# ClaudeMods

> Tested Claude Code mods, each installed in one command. Unofficial, not affiliated with Anthropic.

- Website: https://claudemods.app
- AZN8 listing: https://azn8.com/listing/claudemods
- Pricing: Free
- Categories: [Developer tools](https://azn8.com/category/developer-tools), [AI](https://azn8.com/category/ai), [Productivity](https://azn8.com/category/productivity)
- Listed: 2026-10-13
- Updated: 2026-10-13
- JSON: https://azn8.com/api/v1/listings/claudemods

## About

ClaudeMods (claudemods.app) is an unofficial, independent directory of tested mods for Claude Code, run by developers who use Claude Code every day. Mods are plugins that change how Claude Code looks and behaves while you work. A mod is a hooks module inside an ordinary Claude Code plugin: it listens to events such as tool.call, turn.complete or ui.render, and can draw a line above the prompt, write to the status line, show a toast, add a slash command or refuse a dangerous shell command before it runs. Mods arrived in Claude Code 2.1.287 and run in the terminal and in the desktop app's Code tab.

What sets ClaudeMods apart is testing. Before a mod page goes live, the mod must pass claude plugin validate, its tests must pass with claude plugin test, and the team installs it from a marketplace and records it running in a real terminal session on a current Claude Code build (2.1.291 at the time of writing). The recording on each page is that real run, not a mock-up, and every page states the Claude Code version and date of the last test. When a new Claude Code release breaks something a mod depends on, the mod is re-tested and marked as broken until it works again.

Every mod page also carries permission badges, such as Runs commands, Reads files, Writes files, Intercepts tool calls, Reads your prompts, Calls the model or Changes the UI. The badges are generated from the validation output, from the events a mod handles and the API calls it makes, not from the author's README. A Permissions & safety section explains in plain words why the mod needs each permission, so you can see whether a mod runs commands, reads files, uses the network or calls the model before you install it.

Installing takes one command. Each page shows an install block generated from the same marketplace manifest Claude Code reads, for example /plugin install cm-git-branch --marketplace rotbit/claudemods-marketplace inside a session, or claude plugin marketplace add plus claude plugin install from your shell. Because mods are plugins, you manage them from the /plugin menu you already know: disable one, change its options in /config or uninstall it. claude --safe-mode starts a session with every mod off.

The directory is organised into categories: slash commands, Git & GitHub, toasts & notifications, panes & dashboards, timers, todos and standups, safety guards, status line & prompt bar, tools you add to Claude, and context, quota and cost. Examples include Block Dangerous Commands, which refuses rm -rf /, force-push to main, DROP TABLE and curl | sh; Context Meter, which shows context-window fill, 5-hour and 7-day plan usage and session cost; Secret Redactor, which swaps API keys, emails and public IPs for placeholders before Claude sees them; Blast Radius; Agent Radar; md-preview; Next Steps; and Git Branch Above Prompt.

Mods written by ClaudeMods are MIT-licensed and published on GitHub; community mods are listed with credit to their authors and a link to their repository. Developers who built a mod others would use can submit it, and the team will test it, record a demo and list it. Beginner guides explain what Claude Code mods are and how to install them. The site needs no account and is available in English, Chinese, Japanese, Korean, German, Spanish and Portuguese. ClaudeMods is not affiliated with or endorsed by Anthropic.

Unofficial, not affiliated with Anthropic.

[Visit website](https://claudemods.app)