Agent Skills & Plugins
Reusable skills, slash commands, hooks and subagents for coding agents. As of 2026-11-21, 155 indexed products offer it (101 with full profiles), in 10 forms: 65 Plugins, 37 Agent skills, 31 MCP servers, 7 Rules packs. 45 were published in the last 90 days, against 17 in the 90 days before. Gemini CLI has the most GitHub stars, 23% of the total across 136 products with their own repository.
CapabilitySegment label: Established DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
Plugins 65 indexed · 33 profiled
33 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | lot-mapLot Map for Claude Code: a live map beside the chat that shows what the agent is doing. Tool calls, model steps, hooks, skills and subagents light up as they happen. Local only, in 7 languages. | alexeyw | 1.1k | today | ||
| 2 | awesome-claude-code-mods9,000+ Claude Code mods, with what each one can access before you install it. Context and usage meters, prompt cache warmers, status lines, guards and more, with install hints. | karanb192 | 1.1k | today | ||
| 3 | awesome-claude-code-pluginsAwesome Claude Code plugins — a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code | ccplugins | 1.0k | 3mo ago | ||
| 4 | agy-staffHire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness. | keli-wen | 905 | 2d ago | ||
| 5 | claude-skills-founderClaude Code skills for startup founders — product briefs, competitor analysis, pricing strategy, pitch decks, and GTM plans from your terminal | emotixco | 893 | 18d ago | ||
| 6 | claude-code-workflowsDevelopment workflows for Claude Code that keep broad exploration focused on the outcome you approved. | shinpr | 719 | 1d ago | ||
| 7 | claude-code-hooks🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity. | karanb192 | 586 | 2d ago | ||
| 8 | maestro-orchestrateMulti-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools | josstei | 489 | 19d ago | ||
| 9 | claude-flightdeckA Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes. | scasella | 333 | 2d ago | ||
| 10 | superpowers-symfonyClaude Code plugin for Symfony 7.4 LTS & 8.x — 44 skills, 7 AI subagents & 13 commands for API Platform v4, Doctrine ORM 3, TDD (Pest/PHPUnit), Messenger, security & DDD. | dev-toolings | 234 | 10d ago |
Agent skills 37 indexed · 36 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | agentsPlugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and adapted to each tool by generators with validation and evals. | wshobson | 43k | 3d ago | ||
| 2 | Claude-BugHunterA Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices. | elementalsouls | 15k | today | ||
| 3 | awesome-codex-subagentsA collection of 130+ specialized Codex subagents covering a wide range of development use cases. | VoltAgent | 6.5k | 19d ago | ||
| 4 | founder-skillEleven free Claude skills that test a business before you launch it: a board trained on Hormozi, Thiel and Jobs, a marketing director, a CFO, and a consumer panel of 100 buyer agents. Free, MIT. | Jakeschincariol | 4.5k | 1mo ago | ||
| 5 | Continuous-Claude-v3Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. | parcadei | 4.0k | 5d ago | ||
| 6 | cc-sddTurn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity. | gotalab | 3.8k | 1mo ago | ||
| 7 | Claude-Code-QuestClaude Code guide in three levels, Beginner to Advanced: hands-on lessons with checked exercises, every volatile fact cited to its source. Independent community guide. | wesammustafa | 3.7k | 6d ago | ||
| 8 | gentle-shellGentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD). | Gentleman-Programming | 2.9k | today | ||
| 9 | arena-skillWhen Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill. | Jakeschincariol | 1.6k | 1mo ago | ||
| 10 | evoturns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents. | evo-hq | 1.5k | 3d ago |
MCP servers 31 indexed · 13 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | context-modeFree, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry. | mksglu | 34k | today | ||
| 2 | buildwithclaudeA single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw | davepoon | 3.8k | 1d ago | ||
| 3 | deja-vu — Coding Agent Memory & Session SearchLocal memory & session search across forty-nine coding agents: Claude Code, Codex, Cursor. | vshulcz | 1.6k | today | ||
| 4 | deja-vuLocal memory & session search across forty-nine coding agents: Claude Code, Codex, Cursor. | vshulcz | 1.6k | today | ||
| 5 | Agent SwarmFull Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration. | desplega-ai | 1.1k | today | ||
| 6 | cheap-ag50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex. | muaaz9329 | 339 | 5d ago | ||
| 7 | engramRanked local code-graph context for AI coding agents. Intercepts reads + greps. Apache-2.0. | NickCirv | 143 | 1mo ago | ||
| 8 | sub-agents-mcpMCP server for delegating tasks to specialized AI sub-agents across coding tools | shinpr | 97 | 29d ago | ||
| 9 | jev-useTyped yes/no, pick-one and score judgments from Jev in one batched call; typed escalation back. | shitianfang | 85 | 2mo ago | ||
| 10 | PitroomHands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts. | ATASTECH | 53 | 23d ago |
Rules packs 7 indexed · 4 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | vibes-plugUniversal AI Agent Swarm & MCP Plugin with 178 specialized skills and 8 autonomous subagents for Antigravity, Claude Code, Cursor, Windsurf, and OpenAI Codex. | roedyrustam | 128 | 1d ago | ||
| 2 | slushpileAn adversarial job search that gets better as it goes: pool-anchored fit scoring, a resume and cover letter built against the job description, seven agents that try to reject you before a recruiter does, and a profile that keeps what they find. | VonTerraProject501c3 | 28 | 3mo ago | ||
| 3 | tashan-cursor-skills他山 Cursor Skill 体系 — 95个Skills + 32个Rules + 18个SubAgents,让AI在执行任务时能自主判断、按规范执行、并从经验中自我进化 | TashanGKD | 25 | 7mo ago | ||
| 4 | cognitive-oscognitive-os · 认知操作系统 — 13 Skills + 4 Rules + 4 SubAgents,把人脑分层记忆结构外化为 AI 可操作的知识体系,以50年认知科学研究为基础 | TashanGKD | 12 | 8mo ago |
Platforms 6 indexed · 6 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Gemini CLIOpen-source terminal coding agent powered by Gemini models, extensible through MCP servers, extension packages, Agent Skills, hooks, subagents, custom commands and GEMINI.md context files. | 109k | today | |||
| 2 | gooseOpen-source, local general-purpose AI agent (desktop app and CLI) for coding, research, writing and automation that works with any LLM and is extended through MCP extensions, YAML recipes and subagents. | Agentic AI Foundation (originally Block) | 57k | 1d ago | ||
| 3 | Qwen CodeOpen-source terminal coding agent tuned for Qwen models, with VS Code, Zed and JetBrains integrations, SDKs (TypeScript, Python, Java), a daemon/REST mode, and support for MCP, skills, subagents, extensions, hooks and custom commands. | Alibaba (Qwen team) | 31k | today | ||
| 4 | Devin Desktop (formerly Windsurf)Cognition's AI IDE, formerly Windsurf, whose local agent (Devin Local, successor to Cascade) and Agent Command Center manage local and cloud Devin agents, customizable with rules/AGENTS.md, skills, MCP, hooks, subagents and plugins. | Cognition | — | — | ||
| 5 | Google AntigravityGoogle's agentic development platform comprising a desktop app for managing parallel agents, an agentic IDE, the Antigravity CLI (Gemini CLI's successor for consumers) and a Python SDK, extensible with MCP, rules, skills, hooks, subagents and plugins. | — | — | |||
| 6 | Factory (Droid)Factory's coding agent 'Droid', available as a CLI, a desktop Factory App and web/mobile sessions with cloud 'Droid Computers', configurable with AGENTS.md, MCP, skills, subagents, hooks, plugins and custom slash commands. | Factory | — | — |
Agent projects 3 indexed · 3 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. | bytedance | 86k | today | ||
| 2 | awesome-claude-code-subagentsA collection of 100+ specialized Claude Code subagents covering a wide range of development use cases | VoltAgent | 27k | 19d ago | ||
| 3 | dscodeA DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry | qiz029 | 1.0k | 8d ago |
Frameworks 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | pydantic-deepagentsOpen-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model. | vstorm-co | 1.1k | 22d ago | ||
| 2 | Boucle-frameworkAutonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it. | Bande-a-Bonnot | 126 | 1mo ago |
IDE extensions 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Claude Code Workflow StudioVisual Workflow Editor for Claude Code, GitHub Copilot, and more AI agents | breaking-brake | 5.5k | 1mo ago | ||
| 2 | DamoclesAn AI coding agent that runs as a standalone desktop app for Windows, macOS and Linux, and as a VS Code extension. Chat with Claude, GPT and other models, approve diffs, rewind checkpoints, and use persistent memory, subagents, teams and MCP, powered by the Pi agent runtime. | Aizenvolt | 82 | today |
Infrastructure 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | seedeepWhat Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine. | duqaXxX | 49 | 19d ago |
Agent SDKs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Claude Agent SDKSDK that exposes the agent loop behind Claude Code (file and shell tools, subagents, hooks, permissions, context compaction) for building custom agents in Python or TypeScript. | Anthropic | 8.6k | today |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 31 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 37 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 60 |
| Codex | 20 |
| Cursor | 10 |
| Google Antigravity | 5 |
| OpenCode | 4 |
| Gemini CLI | 4 |
| GitHub Copilot | 2 |
| Claude Desktop | 2 |
| Devin Desktop (formerly Windsurf) | 2 |
| ChatGPT | 2 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 2 | 1.3% |
| Xcode / iOS | 2 | 1.3% |
| AWS | 1 | 0.6% |
| Discord | 1 | 0.6% |
| Pinecone | 1 | 0.6% |
| PostgreSQL | 1 | 0.6% |
| Snowflake | 1 | 0.6% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| agent skills | Ignored |
| claude skills | Ignored |
| skill.md | Ignored |
| claude code plugin | Ignored |
| slash commands | 23 |
| subagents | 83 |
| claude code hooks | 49 |
Segment statistics
Whole catalogue (155 indexed products). Calculated 2026-11-21.
Established. Mid-sized among capabilities, with launches roughly in step with the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.120 means stars are spread as if across about 8 equally popular projects — unconcentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .