts, backoff?}) | Re-run a node on failure (AWS Step Functions "Retry" semantics) | | gate({validate, attempts}) | Write → validate → re-write (quality-gate loop for LLM outputs) | | map({over, as, concurrency?}) | Fan out a body over a collection | | wait(ms) / waitForEvent(name) | Time or event synchronization | | tryCatch(body, {catch, finally})| Error boundary (catches thrown fatal-task errors) | | noop() | Identity |

Grounded in AWS Step Functions ASL, the Workflow Control Patterns taxonomy (van der Aalst), Temporal workflows, and LangGraph.

The pipeline (src/stages/index.ts)

sequence([
  task(setupStage),                                // fatal
  task(classifyStage),
  gate({ validate: gateValidator(...), attempts: 3 }, task(requirementsWriter)),
  gate({ validate: gateValidator(...), attempts: 3 }, task(bddWriter)),
  gate({ validate: researchComplete, attempts: 3 }, task(researchWriter)),
  branch(isBug, { yes: task(debugWriter) }),
  task(assessmentWriter),
  task(designStage),
  task(prototypeStage),
  gate({ validate: gateValidator(...), attempts: 3 }, task(specWriter)),
  gate({ validate: gateValidator(...), attempts: 3 }, task(specReviewWriter)),
  task(implementationStage),                       // per-phase TDD loop
  loop({ until: reviewApproved, times: 3 },
    sequence([
      parallel([codeReview, adversarialReview], { into: "review", join: mergeVerdicts }),
      branch(reviewApproved, { no: reviewFix }),
    ])),
  task(docsWriter),
  task(cleanupTask),
  branch(notBlocked, { yes: task(mergeWriter) }),
], { tolerant: true })

Customize

Compose your own pipeline by importing the node builders:

import { runWorkflow, sequence, task, gate, gateValidator, /* ... */ } from "pi-super-dev/pipeline";
import { requirementsWriter, specWriter, implementationStage } from "pi-super-dev/stages";

const custom = {
  id: "quick",
  root: sequence([
    gate({ validate: gateValidator("gate-requirements", "write-requirements", "requirements"), attempts: 2 },
         task(requirementsWriter)),
    task(specWriter),
    task(implementationStage),
  ]),
};

await runWorkflow(custom, "add a health endpoint", { cwd: process.cwd() });

Testing

npm run typecheck   # tsc --noEmit
npm test            # vitest — LLM-free unit tests

The test suite is fully hermetic (no pi spawns, no network): control-flow algebra semantics, deterministic helpers, control-JSON parsing, workflow composition integrity, package structure.

License

MIT