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

@tisonek/agentfile

v0.1.0

Published

CLI for defining and running LLM workflows as files — for any IDE agent.

Readme

Agentfile CLI

The official CLI for the Agentfile workflow specification.

Installation

npm install -g agentfile

Commands

agentfile init

Scaffold a new Agentfile project in the current directory.

mkdir my-project && cd my-project
agentfile init --name my-project

Creates:

my-project/
  agentfile.yaml       # Project manifest
  shared/
    project.md         # Global conventions
    AGENTS.md          # Global agent rules
  workflows/           # Your workflows go here
  examples/
  .gitignore
  README.md

agentfile create <workflow-name>

Create a new workflow. If the workflow-creator meta-workflow exists and AGENT_API_KEY is set, it uses AI to generate the full workflow. Otherwise it scaffolds a blank structure.

agentfile create code-reviewer
agentfile create pr-summarizer --request "Summarize pull request diffs into structured reports"

agentfile run <workflow-name>

Run a workflow using its reference runtime scripts.

agentfile run code-reviewer --input "path/to/my-file.py"
agentfile run pr-summarizer --input "$(git diff main)"
agentfile run code-reviewer --input "src/auth.js" --shell pwsh

Options: | Flag | Description | Default | |------|-------------|---------| | --input <text> | Input text or file path | $AGENT_INPUT env var | | --key <key> | LLM API key | $AGENT_API_KEY env var | | --model <model> | Model to use | $AGENT_MODEL or claude-sonnet-4-6 | | --shell <shell> | Runtime: bash or pwsh | bash |


agentfile list

List all workflows in the current project.

agentfile list
agentfile list --examples   # include examples/ folder

agentfile validate [workflow-name]

Validate a workflow against the Agentfile spec. Checks YAML schema, agent/skill file references, script presence, and gitignore.

agentfile validate              # validate all workflows
agentfile validate code-reviewer

Environment Variables

| Variable | Description | |----------|-------------| | AGENT_API_KEY | Your LLM API key | | AGENT_INPUT | Default input for agentfile run | | AGENT_MODEL | Model override (default: claude-sonnet-4-6) |


IDE Agent Usage (no CLI needed)

If you're using an IDE agent (Cursor, Windsurf, Claude Code, Cline, etc.), you don't need the CLI — just point your agent at the workflow.yaml directly:

Load workflow.yaml and follow its steps.
Load the agent from agents/ and skills from skills/.
Input: <your input here>