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

@promptwheel/logbook-mcp

v0.4.0

Published

MCP server for @promptwheel/logbook — git history as agent memory for MCP clients (Claude Desktop, Cursor, and any shell-less agent).

Readme

@promptwheel/logbook-mcp

@promptwheel/logbook over MCP — git history as agent memory, for clients without a shell (Claude Desktop, Cursor, and any MCP client).

Tools

  • logbook_digest — the history digest: hotspots, do-not-retry reverts, suppression ledger, fragile areas, notable events, per-file history.
  • logbook_audit — what is STILL suppressed in HEAD and since when (blame-dated), with re-silencing fight logs.
  • logbook_query — precision filters over the full commit-event record (file / revert / suppress / weaken / downgrade / grep / since / until).
  • logbook_context — the same filtered order in deterministic pages capped at 20 events and 8 KiB. Follow its opaque NEXT cursor until END complete; it compacts delivery but does not rank relevance. Cursors reject changed HEADs, filters, analysis windows, or event order instead of silently drifting.
  • logbook_annotate — persist WHY a commit happened (lazy enrichment): when the agent investigates a revert or suppression, the finding is kept — sha-keyed, attributed, dated — and merged into future digests as "why (inferred)" lines instead of being re-derived every session.

Setup

Claude Desktop (JSON config):

{
  "mcpServers": {
    "logbook": { "command": "npx", "args": ["-y", "@promptwheel/logbook-mcp"] }
  }
}

Codex CLI (TOML — ~/.codex/config.toml, or per-project .codex/config.toml):

[mcp_servers.logbook]
command = "npx"
args = ["-y", "@promptwheel/logbook-mcp"]

or the one-liner: codex mcp add logbook -- npx -y @promptwheel/logbook-mcp. Exposing tools is not the same as using them — keep an AGENTS.md line telling the agent when to call logbook_digest.

Performance

Three cache layers: session memo per HEAD (repeat calls: 4ms), disk reuse of events.jsonl with incremental append (0.4s on the 20k-commit repo we measured — the ledger must exist, i.e. a CLI run wrote it; the MCP server itself keeps its cache in memory and does not write events.jsonl), and windowed cold builds that emit MCP progress notifications. Clients can opt in to resetting their timeout on progress (the official TypeScript SDK uses resetTimeoutOnProgress: true); without that opt-in, a cold build on a large repo can still hit the client's timeout — run the CLI once to create the ledger if that bites. Zero network calls; the analysis is git, running locally.

MIT. The logbook records; the referee judges.