What is a Claude Code mod?

Since version 2.1.287, a mod is a Claude Code plugin with JavaScript or TypeScript handlers that run inside Claude Code. Unlike a settings hook or a status line script, a mod can draw panes beside the transcript and bands above the prompt, add buttons and toasts, restyle the spinner and tool rows, and hold, rewrite or answer a tool call. Mods work in the CLI, the Code tab of the desktop app and the VS Code extension.

How do I install a Claude Code mod?

A mod installs like any plugin. Inside Claude Code, add its marketplace with /plugin marketplace add owner/repo, then run /plugin install name@marketplace. To try one without installing it, clone the repo and start Claude Code with --plugin-dir pointing at the mod folder. Every mod page here has the exact commands.

What else is in this directory?

Every other way people customise Claude Code: status line scripts, settings hooks, custom slash commands, output styles, themes, plugin marketplaces and workflow kits, plus the apps people run it with, such as GUIs and mobile clients, usage and cost trackers, session browsers, model routers, multi-agent and worktree runners and editor integrations. Skills and MCP servers have their own directories.

What does a mod's reach mean?

Reach is the widest thing a mod's code asks Claude Code to do, from a static scan of its source: L0 only draws and remembers, L1 reads files or settings, L2 writes files, runs processes or drives Claude, and L3 reaches the network. It is a footprint, not a verdict: a pull request tracker has to run git. A mod runs with your permissions, so read its code before you install it.

How is popularity measured?

By the GitHub stars of each repo, with forks, curated awesome lists and listing in Anthropic's plugin directory as smaller signals. When one repo holds many mods they share its stars, so only its first few rank high. The data refreshes every day.

Are Claude Code mods safe?

Mods, hooks, status lines and most tools run on your machine with your permissions, so treat them like any code from the internet: check a mod's reach, read the code before installing, prefer well-starred and recently updated repos, and check the license. Run claude plugin validate on a clone to list what a mod hooks and calls without running it, and start Claude Code with --safe-mode to turn every customization off for a session.

Claude Code Mods: 8,000+ Status Lines, Hooks, Plugins & Tools

7,353 mods that are real Claude Code mods

agent-state

kleinheinczg/claude-code-agent-state-mod

Reports what a Claude Code session is really doing (idle / working / tool / permission, plus signals and token use) from inside the session, as a JSON snapshot and a JSONL event log

Guard & safety mods/plugin install

agent-state

M-i-k-e-l/agent-state

Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle and in a Sessions pane in the desktop app.

Guard & safety mods/plugin install

agent-taskboard

YohanGarcia/agent-taskboard

A live task board for Claude Code: plans before building and shows every task, its status, time, subagents and checks in a side panel. Progress survives sessions.

agent-state

agent-state

agent-taskboard

agent-tasks

agent-theater

agent-theater

agent-todos

agent-toolkit

agent-trace

agent-tree

agent-tree

agent-tree

agent-tree

agent-watch

agent-watch

agent-watch

agent-watch

agent-workshop

agentctl

agentes-pixel

agents-office

agents-pane

agents-panel

agile-mods

agmsg-inbox

ai-link

ai-usage-band

aidiff-gate

airlock

ajan-panosu

al-syntax

ale

allan

altshift

alvearium

ambient

anchor

android-emulator

anime-cheer

anime-dancer

anki

annotate

answer

answers

anymodel

apercu

apex-thunder

api-cost-compare