Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
Hooks
843 repos · Updated 22 Nov 2026, 03:30 UTC
- 1 affaan-m/ECCSkillsPlugins & marketplacesSubagents A performance optimization harness and engineering framework for Claude Code and other coding agents. It provides a structured workflow with specialized agents, skills, hooks, persistent memory, and security scanning for planning, test-driven development, code reviews, and build repairs. 308.4K+7 days: —
- 2 anthropics/claude-codeOfficialPlugins & marketplacesHooks This agentic coding tool operates in the terminal to interact with your codebase using natural language commands. It executes routine development tasks, explains complex code, and handles git workflows. Developers can run it directly in the terminal, within an IDE, or by tagging Claude on GitHub. 156.6K+7 days: —
- 3 thedotmack/claude-memSkillsPlugins & marketplacesHooks This tool provides persistent memory across sessions for coding agents such as Claude Code, Codex, and OpenCode. It uses lifecycle hooks and a background worker to record tool activity, summarize key insights into observations, and store them locally in SQLite and a vector database. Future sessions automatically receive a compact index of past context, with MCP tools available to query full details on demand. 118.9K+7 days: —
- 4 pbakaus/impeccablePlugins & marketplacesSubagentsHooks This repo provides a design vocabulary, review commands, and an automated slop detector for coding agents like Claude Code. It equips agents with commands to critique UX, audit quality, refine visuals, and test code against 62 deterministic rules directly in workflows, terminal runs, or CI pipelines. 114.6K+7 days: —
- 5 Egonex-AI/Understand-AnythingSkillsPlugins & marketplacesSubagents This plugin analyzes any codebase, documentation, or wiki using deterministic Tree-sitter parsing combined with multi-agent LLM analysis to construct a structured knowledge graph. It offers an interactive browser dashboard, dependency tours, diff impact analysis, and conversational Q&A across multiple AI coding platforms. 93.6K+7 days: —
- 6 career-ops-hq/career-opsSkillsPlugins & marketplacesHooks This open-source AI job search assistant scans company job portals, evaluates job descriptions against a user CV, and tracks applications locally. It tailors ATS-compliant resumes, generates cover letters and outreach drafts, and provides interview preparation without auto-submitting. Developers can run it directly inside AI CLIs such as Claude Code, OpenCode, and Codex. 84.1K+7 days: —
- 7 ruvnet/rufloSkillsPlugins & marketplacesSubagents This agent meta-harness extends Claude Code and Codex with multi-agent swarm coordination, autonomous workflows, and persistent vector memory. It integrates specialized agents, background workers, zero-trust cross-machine federation, and a console for monitoring runs and costs. Developers can run it as Claude Code plugins, via CLI, or as an MCP server. 82.2K+7 days: —
- 8 headroomlabs-ai/headroomMCP serversSkillsPlugins & marketplaces This tool compresses context such as tool outputs, logs, files, and conversation history locally before sending it to language models. It runs as an in-process library, a local proxy, an MCP server, or an agent wrapper for tools like Claude Code to reduce token consumption. The system also supports reversible compression via local caching and shapes verbosity to lower output token costs. 80.3K+7 days: —
- 9 ayghri/i-have-adhdSkillsPlugins & marketplacesHooks This skill alters coding assistant responses to deliver direct, ADHD-friendly answers. It enforces ten formatting rules that remove conversational filler, lead immediately with the required action, and provide clear numbered steps. Developers get focused instructions without preambles or verbose sign-offs. 61.9K+7 days: —
- 10 Imbad0202/academic-research-skillsSkillsPlugins & marketplacesSubagents This plugin provides a suite of Claude Code skills designed to assist researchers across the academic lifecycle from investigation to publication. It orchestrates subagents for deep research, paper drafting, systematic review screening, and multi-perspective peer reviews. The pipeline incorporates human-in-the-loop checkpoints, citation auditing, and integrity gates to verify claims and sources. 58K+7 days: —
- 11 anthropics/claude-plugins-officialOfficialSkillsPlugins & marketplacesMCP servers This repository hosts Anthropic's official plugins and marketplace catalog for Claude Code. It provides reference plugin implementations containing commands, MCP server configurations, skills, and agents. Developers can discover and install these extensions directly through the Claude Code plugin system. 47.9K+7 days: —
- 12 luongnv89/claude-howtoPlugins & marketplacesSubagentsHooks This repository is a visual, example-driven tutorial and reference guide for Claude Code. It provides a structured 10-module learning roadmap along with production-ready copy-paste templates covering slash commands, CLAUDE.md memory, skills, subagents, MCP servers, hooks, and plugins. 47.5K+7 days: —
- 13 wshobson/agentsSkillsPlugins & marketplacesSubagents This repository provides a collection of plugins, agents, skills, and commands written in Markdown in Claude Code format. It includes adapters to automatically translate and configure these components for multiple AI coding tools, including Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi. 42.8K+7 days: —
- 14 Yeachan-Heo/oh-my-claudecodeSkillsPlugins & marketplacesSubagents This plugin and CLI tool provides multi-agent orchestration and workflow automation for Claude Code. It coordinates specialized agents through structured stages such as planning, execution, and verification, and can spawn external CLI workers in tmux. It also includes autonomous execution modes, requirement clarification, and custom skill auto-injection. 41K+7 days: —
- 15 openai/codex-plugin-ccSkillsPlugins & marketplacesSubagents This plugin integrates OpenAI Codex into Claude Code through dedicated slash commands and a subagent. It enables developers to perform standard or adversarial code reviews, delegate debugging and fixing tasks to Codex, and transfer session transcripts directly into Codex. 35.3K+7 days: —
- 16 mksglu/context-modeSkillsPlugins & marketplacesMCP servers This local plugin intercepts tool outputs and runs executions in a sandbox to prevent large payloads from exhausting an agent's context window. It indexes raw command logs, file contents, and web responses into a local SQLite database, returning only targeted excerpts or script results. It operates completely on your machine across Claude Code and other agents without telemetry. 34.4K+7 days: —
- 17 davila7/claude-code-templatesSkillsPlugins & marketplacesSubagents This project provides an open catalog and CLI to search and install Claude Code components, including skills, subagents, slash commands, hooks, and MCP servers. The CLI writes configuration files to their appropriate directories and merges existing setups instead of overwriting them. It also includes local tools for chat history, diagnostics, and session monitoring. 34.1K+7 days: —
- 18 tirth8205/code-review-graphSkillsMCP serversHooks This tool builds a local knowledge graph of a codebase using Tree-sitter and stores code structure in SQLite. It provides an MCP server and CLI to supply AI coding assistants with targeted context, blast-radius analysis, and risk scoring during code reviews. Incremental updates via hooks or watch mode reparse only changed files. 32.9K+7 days: —
- 19 AgriciDaniel/claude-seoSkillsPlugins & marketplacesSubagents This SEO audit plugin for Claude Code coordinates 29 sub-skills and 20 specialist subagents to evaluate websites. It inspects technical factors, Core Web Vitals, E-E-A-T content quality, Schema.org markup, and AI search readiness across LLM platforms. The tool outputs a prioritized action plan and generates reports directly in the terminal. 31.4K+7 days: —
- 20 alirezarezvani/claude-skillsSkillsPlugins & marketplacesSubagents This repository provides a collection of over 400 modular skills, agents, and personas designed for Claude Code and 12 other AI coding tools. Each skill includes structured SKILL.md instructions, reference templates, and dependency-free Python scripts covering engineering, product, compliance, and finance. It enables developers to expand their AI assistant's domain knowledge and automate complex multi-step workflows. 30.3K+7 days: —
- 21 OthmanAdi/planning-with-filesSkillsPlugins & marketplacesHooks This tool provides persistent file-based planning for AI coding agents across long-running tasks. It maintains three Markdown files—task_plan.md, findings.md, and progress.md—on disk to track tasks, decisions, and session logs. Lifecycle hooks re-inject the plan on every turn, allowing the agent to recover progress after compaction or /clear commands. 28.2K+7 days: —
- 22 SuperClaude-Org/SuperClaude_FrameworkSkillsPlugins & marketplacesSubagents This configuration framework extends Claude Code with 30 slash commands, 20 domain-focused AI agents, and 7 behavioral modes across the software development lifecycle. It injects behavioral instructions and orchestrates workflows from brainstorming and deep research to implementation and testing. Developers can also manage and integrate up to 8 MCP servers directly through a companion CLI. 24K+7 days: —
- 23 microsoft/SkillOptSkillsPlugins & marketplacesHooks This framework optimizes reusable natural-language skills for frozen LLM agents without modifying model weights. It turns scored execution trajectories into bounded text edits on markdown documents, accepting changes only when they pass validation gates. The final output is a compact markdown skill file ready to deploy in agents like Claude Code. 19.2K+7 days: —
- 24 AgriciDaniel/claude-obsidianSkillsPlugins & marketplacesSubagents This Claude Code plugin builds and maintains an interconnected Markdown wiki for Obsidian based on the LLM Wiki pattern. It provides skills and read-only agents to ingest sources, connect notes, query knowledge with citations, and lint vault integrity. All changes execute as single transactions with journal backups and hash checks to prevent overwriting edits. 16.7K+7 days: —
- 25 open-metadata/OpenMetadataPlugins & marketplacesMCP serversSubagents An open-source metadata platform and context layer that unifies technical metadata, data lineage, quality checks, and business semantics into a metadata knowledge graph. It provides a built-in MCP server, REST APIs, and SDKs that enable AI agents and developers to run semantic searches, trace column-level lineage, and manage data contracts. 15.8K+7 days: —
- 26 tonhowtf/omnigetPlugins & marketplacesHooksSlash commands A local desktop application and MCP server that connects coding agents like Claude Code, Cursor, Codex, and Gemini CLI to local system tools, downloads, browser sessions, and chats. It provides structured tools to download media or purchased courses, convert files, manage ports, and crawl sites while keeping all data on your machine. It also includes a dedicated Claude Code plugin to download and transcribe media links directly from the terminal. 14.5K+7 days: —
- 27 max-sixty/worktrunkSkillsPlugins & marketplacesHooks This CLI tool manages Git worktrees to support running parallel AI agents such as Claude Code across isolated directories. It replaces complex Git worktree syntax by addressing workspaces directly through branch names for creation, switching, and deletion. Additional features include lifecycle hooks, one-step merges, and automated agent launches. 12.7K+7 days: —
- 28 open-gsd/gsd-coreSkillsPlugins & marketplacesSubagents This repository provides a context-engineering and spec-driven development framework for Claude Code and other AI coding tools. It runs heavy research, planning, and execution inside fresh-context subagents to prevent context rot. Development is organized into a five-step loop covering discussion, planning, execution, verification, and shipping. 11.8K+7 days: —
- 29 AgriciDaniel/claude-adsSkillsPlugins & marketplacesSubagents This skill for Claude Code audits and manages paid media operations across twelve ad platforms including Google, Meta, Amazon, and TikTok. It analyzes account exports or pasted summaries to produce evidence-backed audit reports identifying passes, failures, and data gaps. The tool operates in read-only mode by default, outputting draft plans and versioned JSON reports without modifying remote accounts directly. 11.2K+7 days: —
- 30 tigerless-labs/autoharnessSkillsPlugins & marketplacesSubagents This Claude Code plugin observes tool calls during real sessions to automatically extract and maintain custom agent skills. It consolidates duplicate lessons, updates existing skills when workflows change, and archives inactive ones based on usage metrics. The plugin manages only its self-authored skills without modifying user-written files. 11.2K+7 days: —
- 31 mobile-next/mobile-mcpMCP serversSkillsPlugins & marketplaces This MCP server enables AI agents to automate and interact with iOS and Android applications across simulators, emulators, and real devices. It drives native apps through accessibility snapshots and screenshot-based coordinate taps without requiring platform-specific test frameworks. Features include gesture support, screen mirroring, and logs. 10.8K+7 days: —
- 32 rehan-remade/universal-modderSkillsPlugins & marketplacesSubagents This repository provides a collection of skills, CLI utilities, subagents, and MCP configurations designed for AI coding agents to mod PC games. It guides agents through engine reconnaissance, reverse engineering, asset creation using fal or ComfyUI, in-game verification, and packaging. The package also includes a structured knowledge base where agents search and contribute verified modding field notes. 9.8K+7 days: —
- 33 jnMetaCode/superpowers-zhSkillsPlugins & marketplacesHooks This project provides a Chinese edition of the superpowers framework, offering 21 development skills for 26 AI coding tools like Claude Code, Cursor, and Trae. It supplies structured workflows for brainstorming, test-driven development, debugging, and code reviews, alongside China-specific conventions for Git platforms and commit standards. Developers can install the skills and bootstrap configurations project-wide or globally using an npm command or through the Claude Code plugin marketplace. 8.6K+7 days: —
- 34 trailofbits/skillsSkillsPlugins & marketplacesSubagents A curated marketplace of skills and plugins built for security research, code audits, and vulnerability analysis. It equips Claude Code and Codex with specialized agents for smart contract reviews, static analysis, reverse engineering, differential auditing, and testing workflows. 8.3K+7 days: —
- 35 lingfengQAQ/webnovel-writerSkillsPlugins & marketplacesSubagents This Claude Code plugin provides an end-to-end writing system for serialized long-form web novels. It organizes novel projects through volume planning, chapter drafting, consistency reviews, and a commit-driven fact tracking pipeline that updates project memory and indices. Authors can query world states, inspect progress on a read-only visual dashboard, and run diagnostics across book projects. 8K+7 days: —
- 36 tamaratran/fast-jev-compactionPlugins & marketplacesHooks This Claude Code plugin and npm library replaces context compaction summaries with decision-based pruning powered by Jev. Instead of rewriting or summarizing conversation turns, it scores tool calls and results, discarding or truncating stale ones while leaving user prompts and assistant text verbatim. It falls back to built-in summaries if pruning fails or reductions are insufficient. 8K+7 days: —
- 37 microsoft/TokenEconomizerPlugins & marketplacesHooks This plugin optimizes token costs for coding agents like Claude Code, Codex, and GitHub Copilot CLI by learning from prior sessions within a repository. It captures repository-specific commands and setup facts via micro-skills, prunes unused tool definitions from agent contexts, and detects repetitive failure loops to redirect stuck turns. 7.9K+7 days: —
- 38 uditgoenka/autoresearchSkillsPlugins & marketplacesHooks This skill brings autonomous, metric-guided iteration loops to Claude Code and other agent environments. It runs focused cycles to modify files, execute verification commands, keep improvements, and auto-revert regressions using Git. Built-in subcommands cover planning, automated bug debugging, error fixing, security audits, and shipping workflows. 6.9K+7 days: —
- 39 loopx-project/loopxSkillsPlugins & marketplacesHooks This harness-neutral control plane coordinates long-running AI agents across runtimes like Claude Code, Codex, and DeepSeek Harness. It preserves goals, execution plans, decision trails, and verifiable evidence in a local SQLite store so work continues across sessions, restarts, and compaction cycles without context loss. Developers can oversee multi-day engineering or research tasks, configure recurring heartbeat schedules, and enforce human approval gates on protected actions. 6.7K+7 days: —
- 40 WorldFlowAI/everything-claude-codeSkillsPlugins & marketplacesSubagents This repository provides a complete plugin and configuration toolkit for Claude Code, featuring specialized subagents, custom slash commands, workflow skills, and rule sets. It includes cross-platform Node.js lifecycle hooks for memory persistence and compaction, alongside ready-to-use MCP server configs. 6.7K+7 days: —
- 41 czlonkowski/n8n-skillsSkillsPlugins & marketplacesHooks This plugin provides fourteen Claude Code skills, an automated router, and execution hooks to guide AI assistants in creating and debugging n8n workflows with the n8n-mcp MCP server. It covers correct expression syntax, node configuration, JavaScript and Python Code nodes, error handling, AI agent tools, and multi-instance management. It also provides step-by-step instructions for deploying self-hosted n8n setups using Docker Compose on Linux servers. 6.7K+7 days: —
- 42 kenn-io/agentsviewSkillsPlugins & marketplacesSubagents This local-first tool aggregates, searches, and analyzes coding agent sessions across Claude Code, Codex, and dozens of other agents. It stores transcripts in a local SQLite database and provides a web dashboard alongside CLI commands for tracking token consumption, daily costs, and tool error sequences. Full-text and semantic search help developers locate past prompts and inspect code changes. 6.5K+7 days: —
- 43 Q00/ouroborosMCP serversSkillsPlugins & marketplaces This project provides a spec-first orchestration layer and MCP server for AI coding agents across multiple runtimes, including Claude Code. It clarifies user requirements through an interactive interview, writes testable acceptance criteria, delegates coding tasks to connected agents, and validates the implementation against the spec. 6.4K+7 days: —
- 44 Galaxy-Dawn/claude-scholarSkillsPlugins & marketplacesSubagents This semi-automated research assistant toolkit equips coding CLI assistants like Claude Code with structured workflows for academic and software research. It provides skills, agents, commands, and hooks spanning literature review with Zotero, experimental results analysis, and manuscript writing. Developers and researchers can maintain traceable research notes in Obsidian while keeping human judgment at the center of critical decisions. 6.1K+7 days: —
- 45 awarexone/Agentic-Bug-HunterSkillsPlugins & marketplacesMCP servers This toolkit provides automated reconnaissance, vulnerability scanning, and report generation for bug bounty hunting. It operates as a Claude Code plugin or as a standalone CLI tool compatible with multiple local and cloud AI providers. Developers can run targeted security workflows, validate findings against a triage gate, and produce formatted bounty reports. 6K+7 days: —
- 46 fengshao1227/ccg-workflowSkillsPlugins & marketplacesSubagents This workflow engine turns Claude Code into a multi-model orchestrator that coordinates tasks across external models such as Codex, Gemini, and Grok. It automatically analyzes intent, chooses from ten execution strategies, and uses JavaScript hooks to maintain task context across session compactions. It also provides quality verification gates, persistent task directories, and standalone domain skills. 6K+7 days: —
- 47 eugeniughelbur/obsidian-second-brainSkillsPlugins & marketplacesHooks This plugin gives Claude Code and other AI agents persistent memory by reading and writing markdown notes directly in an Obsidian vault. It captures conversations, tasks, decisions, and external sources into linked notes while updating existing files and resolving contradictions over time. It also includes cross-agent logging through Crew and tools to search past context or challenge current plans against previous decisions. 5.4K+7 days: —
- 48 brycewang-stanford/Auto-Empirical-Research-SkillsSkillsPlugins & marketplacesSubagents This repository provides a curated library of agent skills for social science empirical research, covering 78 collections and over 1,100 skills. It supports the full empirical workflow from topic refinement, data retrieval, and causal identification to econometric estimation, robustness checks, and publication-ready drafting. 5.1K+7 days: —
- 49 anthropics/claude-plugins-communityOfficialSkillsPlugins & marketplacesHooks This repository is a read-only mirror of the community plugin marketplace for Claude Cowork and Claude Code. It hosts a catalog of community-contributed plugins that have passed automated security scanning and Anthropic approval. Developers can add this catalog to Claude Code to discover and install community plugins. 4.9K+7 days: —
- 50 zenbu-labs/terminal-browserPlugins & marketplacesHooks This project runs a Chromium-based web browser directly inside your terminal using the kitty graphics protocol and offscreen rendering. It enables developers and coding agents to browse pages, interact via split panes, select elements, and proxy localhost sites across remote SSH connections. 4.7K+7 days: —
- 51 michael-denyer/pstack-claudeSkillsPlugins & marketplacesSubagents This repository ports Lauren Tan's pstack skill stack from Cursor to Claude Code, Codex, Pi, GitHub Copilot, Muse, and other agent harnesses. It translates Cursor primitives into native skills, subagents, and hooks without runtime overhead, featuring poteto-mode to automate reproduction, planning, delegation, and verification across workflows. 4.7K+7 days: —
- 52 nyldn/claude-octopusSkillsPlugins & marketplacesHooks This plugin orchestrates Claude Code with up to twelve external AI providers, including Codex, Copilot, Ollama, and Perplexity, to cross-check research, architecture, and code. It remains dormant during normal prompts and activates via slash commands to run multi-model debates, councils, and end-to-end development workflows with consensus verification gates. 4.5K+7 days: —
- 53 nykooi1/vibe-wiseSkillsPlugins & marketplacesHooks This plugin for Claude Code and Codex guides developers through software architecture and system design while letting AI write the implementation. It introduces structured checkpoints that prompt developers to choose approaches, evaluate tradeoffs, and review plans before generating code. Learning notes, preferences, and project maps are stored locally to maintain continuity across coding sessions. 4.4K+7 days: —
- 54 lennney/stop-that-shitSkillsPlugins & marketplacesSubagents This project provides a multi-platform guard and skill system for AI coding agents such as Claude Code and Codex. It intercepts unrequested scope creep, unnecessary checksum calculations, unauthorized file modifications during reviews, and redundant task thrashing while preserving essential code changes and migrations. 4.1K+7 days: —
- 55 gadievron/raptorHooksCLAUDE.md & templates This autonomous security research framework extends Claude Code with static analysis, binary analysis, vulnerability validation, and patch generation. It filters false positives from tools like Semgrep and CodeQL, generates proof-of-concept exploits, and drafts candidate security fixes in isolated sandboxes. Developers can audit codebases, inspect software supply chains, and analyze binaries through slash commands or a standalone CLI. 4K+7 days: —
- 56 rebelytics/one-skill-to-rule-them-allSkillsPlugins & marketplacesHooks This repository provides Task Observer, a meta-skill that monitors sessions, identifies gaps or adjustments, and proposes updates to existing skills and candidates for new ones. It captures corrections and cross-cutting principles into structured observation logs without altering installed skills until you review and approve the changes. 4K+7 days: —
- 57 Jakeschincariol/linkedin-agent-skillSkillsPlugins & marketplacesHooks This repository provides eleven Claude skills and Python tools to assist with managing a LinkedIn account. It drafts posts using 21 hook formulas, crafts comments, plans schedules, scores profiles, and strips AI tells like invisible characters, typography quirks, and overused buzzwords without auto-posting to LinkedIn. 3.8K+7 days: —
- 58 strukto-ai/mirageSkillsPlugins & marketplacesHooks This project provides a virtual terminal and unified virtual filesystem designed specifically for AI agents. It decouples the terminal interface from storage and computing machines, allowing services like S3, Slack, and databases to mount side by side under a single root. Developers can route command execution across sandboxes and enforce granular access profiles. 3.8K+7 days: —
- 59 davepoon/buildwithclaudeSkillsPlugins & marketplacesSubagents A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw 3.8K+7 days: —
- 60 Haleclipse/CCometixLinePlugins & marketplacesHooks Claude Code statusline tool written in Rust 3.6K+7 days: —
- 61 agenticnotetaking/arscontextaSkillsPlugins & marketplacesSubagents Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own. 3.5K+7 days: —
- 62 giancarloerra/SocratiCodeSkillsPlugins & marketplacesMCP servers Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta. 3.4K+7 days: —
- 63 microsoft/skillsPlugins & marketplacesHooks Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents 3.2K+7 days: —
- 64 Chachamaru127/claude-code-harnessSkillsPlugins & marketplacesSubagents Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle 3.2K+7 days: —
- 65 plugin87/ux-ui-agent-skillsPlugins & marketplacesHooks Design-system skills for Claude Code, Codex, Cursor, Copilot and Gemini CLI: DTCG tokens, WCAG 2.2 AA to AAA, 2,144 design systems, 26 skills, any-framework code, and 52 gates that fail the build instead of taking the agent's word for it. 3.2K+7 days: —
- 66 aaron-he-zhu/aaron-marketing-skillsPlugins & marketplacesHooksSlash commands 120 marketing skills as an AI marketing staff — plugin, portable skills, or an 8-bot team across 7 disciplines (narrative, SEO/GEO, social, email, paid, influencer, launch) on one contract, with 8 auditor gates: TALE · CORE-EEAT · CITE · ECHO · SEND · ROAS · STAR · RAMP. 3.2K+7 days: —
- 67 openlit/openlitPlugins & marketplacesHooks Same agent, Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost. 3.1K+7 days: —
- 68 alexgreensh/token-optimizerSkillsPlugins & marketplacesHooks Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay. 3K+7 days: —
- 69 cocoindex-io/cocoindex-codeSkillsPlugins & marketplacesMCP servers A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it! 3K+7 days: —
- 70 rohitg00/pro-workflowSkillsPlugins & marketplacesSubagents Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills. 3K+7 days: —
- 71 jeremylongshore/tons-of-skills-marketplaceSkillsPlugins & marketplacesSubagents Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. 2.9K+7 days: —
- 72 zilliztech/memsearchSkillsPlugins & marketplacesHooks A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. 2.9K+7 days: —
- 73 letta-ai/claude-subconsciousPlugins & marketplacesHooks Give Claude Code a subconscious 2.9K+7 days: —
- 74 kaitranntt/ccsPlugins & marketplacesHooks Switch between Claude accounts, Gemini, Copilot, OpenRouter (300+ models) via CLIProxyAPI OAuth proxy. Visual dashboard, remote proxy support, WebSearch fallback. Zero-config to production-ready. 2.9K+7 days: —
- 75 rohitg00/awesome-claude-code-toolkitSkillsPlugins & marketplacesSubagents The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills, 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 14 MCP configs, 26 companion apps, 52 ecosystem entries, and more. 2.9K+7 days: —
- 76 supermemoryai/claude-supermemoryPlugins & marketplacesSubagentsHooks Enable Claude Code to learn in real-time, update it's knowledge, and grow with you, using supermemory. 2.8K+7 days: —
- 77 stellarlinkco/myclaudeSkillsPlugins & marketplacesSubagents Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode) 2.8K+7 days: —
- 78 ZeframLou/call-meSkillsPlugins & marketplacesHooks Minimal plugin that lets Claude Code call you on the phone. 2.7K+7 days: —
- 79 nizos/tdd-guardSkillsPlugins & marketplacesHooks Automated TDD enforcement for Claude Code 2.4K+7 days: —
- 80 tractorjuice/arc-kitSkillsPlugins & marketplacesSubagents Enterprise architecture governance for Claude Code and other AI coding assistants. 76 commands draft requirements, business cases and design reviews. 2.3K+7 days: —
- 81 LeoYeAI/agent-master-skillsSkillsPlugins & marketplacesSubagents 🧠 Curated collection of 2700+ best agent skills — AI, coding, marketing, design, finance and more. Harness-agnostic: works with Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, Hermes and any Agent Skills runtime. Refreshed daily by MyClaw.ai — Powered by MyClaw.ai 2.2K+7 days: —
- 82 Jesseovo/last30days-skill-cnSkillsPlugins & marketplacesHooks 给 AI Agent 的中文互联网研究 Skill:检索 8 大平台最近 30 天的讨论,追踪跨平台热点,生成附原始来源的报告,并提供每日全网热榜。支持 Claude Code、Codex、OpenClaw。 2.2K+7 days: —
- 83 doobidoo/mcp-memory-serviceMCP serversPlugins & marketplacesSubagents Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. 2.1K+7 days: —
- 84 GammaLabTechnologies/harmonistHooks Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies. 2.1K+7 days: —
- 85 nimbalyst/nimbalystSkillsPlugins & marketplacesSubagents Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android. 2.1K+7 days: —
- 86 kenryu42/cc-safety-netSkillsPlugins & marketplacesHooks A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi. 2.1K+7 days: —
- 87 pchalasani/claude-code-toolsSkillsPlugins & marketplacesSubagents Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents. 2K+7 days: —
- 88 xu-xiang/everything-claude-code-zhSkillsPlugins & marketplacesSubagents everything-claude-code 中文翻译项目:完整的 Claude Code 配置集合(agents, skills, hooks, commands, rules, MCPs)。源自 Anthropic 黑客松获胜者的实战配置,助力中文工程师高效理解与使用 Claude Code。 2K+7 days: —
- 89 RedPlanetHQ/corePlugins & marketplacesMCP serversHooks Your Personal AI OS 2K+7 days: —
- 90 EpicGames/unreal-engine-skills-for-claude-code-pluginSkillsPlugins & marketplacesHooks 2K+7 days: —
- 91 composio-community/awesome-claude-pluginsSkillsPlugins & marketplacesSubagents A curated list of Plugins that let you extend Claude Code with custom commands, agents, hooks, and MCP servers through the plugin system. 2K+7 days: —
- 92 BayramAnnakov/claude-reflectSkillsPlugins & marketplacesHooks A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md. 2K+7 days: —
- 93 severity1/claude-code-prompt-improverSkillsPlugins & marketplacesHooks Intelligent prompt improver hook for Claude Code. Type vibes, ship precision. 2K+7 days: —
- 94 ReScienceLab/opc-skillsSkillsPlugins & marketplacesHooks Agent Skills for Solopreneurs 1.9K+7 days: —
- 95 NeoLabHQ/context-engineering-kitSkillsPlugins & marketplacesSubagents Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative. 1.8K+7 days: —
- 96 mims-harvard/ToolUniversePlugins & marketplacesMCP serversSubagents Democratizing AI scientists with ToolUniverse 1.8K+7 days: —
- 97 AltanS/colliePlugins & marketplacesHooks Herdr mobile app for iPhone and Android. A self-hosted PWA to drive Claude Code, Pi, Codex and OpenCode in Herdr, tmux or zellij from your phone. Push alerts, no app store. 1.7K+7 days: —
- 98 codeaholicguy/ai-devkitSkillsPlugins & marketplacesHooks The control plane for AI coding agents. 1.7K+7 days: —
- 99 microsoft/azure-skillsSkillsPlugins & marketplacesHooks Official agent plugin providing skills and MCP server configurations for Azure scenarios. 1.7K+7 days: —
- 100 activeloopai/hivemindSkillsPlugins & marketplacesHooks Hivemind turns your traces into reusable skills across agents 1.7K+7 days: —
Summary written by AI from the README; it may be imprecise. Ranked by GitHub stars, not a recommendation. Read the safety notes before installing.