Find plugins

by Philip Wilson

Hand-drawn input for Claude. A persistent canvas you open on any device, so Claude can ask you to sketch an idea or annotate a screenshot and get the answer back as an image.

by Bellwether AI

Guards a Claude subscription against pay-as-you-go extra-usage credits. Watches the 5-hour and 7-day plan windows, tells Claude to wind down and checkpoint at 85%, and hard-denies tool calls at 97% (git commit and memory writes stay allowed). Status line shows live usage. Fails open but loud if Claude Code's usage cache changes shape.

by Jarrod Watts

Real-time statusline HUD for Claude Code - context health, tool activity, agent tracking, and todo progress

by Chris Sparks

A repeatable, context-durable workflow for Claude Code and Codex: capture fast, defer by default, drain automatically, and preserve working state across compaction.

by Lenivvenil

Core of the claude-mini harness: Conventional Commits check on git commit, read-only critics (adversarial, security, ADR), plan / ADR / Codex second-opinion skills. Enable per project (project or local scope), never at user scope.

by Evan Scott

macOS notifications for Claude Code, tuned for Ghostty + Zellij

by Mattia Pispisa

EXPERIMENTAL, personal use: agent-tree orchestration for Claude Code — explorer/worker/researcher subagents, driven by a single /orchestrate command.

by Diego Zuluaga

Qualify good agent usage and compare approaches on a cost-per-successful-outcome basis (tokens, time, prompts).

by 1TommyCheung

Capture complete Claude Code projects and natively resume restored sessions.

by Raghu Betina

Review working changes, branches, commits, ranges, or repositories with Claude from Codex.

by Durun

Claude が走って柱を跳び越える。/claude-run で始める。1 で跳ぶ、2 でもう一度、3 でやめる。

by lucasschirm

Sync Claude Code session data to S3-compatible storage.

by TheFunnyMan120

Sets up, audits, and improves Claude Code for any project: learns the codebase and (with permission) past sessions, scores CLAUDE.md, hooks, permissions, skills, agents and MCP config, then fixes it or builds a tailored setup from scratch. Adds a cross-project global mode and an opt-in learning hook that turns your corrections into setup suggestions.

by Danylo Vorvul

Replaces the spinner with an animated ASCII slot machine: pull the lever on every prompt, watch the reels spin while Claude works, cash in when the turn completes.

by Eric Altenburg

Session memory for Claude Code: records each session, distils idle ones into dated facts, and searches them and your prompt history with toc-search.

by Samuel Daigle

General-purpose tools and skills for Claude Code

by David Allada

Export Claude Code transcripts out of dev containers and analyze hook fire rates, CLAUDE.md adherence and tool-use patterns.

by Hermes Labs

Blocks permanent-delete shell commands in Claude Code and redirects agents to a recoverable trash workflow.

by Bryan Chan

Point-and-comment real-time feedback for Claude Code agents. Wraps an MCP server, slash commands, an auto-approve hook, and a live review surface (markdown + widget) in one plugin.

by Alex

A role-shaped subagent fleet: eleven agents, the skills they preload, the hooks that keep the board honest, the board itself, and the workflows that organise multi-phase work.

by Ariful

Shows your daily and weekly Claude usage percentages on the Claude Code status line, on the row above the mode indicator.

by Argeu Thiesen

O mascote do Claude Code vivo na sua mesa: um ESP32 com display que reage ao que o Claude está fazendo e mostra o uso do plano. Sem servidor e sem token da Anthropic.

by libf-de

Flags overly verbose comments / JSDoc-TSDoc in TS/JS files using a configurable comment-to-subject length ratio, plus opt-in structural checks, and pushes back to Claude to fix them.

by therahul-yo

Clawdman: a small orange mascot who walks on dotted ground above the prompt box with its idle animations, sits at a desktop while Claude works and cheers when a turn ends. /clawdman turns it on or off.