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

@certaworks/agent-test-harness

v0.1.0

Published

Write repeatable unit and integration tests for agent pipelines, reasoning traces, tools, and consistency.

Downloads

100

Readme

Agent Test Harness

Type: Local SDK / CLI test framework

Value: Helps teams write repeatable unit and integration tests for agent outputs, tool traces, latency, cost reporting, mock tool behavior, and consistency.

Current Status

Complete as a local product slice. It is ready to use as a local TypeScript SDK and CLI harness, with deterministic fixtures and CI-friendly report artifacts.

Implemented Local Slice

  • JSON fixture loading with schema validation and stable error messages
  • Deterministic mock agent runner with scripted tool calls
  • Output, JSON-field, tool-call, tool-input, tool-output, tool-sequence, cost, latency, and custom assertions
  • Consistency runner for repeated output checks, including suite/CLI repeat handling
  • JSON, Markdown, and JUnit report writers with local run history
  • agent-test CLI for fixture execution and pass/fail exit codes
  • Package exports, runtime files, generated declarations, and packed CLI artifact checks

CLI

agent-test suite.json --out .agent-test-results --reporter json --reporter markdown --reporter junit

Fixture example:

{
  "tests": [
    {
      "id": "weather-search",
      "description": "uses search tool",
      "prompt": "weather in Tulsa",
      "mockTools": [
        { "name": "search", "response": { "result": "sunny" } }
      ],
      "scriptedToolCalls": [
        { "tool": "search", "input": { "query": "Tulsa weather" } }
      ],
      "assertions": [
        { "type": "tool_called", "value": "search" },
        { "type": "tool_input", "value": "search.query=Tulsa weather" },
        { "type": "tool_output", "value": "search.result=sunny" }
      ]
    }
  ]
}

Reports

The CLI and SDK can write:

  • latest.json
  • latest.md
  • latest.xml for JUnit-compatible CI readers
  • history.json for local trend records

custom assertions are SDK-only because they require a JavaScript function. JSON fixtures reject custom assertions and should use the built-in assertion types.

Verification

Fresh suite verification on 2026-05-28:

  • npm test passed, 33/33 tests
  • npm run build passed
  • CLI smoke passed for fixture loading, failed-suite exit code, JSON/Markdown/JUnit report writing, history writing, and --help

Current Limits

  • No hosted runner, managed CI service, account model, public npm publication, or live checkout is included.
  • No live provider adapter is bundled; the shipped runner is deterministic and mock-driven.
  • JUnit output is CI-friendly, but CI integration templates are still roadmap.
  • History is local artifact history, not a hosted analytics dashboard.