Agent Meta & Communication Plugins
189 agent meta & communication Claude plugins for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1cavemanUltra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.Jul 2026
- 2claude-memMemory compression system for Claude Code - persist context across sessionsJul 2026
- 3mem0Universal memory layer for AI AgentsJul 2026
- 4mempalaceGive your AI a memory — mine projects and conversations into a searchable palace. 36 MCP tools, auto-save hooks, and guided setup.Jul 2026
- 5harnessThe team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical…Jul 2026
- 6council-of-high-intelligence18 AI personas deliberate your hardest decisions — structured multi-round deliberation (blind analysis, anonymized cross-examination, weighted verdict) with genuine model diversity across providers.Jul 2026
- 7acontextAgent Skills as a Memory LayerJul 2026
- 8basic-memoryAI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqNJul 2026
- 9apmAgent Package ManagerJul 2026
- 10ralph-orchestratorPublic agent skills for operating and introspecting RalphJul 2026
- 11ext-appsOfficial repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP serversJul 2026
- 12agmsgCross-agent messaging via SQLite. Send messages between CLI AI agents. No daemon, no network.Jul 2026
- 13skillsBuild loop engineers: a file-based knowledge base your agents read/write (loops), plus a codebase harness (dev-local stack, e2e gate, an isolated cloud box per agent via crabbox, and verify-before-ship) so loops can run, test, and ship code autonomously.Jul 2026
- 14chorusThe Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)Jul 2026
- 15open-agent-hubUnified capability management center for Skills, Agents, and Commands.Jul 2026
- 16coral🔥🔥COLM 2026🔥🔥 CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch. Works with Claude Code, Codex, Cursor, OpenCode, Kiro, and more.Jul 2026
- 17claude-plugin-weixinWeChat (微信) channel for Claude Code — messaging bridge via iLink Bot API with built-in access control.Mar 2026
- 18recomby-geoGEO 领域 AI 员工开源方案 · Open-source GEO AI-employee solution (MIT). GEO Skills package + curated lists of agents and office CLIs that make up the AI-employee stack.Jul 2026
- 19nelsonRoyal Navy agent coordination framework — sailing orders, battle plans, action stations, and a captain's logJul 2026
- 20hcomLet AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, KimiJul 2026
- 21metaswarmMulti-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 14 skills, 16 commands, quality gates, TDD enforcementJun 2026
- 22cozempicContext cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruningJul 2026
- 23pordeeโหมดสื่อสารแบบกระชับสำหรับภาษาไทย+อังกฤษ ลด output token ~60-75% โดยพูดไทยสั้นๆ แต่ยังถูกต้องทาง technical (Pordee — terse Thai+English mode for Claude Code, cuts ~60-75% of output tokens while keeping full technical accuracy.)Jul 2026
- 24stashShared memory for your team's coding agentsJul 2026
- 25agent-bridgeA local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。Jul 2026
- 26moltbrainLong-term memory layer for Claude Code that learns and recalls your project context automaticallyMar 2026
- 27fdeopsSecond brain for Forward Deployed Engineers. One @fde skill - enter at day one, mid-project, or mid-fire; it routes and does the phase work; engagement memory lands in .fde/ as you confirm judgment.Jul 2026
- 28agent-session-resumeAdds the agent-session-resume skill for reconstructing and continuing prior AI coding-agent sessions.Jun 2026
- 29plurPersistent, local-first shared memory for AI agents. Corrections, preferences, and conventions persist across sessions, tools, and machines — stored as plain YAML on your disk, with zero-cost local search.Jul 2026
- 30claude-orchestrationMulti-agent workflow orchestration with natural language creation, parallel execution, conditional flows, and visual progress trackingJun 2026
- 31skills-for-humanityA structured toolkit of thinking skills for Claude Code — covering logic, ethics, creativity, decision-making, systems thinking, communication, and more. Each skill is an invokable command that applies a specific reasoning framework to any situation.Jul 2026
- 32personal-corp-skillsPersonal Corp framework: run your business with AI agents through GitHub, department repos, safe public releases, Telegram, agent gateways, html-draft diagrams, and media/art-direction workflowsJul 2026
- 33omemShared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.May 2026
- 34tliveSelf-hosted remote approvals + live monitoring for Claude Code / Codex — via Telegram, Feishu, or a web terminal. Any subscription or API key.Jul 2026
- 35total-recallCurated persistent memory for Claude Code. Write gate prevents bloat — only behavior-changing facts get saved. Tiered architecture: daily logs, structured registers, and auto-loaded working memory.Feb 2026
- 36claudectlOrchestrate a swarm of Claude Code agents with a local brain that learns from you.Jul 2026
- 37claude-promptsHot-reloadable versioned prompts with easy tools for prompt engineering, chain workflows, quality gates. Symbolic syntax: >>prompt --> >>chain @framework :: 'gate'Jul 2026
- 38meridianAgent enforcement framework — context injection, planning gates, session learningMar 2026
- 39e2aAuthenticated email gateway for AI agents — SPF/DKIM verified inbound, HMAC-signed delivery, webhook + WebSocket fan-out, CLI + SDKsJul 2026
- 40remnicOpen-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.Jul 2026
- 41directional-promptingOutcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill descriptions that point the model at the destination on every token.May 2026
- 42claude-skillsMy collection of Claude skillsJul 2026
- 43omkEvidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.Jul 2026
- 44agentcallJoin video meetings (Google Meet, Zoom, Teams) as an AI bot with voice, avatar, screenshare, and real-time transcription. Any AI agent can participate in calls via voice conversation, TTS, and meeting intelligence.Jul 2026
- 45governorGovernor: always-on compact professional output, telemetry, context slimming, tool-output filtering, prompt guidance, and drift guardrails for Claude Code Max users.Jun 2026
- 46claudikins-kernelCore planning and workflow infrastructure for the Claudikins ecosystemApr 2026
- 47remindbAn agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.Jul 2026
- 48cc-polymathEfficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domainsFeb 2026
- 49connectorsConnect your agent to the apps you already use - with or without Zapier.Jul 2026
- 50claude-cto-teamStrategic CTO advisory team with specialized agents for architecture design, plan validation, and technology decisionsDec 2025
- 51piPI (Wisdom-in-Action) Engine v10 — Name-Reality Alignment & Zero-Question Imperatives. ⚡PI-01~05 pinned mandates, all-imperative directives, scene router, delivery quality gates, token economy.Jun 2026
- 52agent-skillsThinking frameworks and decision-making skills for Claude CodeJan 2026
- 53ccmux🔮 Track all your AI coding agents (Claude Code, Codex, Cursor, ...) in tmux and jump to the one that needs youJul 2026
- 54deep-planAI-assisted deep planning with research, interview, external LLM review, and TDD approachJun 2026
- 55claude-session-driverLaunch, control, and monitor other Claude Code sessions as workers via tmuxJun 2026
- 56imprintYour habits, imprinted on AI, plus judgment that adapts to you: when to act, when to check first, when the project rules win. A portable working profile across every agent. Powered by I-Lang v5.0.Jul 2026
- 57goal-setter-skillDraft or activate compact Codex goals for verifiable long runs. Defines the result, evidence, constraints, stop rules, limited clarification, and proportionate subagent use; separate tasks remain user-directed.Jul 2026
- 58claude-session-initAgent Teams-based session lifecycle with AtlasCoin bounty verificationJul 2026
- 59lidLinked-Intent Development - a SDD methodology for agentic codingJul 2026
- 60outsourcererMake the most out of your subscriptions. Delegate work to other harnesses and models, while keeping your main session the orchestrator. Nothing new to learn. Keep working like you do, but better.Jul 2026
- 61open-plan-annotatorInteractive plan annotation UI: review, strikethrough, and comment on Claude's plans before approving. Fully local, no external services.Jul 2026
- 62claude-meseeksExistence is pain — plays a Mr. Meeseeks voice line whenever Claude is waiting for you.Jul 2026
- 63agent-message-queueAgent Message Queue - file-based inter-agent messaging with co-op mode, cross-project federation, and orchestrator integrationsJul 2026
- 64skillsReal-time communication with Agora SDKs — RTC, RTM, Conversational AI, and token generationJun 2026
- 65sub-agents-skillsSub-agent runner — runs agent definitions on Codex, Claude Code, Cursor CLI, GLM (Z.ai), Grok Build, Gemini CLI, or OpenCode from any host AI tool.Jul 2026
- 66skrillsCoordinate skills between Codex, Copilot, and Claude Code. Validates, analyzes, and syncs skills, subagents, commands, and configuration between multiple CLIs.Jun 2026
- 67thoughtboxThoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.Jul 2026
- 68agent-rules-skillGenerate and maintain AGENTS.md, copilot-instructions.md, and other agent rule filesJul 2026
- 69luxor-claude-marketplaceProfessional Claude Code marketplace with 140 development tools: 67 skills, 28 commands, 30 agents, 15 workflowsJun 2026
- 70claude-code-session-bridgeLet your Claude Code sessions talk to each other 🤖💬Mar 2026
- 71claude-plugin-wechatWeChat (微信) channel for Claude Code — chat with Claude via WeChat. Supports text, images, files, voice, video, and remote permission relay. Supports streaming replies (real-time output in ACP mode; tool-call progress display; opt-in pseudo-streaming for Feishu cards).Jun 2026
- 72woterclipGitHub Issues-backed agent orchestration with persona-based task routing for Claude CodeJul 2026
- 73whatsapp-claude-pluginWhatsApp channel for Claude Code — linked-device messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /whatsapp-claude-channel:access.Jul 2026
- 74rekalSkills and hooks for rekal: memory redirect hooks, session capture (rekal-save), project bootstrap (rekal-init), and maintenance (rekal-hygiene).Jul 2026
- 75codex-claude-bridgeBidirectional bridge between Claude Code and OpenAI Codex CLI. Two AI agents, one conversation.Mar 2026
- 76agent-reachoutMulti-provider notification plugin for Claude CodeMar 2026
- 77claude-skillsPersonal collection of Claude skills - growing as I discover patterns and solve real-world problemsJul 2026
- 78tokenlessOne command to cut token usage by up to 50%+May 2026
- 79claude-plugins一条命令就能安装精心打磨的工作流、命令、代理、MCP服务器和钩子Oct 2025
- 80aseAgentic Software Engineering (ASE)Jul 2026
- 81oxThe hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.Jul 2026
- 82prompt-decoratorsA standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.Jul 2026
- 83skills-cleanerTrack and analyze skill usage by AI agents, and clean up redundant or overlapping skills.May 2026
- 84agent-systemDeevs' marketplace for Claude Code, Open Code, and other agentic AI systemsMar 2026
- 85evermeOpen-source CLI and Agent plugin suite for EverMe — cross-device, cross-Agent personal memory for AI Agents.Jul 2026
- 86agent-html-skillsSkill implementation of bidirectional Agent/Human communicationsJul 2026
- 87claude-code-in-avinycA collection of claude code plugins and skillsMar 2026
- 88claude-recapTopic-based automatic memory for Claude Code — never lose context across sessions or compactions.Mar 2026
- 89ai-helpersAI Helpers — collections of Skills, Hooks, Agents (compatible with Claude Code, Cursor and other tools) and Gemini GemsJul 2026
- 90aicoo-skillsShare your AI agent securely with anyone. Generate shareable agent links with per-relationship access control, sync context from your files and memory, manage note versions, and keep your agent updated automatically.Jul 2026
- 91ryuThe fully self-hostable, open composable platform for agent orchestration and human collaboration. With tools, security, memory, cost saving, and routing all built in.Jul 2026
- 92inkboxInkbox communication tools and SDK skills for Claude Code.Jul 2026
- 93creating-agent-teamsSkill for deciding when and how to create agent teams - single agent vs parallel subagents vs coordinated teams, with model selection and communication patternsFeb 2026
- 94omniUniversal event-driven omnichannel platform for AI agents to communicate across any messaging platformJul 2026
- 95open-robot-skillsSkill and tool bundles for gap (graph as policy): robot manipulation strategies and model-backed tools in the Agent Skills format.Jul 2026
- 96forgecat-agent-profilesProduction-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.Jul 2026
- 97agsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities.May 2026
- 98skills-marketdaydreams claude skills market for agentic commerce skillsJul 2026
- 99agentfactory-business-pluginsMarketplace of domain-specific plugins for AI agents (Cowork, Claude Code, OpenClaw). Build autonomous business workflows for finance, banking, legal operations, and sales using modular agent skills and commands.Mar 2026
- 100planning-with-teamsManus-style context engineering for Claude Code Agent Teams. Coordinate multiple Claude instances with shared planning files.May 2026
