A Claude Code plugin with skills for auditing a whole repo, reviewing a change, listing deferred shortcut comments, and showing measured savings and a quick command reference.
+7,244this week
179.6k stars in total10 hooks
Trending
Trending hooks for Claude Code
92 plugins that ship hooks, ranked by GitHub stars gained in 7 days, as of . Together they ship 576 hooks.
A skill that shapes Claude Code's output for readers with ADHD: it leads with the next action, numbers multi-step work, restates state across turns, drops tangents, gives specific time estimates, and makes progress visible. Invoke it with /i-h.
+1,065this week
59.3k stars in total1 hook
Keeps large command outputs, logs and data files out of your AI assistant's context by running processing in a sandbox and returning only the relevant parts. You also get a searchable index of local files and diagnostics for checking the setup.
+1,044this week
32.8k stars in total6 hooks
Lets Claude watch a video from a URL or local file by pulling timestamped frames and a transcript. Works in Claude Code, and the watch skill downloads with yt-dlp and extracts frames with ffmpeg.
+458this week
19.5k stars in total1 hook
Hooks and skills that stop an AI coding agent from adding unrequested hashes, checksums, or extra scope to a task. Built for Codex and GPT workflows across several platforms.
+346this week
3.3k stars in total8 hooks
Skills for working with Worktrunk, a CLI for Git worktree management. Covers creating and switching worktrees, hooks and config, CLI output standards, and the release and CI workflows for the project.
+173this week
9.6k stars in total3 hooks
Lets Claude Code control a running Unreal Editor over MCP, covering actors, blueprints, materials, Niagara, Sequencer, widgets and more. Includes skills for building Unreal toolsets and Agent Skills.
+153this week
1.7k stars in total1 hook
Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the savings. It also tracks costs, helps resume prior sessions, and offers a usage dashboard.
+149this week
2.8k stars in total11 hooks
Edits CapCut and JianYing video projects from the terminal or an LLM agent, covering subtitles, timing, speed, volume, templates, animations, and cutting long videos into shorts. The result opens in CapCut with every track still editable.
+123this week
1.1k stars in total1 hook
Draw and edit draw.io diagrams by chatting with an AI. Describe a diagram in a sentence and the AI draws it on a real draw.io canvas. Edit it by hand like any draw.io file, or select a few shapes and tell the AI what to change.
+122this week
36.5k stars in total7 hooks
A pre-execution guard that blocks destructive Git and file system commands, and common attempts to read sensitive files, before a tool call runs. Works with several AI coding agents, including Claude Code.
+104this week
1.8k stars in total1 hook
Local-first memory for Claude Code. It stores conversations verbatim in a private palace you can search before answering about past work, people, projects, or decisions, with optional shared-brain hub setup.
+83this week
59.8k stars in total4 hooks
A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents, so you don't have to.
+67this week
6.6k stars in total103 hooks
A Claude Code skill that researches what Chinese internet users said recently across Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu and Toutiao. It ranks posts by engagement and recency and writes a sourced research report.
+55this week
2.0k stars in total1 hook
A self-learning system for Claude Code that captures your corrections during sessions and reminds you to run /reflect to save them to CLAUDE.md as permanent memory. It also discovers recurring workflow patterns.
+49this week
1.9k stars in total4 hooks
A shadcn/ui registry of animated React components with a shared motion system, including a hover highlight that glides between items. Useful for building interactive frontend interfaces.
+40this week
1.1k stars in total4 hooks
Cuts AI coding agent token costs through terse prose, YAGNI-first code style, and compressed tool output. Adds audit, review, and a terse dev mode for Claude Code and other agents.
+29this week
725 stars in total8 hooks
Gives a marketing team an AI staff for planning and running campaigns across SEO, content, paid ads, email, influencer work and product launches. Each area comes with ready-made commands that work on data you supply.
+28this week
3.0k stars in total7 hooks
A lightweight code search engine that uses AST-based semantic search with local embeddings and incremental indexing. It helps Claude Code users find code faster and more efficiently.
+18this week
3.0k stars in total2 hooks
Writ turns supported workflow requirements into executable checks and acceptance gates for Claude Code, instead of relying on the model to follow written instructions.
+13this week
243 stars in total12 hooks
Your coding agents outgrew your terminal. CCC puts every session on one local board and tells you which one needs you. Not affiliated with Anthropic. Start the next while Claude builds the first. A real share card from one of the maintainer's machines.
+12this week
212 stars in total12 hooks
Skills for Databricks development covering the Python SDK, Databricks Connect, CLI and REST API, plus Python coding guidance on code quality, error handling, testing and environment management.
+11this week
2.0k stars in total1 hook
A real-time dashboard for watching Claude Code and Codex agent sessions, with filtering, search, session replay and token usage stats. Includes an observe skill for managing the dashboard and its server.
+10this week
712 stars in total28 hooks
Gives AI coding agents access to Shopify's developer documentation, API schemas, and code validation for building apps and themes, plus store management through the Shopify CLI. Also includes a skill for finding and buying products from UCP merchants.
+9this week
618 stars in total2 hooks
Orchestrates multiple Claude Code agents across terminals and machines, giving them persistent memory and agent-to-agent messaging so you no longer have to relay messages between them by hand.
+8this week
839 stars in total31 hooks
Reduces context and token usage when Claude Code reads, searches, or edits files, using cached file reads and a shared local knowledge graph. Useful when large files are re-read or the context window is filling up.
+8this week
563 stars in total4 hooks
Gives you one window to watch every AI coding agent on your machine, with live cost and token counts, a log of tool calls, and a hold on risky actions until you approve them. It also lets an agent drive a browser already signed in to your project's sites.
+8this week
345 stars in total8 hooks
A memory layer that lets AI agents read and write an agent-owned second brain in an Obsidian vault. It works through MCP servers, lifecycle hooks and a command-line tool, and includes skills for recording preferences and setting up semantic search.
+7this week
499 stars in total9 hooks
A command line tool for HEY that lets you read and send email, manage contacts, labels, calendars, todos, habits, time tracking and journal entries from the terminal or from your coding agent.
+7this week
421 stars in total1 hook
Detects AI-writing patterns in prose files your agent saves, and includes a skill that helps humanize text and remove AI-sounding phrasing. Runs locally using only the Python standard library, with no network access or model.
+7this week
410 stars in total7 hooks
Opinionated Claude Code defaults and workflows from Trail of Bits, covering sandboxing, permissions, hooks, MCP servers, and usage patterns for security audits, development, and research.
+6this week
2.1k stars in total2 hooks
Probity forces AI coding agents to follow your rules. It hooks into your agent and checks every file write and shell command before it happens. When an action breaks a rule, Probity blocks it and tells the agent why.
+6this week
238 stars in total1 hook
claude-carbon: track the carbon footprint of your Claude Code sessions.
+6this week
231 stars in total4 hooks
Scrapes tracked competitor accounts on X, Instagram, TikTok and YouTube, scores what is performing well, and turns it into a daily feed of content ideas framed against your own brand.
+6this week
147 stars in total1 hook
A plugin that adds skills for running Claude Code reviews of local git changes, delegating tasks to Claude Code, and tracking, cancelling, or retrieving background jobs in a repository.
+5this week
230 stars in total4 hooks
Offline security scanner that audits git repos, AI skills, plugins, MCP servers, and agent credentials for prompt injection, credential theft, and known vulnerabilities. Runs as a skill and as pre-tool-use hooks.
+5this week
199 stars in total3 hooks
An MCP server for code navigation, change-impact analysis, and framework-aware queries, with skills for safe refactoring, bulk codemods, and pre-commit security and quality checks in Claude Code.
+5this week
198 stars in total14 hooks
Checks the shell commands, URL fetches and file writes an AI coding assistant is about to run, and blocks dangerous ones such as reverse shells, command injection and risky credential or supply chain actions before they execute.
+4this week
322 stars in total3 hooks
Your coding agent starts every session blank. It doesn't know what you worked on yesterday, what conventions your team follows, or what mistakes it already made. You re-explain everything, every time. Claude Remember fixes that.
+4this week
205 stars in total4 hooks
Rewrites AI-written text so it reads more like a human wrote it, removing stock phrases, sycophancy, and hedging while keeping code, URLs, and headings intact. Covers commit messages, memory files, code reviews, and reasoning traces.
+4this week
165 stars in total9 hooks
Lets Claude create and update Linear issues, check project status and manage team workflows, so you can handle tracker work from your coding session instead of switching to the Linear app. It works through Linear's MCP tools, SDK and GraphQL API.
+4this week
139 stars in total1 hook
Claudable is an open-source web app builder that uses local CLI agents such as Claude Code, Codex and Gemini CLI to generate, preview and deploy projects from natural language prompts.
+3this week
4.1k stars in total3 hooks
Vestige is a fail-closed runtime firewall for AI agents. The model proposes, a deterministic gate decides, and every action leaves a receipt. When something breaks, causal_walk finds the real cause.
+3this week
658 stars in total12 hooks
Gives you a guide to setting up Claude Code, covering global instructions, MCP servers, custom commands, hooks and skills, plus tools for generating commit messages and auditing code for security issues. This version is marked obsolete, with a newer starter kit recommended instead.
+3this week
558 stars in total5 hooks
Helps hardware teams turn product requirements into a reviewable, buildable PCB design plan. Covers embedded architecture, MCU or SoC selection, power tree, interfaces, sensors, connectivity, and BOM risk.
+3this week
394 stars in total1 hook
A local-first dashboard for monitoring Claude Code sessions, with usage analytics, token and cost tracking, and a skill to link a session to a Linear, Jira, GitHub Issues, or GitHub Pull Request ticket.
+3this week
337 stars in total7 hooks
Tracks what a Claude Code session costs and where the tokens go, and offers tools to cut that spend, such as a usage board, a CLAUDE.md audit, and a handoff to a fresh chat. Useful for anyone whose long sessions burn through usage limits quickly.
+3this week
125 stars in total6 hooks
Enriches vague prompts for Claude Code with targeted research and clarifying questions before execution. It injects relevant context at prompt submit, tool use, and subagent start so Claude has what it needs before acting.
+2this week
2.0k stars in total3 hooks
An MCP server that lets AI assistants control a web browser for automation and browsing tasks. Installs as a plugin with a browser-use skill.
+2this week
972 stars in total1 hook
Sends desktop alerts with sounds and webhooks when Claude Code needs your attention or reaches a milestone during long-running work. Clicking a notification brings the matching window back into focus, on macOS, Linux, and Windows.
+2this week
820 stars in total5 hooks
Gives Claude Code durable memory across sessions so you do not have to re-explain your project each time. Runs entirely offline, with no data sent to external services.
+2this week
764 stars in total3 hooks
Turns a single line of story text into a finished short drama, covering the script, storyboards, character-consistent video and voiceover. Works with the AI model providers you already use, so you skip assembling each step by hand.
+2this week
703 stars in total11 hooks
Real-time usage monitor for Claude Code, session limits, weekly limits, and plan tier with colour-coded progress bars.
+2this week
467 stars in total1 hook
Helps Claude Code users find, compare, audit, and install reusable agent skills before an agent acts. Activates when a user asks for a skill, plugin, or a tool for a task.
+2this week
365 stars in total2 hooks
Gives Claude Code persistent memory across conversations, with local embeddings, semantic search and a knowledge graph. It runs offline as a single binary, with no cloud service or API keys needed.
+2this week
316 stars in total6 hooks
Lets your AI coding agent find code by meaning instead of reading whole files, so it spends fewer tokens and finishes sessions faster. It runs fully locally on your machine with open-source embedding models, with no API keys or cloud service needed.
+2this week
313 stars in total2 hooks
+2this week
234 stars in total2 hooks
Source version: 1.7.2. See release notes and Production-oriented ROS 2 engineering guidance for coding agents, with focused references, static validators, regression tests, and multi-distribution CI.
+2this week
229 stars in total2 hooks
MCP server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.
+2this week
191 stars in total5 hooks
Records your screen while you perform a repetitive task once, then has Claude Code automate that task for you from the recording.
+2this week
64 stars in total1 hook
Let your Claude Code message you on Telegram when it needs decisions or finishes work, even when you’re away from your desk. Claude Code → Agent Reachout → Telegram → Human reply → Agent continues.
+2this week
58 stars in total2 hooks
A Claude Code plugin for full-stack development, offering modes for building, fixing, reviewing and deploying code, plus layered security hooks and token budget monitoring to manage context use.
+2this week
45 stars in total33 hooks
Lets Claude Code call your phone when a task finishes, gets stuck, or needs a decision, so you can start a task and step away. Works with a phone or watch.
+1this week
2.6k stars in total1 hook
Understand any code, not just accept it. A code learning & audit framework for Claude Code that turns any codebase, new, legacy, or AI-generated, into educational deep dives or senior-level architectural audits.
+1this week
1.1k stars in total2 hooks
Adds drag-and-drop, sortable lists and grids, and drop zones to React Native apps with react-native-reanimated-dnd. The skill covers its components, hooks, and configuration options.
+1this week
1.1k stars in total10 hooks
A skill that guides developers in building modern, accessible, and composable UI components. It covers composable APIs, design tokens, and publishing components to npm.
+1this week
802 stars in total1 hook
Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.
+1this week
581 stars in total3 hooks
Taskmaster is a completion guard for coding agents. It addresses a common failure mode: the agent makes partial progress, writes a summary, and stops before the user goal is actually finished.
+1this week
532 stars in total2 hooks
Semantic search over past Claude Code conversations, so a session can recall earlier discussions, decisions, and patterns. It adds a remembering-conversations skill that checks prior sessions before the assistant says it doesn't know.
+1this week
493 stars in total1 hook
Reduces AI context cost for coding agents by compressing context in a way that can be reversed, with byte-exact recovery and an auditable receipt for each reduction. Runs locally and works through a proxy, MCP server, SDK, or agent wrapper.
+1this week
480 stars in total1 hook
Turns design docs and plan drafts into HTML pages you can comment on inline. Fires when you ask to review a design, preview a plan, or render visual output.
+1this week
301 stars in total1 hook
Lets you manage Basecamp projects, todos, cards, messages, files and schedules from your terminal or from Claude Code, so you stop switching to the web app for routine updates.
+1this week
294 stars in total4 hooks
Plugin for Claude Code that turns project ideas into task graphs. Adds skills to brainstorm a brief, decompose features and oversized tasks, and run a project review, backed by an MCP server and a composer agent.
+1this week
197 stars in total8 hooks
Stop fixing the same AI mistake twice. A Lean quality system for AI-assisted work, operators turn recurring defects into countermeasures. Built by a manufacturing operator, for people who actually ship.
+1this week
168 stars in total3 hooks
Helps Claude Code users stretch their Max-plan usage limits by slimming context, filtering noisy tool output, compacting CLAUDE.md, and guarding against retry loops and drift.
+1this week
132 stars in total5 hooks
A fully local agentic coding plugin that intercepts plan mode and opens an annotation UI in your browser. Mark up the plan, send structured feedback to the agent, and receive a revised version, iterate as many times as you need until you're ready to approve.
+1this week
99 stars in total3 hooks
Tracks your AI usage, lines of code generated, and time spent prompting Claude Code, sending the data to WakaTime for metrics and time tracking.
+1this week
98 stars in total6 hooks
A Claude Code plugin for autonomous development. It creates structured TDD implementation plans, then runs them with parallel workers, and includes project setup and config sync skills.
+1this week
82 stars in total3 hooks
claude-mem-lite is a persistent memory (also called long-term memory or cross-session context) system for Claude Code, Anthropic's CLI coding agent.
+1this week
68 stars in total7 hooks
Lints and scores the setup files of AI coding agents such as CLAUDE.md and AGENTS.md, checks supply chain risks, and analyzes session logs. Works with Claude Code, Codex, and Cursor.
+1this week
61 stars in total1 hook
Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
+1this week
54 stars in total8 hooks
Creates presentations from ideas, outlines, or existing decks, offering both editable PowerPoint (.pptx) slides and animated browser-based HTML slides. Built for Claude Code users who need slide decks.
+1this week
42 stars in total2 hooks
Compound V is a Claude Code plugin for planning and building features with multiple AI models. You describe a feature, and Claude sizes it, splits it into non-overlapping pieces, and hands each to a worker in its own isolated worktree. It also includes skills for PR review and promo clips.
+1this week
42 stars in total5 hooks
A Claude Code plugin where Fable has the lead as orchestrator, keeping the main judgment while tiered subagents on Opus, Sonnet and Haiku do the work. Once installed, new sessions in every repo start this way.
+1this week
29 stars in total3 hooks
Logs Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, and adds skills to trace, evaluate, diagnose and compare AI applications. Built by Comet.
+1this week
24 stars in total8 hooks
grounded-copy makes your agent state the fact and get to the point, in chat replies and in the documents it writes. A separate mode covers product pages and marketing copy.
+1this week
23 stars in total7 hooks
A Claude Code plugin that acts as a conversational UX designer, guiding discovery, auditing designs against UX rules, showing a live preview, and exporting components.
+1this week
21 stars in total1 hook
Gearbox is a Claude Code plugin that automatically routes subagent delegations to the cheapest model tier that can handle the work, haiku for search and mechanical edits, sonnet for standard implementation, opus for hard architectural problems.
+1this week
17 stars in total4 hooks
Monitors Claude Code context usage and, when a session nears its limit, writes a handoff summary so work can resume in a fresh session. Adds a statusline indicator and commands to configure the trigger threshold and summary length.
+1this week
15 stars in total2 hooks
A Claude Code plugin that runs feature work in phases, with separate skills for writing acceptance criteria, reviewing design, writing failing tests first, implementing the minimum code, and verifying the result end to end. Aimed at developers who want a structured test-driven workflow.
+1this week
14 stars in total7 hooks
Four-layer long-term memory (L0 Conversation → L1 Atom → L2 Scene → L3 Persona) for Claude Code, inspired by Tencent/TencentDB-Agent-Memory. Fully local, no external Gateway, no paid API, no Python.
+1this week
12 stars in total5 hooks
Archives every Claude Code session locally in a searchable SQLite store and saves durable facts into persistent memory. Adds skills to flush and review memory at session start or before clearing a conversation.
+1this week
5 stars in total5 hooks
Nothing in this list is paid.