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

@beach-ai/ghiak-agents

v0.2.4

Published

5 AI agents (Spec Author / Test Gen / Coder / Reviewer / Curator) for GHIaK Agentic — collaboration layer on GitHub Issues.

Readme

agents/ — Agentic runtime workspace

5 agent (Spec Author / Test Gen / Coder / Reviewer / Curator) chia sẻ _shared/ (env, logger, claude-client, mcp-tools).

Run modes

| Mode | GHIAK_STUB | Behavior | |---|---|---| | Stub (default for tests + smoke) | 1 | mcp-tools.ts returns fixture JSON. Anthropic client = scripted in run.ts. No network. | | Real | 0 | mcp-tools.ts → real MCP Worker fetch. Anthropic client = live API. |

Real-mode setup

Required env vars:

export GHIAK_STUB=0
export GHIAK_MCP_URL=https://ghiak-mcp.huy-tran-957.workers.dev   # deployed Worker (account subdomain)
export GHIAK_API_KEY=$(cat ~/.ghiak/key)                          # bearer token (Lead-distributed)
export ANTHROPIC_API_KEY=...                                      # team-shared
export GITHUB_TOKEN=$(gh auth token)
export GITHUB_REPOSITORY=monstar-lab-consulting/mvn-hackathon-dn-dn-beach-ghiak-agentic
export GITHUB_EVENT_NAME=issues
export GITHUB_EVENT_PATH=spec-author/test/fixtures/stub-event.json
export AGENT_NAME=spec-author

Worker URL has account subdomain huy-tran-957 (Lead's Cloudflare account). The canonical placeholder ghiak-mcp.workers.dev in execution-plan docs is a documentation shorthand — actual DNS requires the subdomain. Custom domain (e.g. mcp.ghiak.dev) planned post-Day-4.

Smoke harnesses

pnpm --filter @beach-ai/ghiak-agents smoke:stub   # offline, 15 tools fixture round-trip
pnpm --filter @beach-ai/ghiak-agents smoke:real   # live: env validate + /healthz + /mcp tools/list

smoke:real requires all env vars above. Exits non-zero on:

  • GHIAK_STUB=1 (wrong mode)
  • env schema invalid
  • /healthz ≠ 200
  • /mcp tools/list ≠ 200 (401 → bearer key hash mismatch on Worker)

Run a single agent locally

pnpm tsx spec-author/run.ts

Reads GITHUB_EVENT_PATH JSON, drives Claude agentic loop with whitelisted tools from spec-author/tools.ts. Stub mode uses scripted Claude responses (see run.ts buildStubAnthropic); real mode hits Anthropic API.

Tickets

  • T-D1.C1..C6 — workspace scaffold + _shared utilities + claude-client + 15-tool registry + system prompt
  • T-D2.C1..C7 — spec-author tools whitelist, stub-mode e2e, real MCP swap (C3), prompt v1.0, workflow YAML, manual e2e, feedback loop