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

@contextium-staging/cli

v0.6.7

Published

Command-line tool for managing Contextium documentation, agents, skills, and workflows — pipe context to AI coding assistants

Readme

Contextium CLI

Command-line interface for Contextium that allows developers to fetch and pipe documentation to external AI tools.

Installation

# Build the CLI
npm run build

# Link for local development
npm link

Setup

1. Initialize a Project

# Navigate to your project directory
cd /path/to/your/project

# Initialize Contextium with your workspace and project
contextium init \
  --api-key YOUR_API_KEY \
  --workspace your-workspace-slug \
  --project your-project-slug \
  --api-url http://localhost:3001/api/v1

# Or use environment variable for API key
export CONTEXTIUM_API_KEY=your_api_key
contextium init --workspace your-workspace-slug --project your-project-slug

This creates:

  • .contextiumrc - Configuration file
  • .contextium-cache/ - Local cache directory
  • Updates .gitignore to exclude cache directory

2. Sync Files

Download all project files to local cache:

# Sync all files
contextium sync

# Sync specific files
contextium sync README.md API_GUIDE.md

# Sync files with specific tags
contextium sync --tag foundation-context --tag always-include

# Force re-download all files
contextium sync --force

# Dry run to see what would be synced
contextium sync --dry-run

Usage

Check Status

Check which files are cached and up-to-date:

contextium status

Output:

Project: My Project
Project ID: abc-123
Workspace: my-workspace

✓ README.md v3 (up to date)
↓ API_GUIDE.md v2 (v5 available, 3 versions behind)
? SETUP.md (not cached)

2 file(s) need update - run 'contextium sync'
1 file(s) not cached - run 'contextium sync'

Output File Content

Output file content to stdout for piping to AI tools:

# Output all files
contextium cat --all

# Output specific files
contextium cat README.md API_GUIDE.md

# Output files with specific tags
contextium cat --tag always-include

# Include metadata headers
contextium cat --all --with-meta

# Output as JSON
contextium cat --all --format json

Pipe to External AI Tools

The primary use case - pipe documentation to AI tools like Cursor, Claude, or Copilot:

# Pipe all documentation to clipboard
contextium cat --all | pbcopy

# Pipe to Cursor
contextium cat --all | cursor --add-context

# Pipe foundation docs to Claude
contextium cat --tag foundation-context | claude --context

# Pipe specific files
contextium cat README.md API_GUIDE.md | cursor --add-context

Search Files

Search for files in your project:

# Search by filename or content
contextium search "authentication"

# Search with tag filter
contextium search "api" --tag backend

# Limit results
contextium search "guide" --limit 5

Configuration

The .contextiumrc file contains your project configuration:

{
  "api_key": "your-api-key",
  "api_url": "http://localhost:3001/api/v1",
  "project_id": "project-uuid",
  "workspace": "workspace-slug",
  "cache": {
    "enabled": true,
    "ttl": 3600,
    "directory": ".contextium-cache",
    "max_size_mb": 100
  },
  "sync": {
    "auto": true,
    "on_command": ["build", "test"],
    "notify_changes": true,
    "interval": 300
  },
  "files": {
    "include": [],
    "exclude": ["DEPRECATED_*.md", "DRAFT_*.md"],
    "tags": ["foundation-context", "always-include"],
    "auto_include_tags": true
  }
}

Workflow Example

# 1. Initialize in your project
cd ~/projects/my-app
contextium init --workspace my-company --project my-app

# 2. Sync all documentation
contextium sync

# 3. Start coding with AI assistance
# Pipe all relevant docs to your AI tool
contextium cat --tag always-include | cursor --add-context

# 4. Update when docs change
contextium status  # Check for updates
contextium sync    # Download latest versions

Cache Management

The CLI caches files locally for faster access:

  • Cache directory: .contextium-cache/
  • TTL: 1 hour (configurable)
  • Auto-syncs based on configuration
  • Use --no-cache flag to bypass cache

Development

# Build
npm run build

# Watch mode
npm run dev

# Type check
npm run type-check

Architecture

The CLI is designed to be a lightweight bridge between your Contextium documentation repository and external AI coding tools:

Your Project
    ↓
Contextium CLI (fetch docs)
    ↓
Local Cache (.contextium-cache/)
    ↓
Pipe to AI Tool (Cursor, Claude, Copilot)
    ↓
AI-assisted Development

For more information, see the Platform Specification.