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

jumpstart-mode

v1.1.14

Published

Spec-driven agentic engineering framework that transforms ideas into production code through AI-powered sequential phases

Readme

⚡ Jump Start

Version License Node

Jump Start is a spec-driven agentic engineering framework that turns ideas into production code through sequential, AI-guided phases.

It keeps requirements, plans, architecture, and implementation artifacts in your repository so they stay reviewable, diffable, and reusable by both humans and AI assistants.

Why Jump Start

  • Start with problem discovery before code generation.
  • Keep specs as the source of truth instead of letting implementation drift drive decisions.
  • Use explicit human gates between phases.
  • Support greenfield builds and brownfield codebase analysis.
  • Work across GitHub Copilot, Claude Code, Cursor, and Windsurf.

Quick Start

Recommended fast path:

npx jumpstart-mode quickstart

Standard interactive install:

npx jumpstart-mode

Use the quickstart wizard when you want the fastest route into the workflow. Use the standard install when you want full control over setup options such as project type, assistant integration, and the optional local copilot-observability dashboard.

Common install examples:

# Install into the current directory
npx jumpstart-mode

# Install into a specific directory with a project name
npx jumpstart-mode ./my-project --name "My Project"

# Install for an existing codebase
npx jumpstart-mode ./existing-app --type brownfield --copilot

# Include the optional local observability dashboard
npx jumpstart-mode . --copilot-observability

# Set up and launch the observability dashboard
npx jumpstart-mode . --run-copilot-observability

# Preview without writing files
npx jumpstart-mode --dry-run .

Then start from the default router:

  • In GitHub Copilot, choose Jump Start: AutoNav.
  • In command-based assistants, run /jumpstart.autonav.

If you already know the project type:

  • Greenfield projects typically route into Challenge first.
  • Brownfield projects typically route into Scout first.

Upgrade

For existing installations:

npx jumpstart-mode upgrade

Install Flags

Key installer flags:

  • --type <greenfield|brownfield> to override auto-detection.
  • --copilot to include GitHub Copilot integration files.
  • --copilot-observability to copy and set up the local observability tool.
  • --run-copilot-observability to launch the dashboard after setup.
  • --conflict merge to preserve existing AGENTS.md or CLAUDE.md content while updating Jump Start blocks.
  • --dry-run to preview changes without writing files.
  • --force to overwrite framework-owned files during installation.

If your repository already has AGENTS.md or CLAUDE.md, prefer --conflict merge over skip so assistant integration stays intact.

The bundled observability tool is local-first and optional. Setup details, privacy posture, and dashboard usage live in copilot-observability/README.md.

Workflow

flowchart LR
    A[AutoNav] --> B[Scout or Challenge]
    B --> C[Analyze]
    C --> D[Plan]
    D --> E[Architect]
    E --> F[Build]

Each phase produces repository-owned artifacts that become input to the next phase. Human approval sits between phase transitions.

Documentation Map

Getting Started

Concepts

Reference

Extending

Typical Use Cases

  • A new product or internal tool that needs disciplined requirements and architecture before implementation
  • An existing codebase that needs AI help without losing context or spec traceability
  • Teams that want AI-generated outputs to remain version-controlled and reviewable
  • Organizations that need reusable workflows across multiple assistants and projects

Package Notes

  • Package name: jumpstart-mode
  • CLI binaries: jumpstart-mode and jumpstart
  • Node requirement: >=14.0.0
  • Bundled optional tool: copilot-observability/

License

MIT License - see LICENSE for details.