Skip to content
claudemods

About ClaudeMods

Last updated 2026-10-07

ClaudeMods is an independent directory of mods for Claude Code, run by developers who use Claude Code every day. It is not affiliated with, sponsored by or endorsed by Anthropic. Claude and Claude Code are trademarks of Anthropic.

How do we test a mod?

Every mod goes through the same steps before its page is published:

  1. claude plugin validate must pass. Its output gives us the events the mod handles and the API calls it makes.
  2. The mod's tests must pass with claude plugin test.
  3. We install it from a marketplace and record it working in a real terminal session. The recording on the page is that run, not a mock-up.

Each page states the Claude Code version and date of the last test. When a new Claude Code release changes something a mod depends on, we re-test it, and mark it as broken until it works again. A page without a recording stays a draft and is not indexed.

Where do the mods come from?

Some mods are written by us. Their source is MIT-licensed and published in our GitHub repository, and they install from our marketplace. Others are community mods, which we list with credit to their authors and a link to their repository. We only redistribute a community mod when its licence allows it.

How do permission badges work?

Badges are generated from the hooks: and calls: lines of the validation output, not from a mod's README. A mod that calls $.process.run gets "Runs commands"; one that hooks tool.call gets "Intercepts tool calls"; and so on. The "Permissions & safety" section on each page explains in plain words why the mod needs each one.

Contact

Questions, corrections or removal requests: see the contact page.