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

@sentiosurge/agent-creator

v1.0.1

Published

Scaffold AI agent definition files from a name and natural language prompt

Readme

@sentiosurge/agent-creator

Scaffold AI agent definition files from a name and natural language prompt. Compatible with Claude Code, OpenClaw, and the open AGENTS.md standard.

Install

npm install -g @sentiosurge/agent-creator

Usage

# Short prompt — inline
agent-creator -n "news-briefer" -p "Daily morning tech news briefing via Telegram"

# Long prompt — from file
agent-creator -n "news-briefer" --prompt-file ./my-idea.txt

# Long prompt — piped via stdin
cat my-idea.txt | agent-creator -n "news-briefer"

# Custom output directory
agent-creator -n "news-briefer" -p "..." -o ./my-agents

# Split format (SOUL.md + IDENTITY.md + AGENTS.md)
agent-creator -n "news-briefer" -p "..." -f split

Options

| Flag | Short | Description | Default | |------|-------|-------------|---------| | --name <name> | -n | Agent name (slug or display name) | required | | --prompt <text> | -p | Short inline prompt | — | | --prompt-file <path> | | Read prompt from a file | — | | --output-dir <dir> | -o | Parent directory for agent folders | ./agents | | --format <fmt> | -f | unified or split | unified | | --help | -h | Show help | — |

Output Formats

Unified (default)

Creates a single agent.md with YAML frontmatter + Markdown body:

agents/news-briefer/
  agent.md
---
name: news-briefer
display_name: "News Briefer"
description: "AI agent: News Briefer"
emoji: "🤖"
model: gpt-5-mini
skills: []
---

# Soul

## Role
...

## Personality
...

## Principles
...

## Boundaries
...

# Instructions
...

Split (OpenClaw-compatible)

Creates three separate files:

agents/news-briefer/
  SOUL.md        # Personality, principles, boundaries
  IDENTITY.md    # Name, emoji, vibe
  AGENTS.md      # Operational instructions, model, skills

JSON Output

The CLI outputs structured JSON for programmatic use:

{
  "status": "ok",
  "agent_name": "news-briefer",
  "display_name": "News Briefer",
  "format": "unified",
  "directory": "/path/to/agents/news-briefer",
  "files": ["/path/to/agents/news-briefer/agent.md"],
  "prompt": "Daily morning tech news briefing via Telegram",
  "next_step": "Edit agent.md to fill in soul, skills, and instructions."
}

As a Skill

This package also works as a skill for AI coding assistants. The SKILL.md file provides a 5-step workflow for AI agents to decompose natural language descriptions into complete agent definitions:

  1. Understand the request
  2. Decompose into identity, soul, capabilities, operations
  3. Scaffold directory structure
  4. Generate file contents
  5. Review with user

Cross-Platform Compatibility

| Platform | How to use | |----------|-----------| | Claude Code | Copy frontmatter fields to .claude/agents/name.md | | OpenClaw | Use --format split for SOUL.md + IDENTITY.md + AGENTS.md | | Generic | Frontmatter is valid YAML; body is standard Markdown |

License

MIT