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

@plaited/agent-eval-harness

v1.0.0

Published

General-purpose eval harness for running trials against CLI agents

Readme

@plaited/agent-eval-harness

npm version CI License: ISC

General-purpose eval harness for CLI agents with one entrypoint:

agent-eval-harness eval '<json>'

Usage policy

  • Use skills to generate and operate eval suites that call this CLI.
  • Use skills to generate adapters for those suites.
  • Do not hand-code eval orchestration outside the skill workflows.
  • Use skills/trial-runner, skills/trial-adapters, and skills/compare-trials as canonical workflows.
  • .agents/skills/* paths are compatibility symlinks to the root skills/ directory.

Modes

  • run: run one adapter command over tasks JSONL and stream raw trial_result rows (JSONL).
  • grade: consume raw/graded trial_result rows and stream normalized graded rows (JSONL).
  • compare: compare two graded JSONL files and emit one bounded JSON report, including per-task exactPassAtK.
  • calibrate: sample graded rows for review and emit one bounded JSON packet.

Canonical pipeline

agent-eval-harness eval '{"mode":"run",...}' > raw.jsonl
agent-eval-harness eval '{"mode":"grade",...}' < raw.jsonl > graded.jsonl
agent-eval-harness eval '{"mode":"compare",...}'
agent-eval-harness eval '{"mode":"calibrate",...}'

Schema discovery

agent-eval-harness eval --schema input
agent-eval-harness eval --schema output
agent-eval-harness eval --schema run-input
agent-eval-harness eval --schema grade-input
agent-eval-harness eval --schema compare-input
agent-eval-harness eval --schema calibrate-input
agent-eval-harness eval --schema trial-row
agent-eval-harness eval --schema task
agent-eval-harness eval --schema adapter-input
agent-eval-harness eval --schema adapter-output
agent-eval-harness eval --schema grader-input
agent-eval-harness eval --schema grader-output

Streaming behavior

  • run and grade write compact JSONL to stdout only.
  • Routine progress logs go to stderr (disable with quiet: true).
  • Trial/grader failures are encoded in rows, not treated as CLI failure.

CLI exit codes

  • 0: successful command execution and valid output emission.
  • 2: usage/schema/input errors.
  • 1: internal/runtime harness failure.

Development

bun install
bun run check
bun test src/