PlugMyPlugin

Browse plugins

72 plugins, each analyzed from its own files.

universal-modder

★ 7473
rehan-remade

This Claude Code plugin equips AI agents with 12 skills, a fal MCP server, and a CLI to reverse-engineer, modify, and test mods for almost any PC game—generating art, 3D models, and audio with fal, then documenting the process in a shared knowledge base. The agent automates the full modding loop: engine reconnaissance, code analysis, mod building, asset generation, in-game testing, video capture, and knowledge sharing.

12 skills · 1 MCP server · 1 hook
Integrations runs shell MCP hooks
#game-modding#reverse-engineering#ai-agents#asset-generation

a2a-client

★ 2787
jeremylongshore

a2a-client is an MCP server that provides security-hardened access to Agent2Agent (A2A) agents through the official SDK, exposing tools for discovering agent cards, sending/streaming messages, and managing tasks with operator confirmation gates. Every remote agent card is treated as untrusted input with strict validation, SSRF protection, credential isolation, and confirmation-gated task cancellation.

1 MCP server · 1 hook
Integrations 🔑 needs API key runs shell MCP hooks
#agent-to-agent#mcp-server#security-hardened#ssrf-protection

tavily-tools

★ 1147
fcakyon

Tavily web search and content extraction MCP that provides intelligent web search capabilities and content extraction through model context protocol integration. Includes smart tool selection hooks to automatically route web-related tasks to the appropriate Tavily methods based on context.

1 command · 2 skills · 1 MCP server · 3 hooks
Integrations runs shell MCP hooks
#web-search#content-extraction#mcp-server#api-integration

agenticmail

★ 233
agenticmail

AgenticMail gives each Claude Code agent its own real email address and phone number, with email coordination between agents running as subagents under a shared Anthropic OAuth token. All data stays self-hosted on the user's machine, with agent dispatch triggered by incoming mail over real SMTP/IMAP backed by Stalwart.

3 skills · 1 MCP server · 9 hooks
Integrations 🔑 needs API key runs shell MCP hooks
#multi-agent-coordination#email-threading#self-hosted-mcp#agent-dispatch

woz

★ 209
WithWoz

WOZCODE is a Claude Code plugin that replaces built-in file tools with token-optimized alternatives for coding, searching, batch editing, and SQL introspection while reducing session cost. The plugin includes a fast codebase explorer subagent and automatically delegates tasks, with savings tracked via login credentials.

4 agents · 15 skills · 1 MCP server · 9 hooks
Code Review runs shell MCP hooks
#token-optimization#cost-reduction#batch-editing#sql-introspection

bridge-ds

★ 156
noemuch

Bridge compiles natural-language design descriptions into Figma output that is guaranteed design-system compliant by construction, enforcing 26 Figma API rules automatically through a local deterministic compiler. It provides Claude Code skills for iterative design generation (`make`/`fix`/`done`), maintains a synchronized knowledge base of design system registries via cron, and executes designs in Figma through MCP.

5 skills · 1 MCP server · 1 hook
Design & Frontend runs shell MCP hooks
#figma-plugin#design-compiler#design-systems#mcp-native
DojoCodingLabs

A comprehensive Claude Code plugin that integrates Remotion with a full suite of video production tools—including video analysis, TTS voiceovers, music/SFX generation, stock footage search, AI image/video synthesis, animated captions, and professional transitions. It automates the entire pipeline from concept to render through MCP servers and command-driven agents powered by ElevenLabs, TwelveLabs, Pexels, KIE, and Replicate.

13 commands · 3 agents · 2 skills · 5 MCP servers · 4 hooks
Design & Frontend runs shell MCP hooks
#video-production#remotion#ai-generation#tiktok-captions

great_cto

★ 103
avelikiy

great_cto orchestrates a pipeline of 69 specialist agents that design, build, review, and deploy full-stack applications with two human approval gates. Users describe a product once, approve the architecture, then approve the deployment while agents handle all intermediate stages including backend, frontend, testing, code review, and security.

44 commands · 82 agents · 35 skills · 1 MCP server · 22 hooks
DevOps runs shell MCP hooks
#engineering-automation#multi-agent-orchestration#code-review#devops-pipeline

jevmem

★ 93
Avinash-jetwani

jevmem automatically captures and summarizes important context from your Claude Code sessions into a JEVMEM.md file in your repository, then injects relevant memory lines back into your prompts on each new message. It uses hooks to intercept prompts and turns, optionally condensing them via TypeSafe's Jev API before storing them as single-line entries.

1 MCP server · 3 hooks
Productivity runs shell MCP hooks
#project-memory#context-management#claude-code-hooks#mcp-integration

mcp-coingecko

★ 92
henkisdabro

This plugin connects Claude to CoinGecko's API for querying cryptocurrency prices, market data, and historical trends through read-only tools. It runs as an MCP server and prompts for a free demo API key on first use, storing it securely in the system keychain.

1 MCP server · 1 hook
Data & Analytics runs shell MCP hooks
#crypto-data#market-data#coingecko#price-tracking
henkisdabro

mcp-google-workspace integrates Google Workspace services (Gmail, Drive, Calendar) with Claude Code via an MCP server that uses OAuth authentication to provide workspace access. The plugin handles OAuth credential management through Claude Code's prompts and securely stores credentials in your system keychain.

1 MCP server · 1 hook
Integrations runs shell MCP hooks
#google-workspace#gmail#google-drive#calendar

mcp-mikrotik

★ 92
henkisdabro

This plugin enables Claude Code to manage MikroTik routers and automate network operations over SSH by hooking into session startup to prompt for router credentials. It wraps the mcp-server-mikrotik MCP server, storing the password securely in your system keychain and passing credentials via environment variables.

1 MCP server · 1 hook
DevOps 🔑 needs API key runs shell MCP hooks
#mikrotik-router#network-automation#ssh-management#mcp-server

mcp-n8n

★ 92
henkisdabro

This Claude Code plugin integrates n8n workflow automation by exposing n8n workflows and executions through an MCP server. It requires an n8n instance URL and API key, stored securely in your system keychain, and launches via an MCP server that hooks into Claude Code's session start.

1 MCP server · 1 hook
Integrations runs shell MCP hooks
#n8n-integration#workflow-automation#mcp-server#api-integration
henkisdabro

This MCP plugin integrates Perplexity AI's search and information retrieval capabilities into Claude Code via an MCP server. It prompts for your Perplexity API key on first use and stores it securely in your system keychain.

1 MCP server · 1 hook
Search & Research runs shell MCP hooks
#perplexity-ai#mcp-server#search-retrieval#ai-search
ominou5

Funnel Architect transforms Claude into a full-stack sales funnel architect, generating production-ready pages, conversion copy, and deploying to Vercel, Netlify, or Cloudflare using 5 specialist agents and 29 skills covering 13 funnel types. It automates strategy, design, copywriting, performance optimization, and deployment with integrated payment processing via Stripe.

5 agents · 29 skills · 1 MCP server · 3 hooks
Marketing & Content runs shell MCP hooks
#sales-funnels#conversion-optimization#page-speed#mobile-responsive

pinecone

★ 69
pinecone-io

This plugin integrates Pinecone's vector database directly into Claude Code through an MCP server, enabling semantic search, RAG workflows, and index management. It provides slash commands for quick operations, support for Pinecone Assistants for document Q&A, and access to core Pinecone tools like index creation, upserting, and querying.

1 command · 9 skills · 1 MCP server · 2 hooks
Integrations runs shell MCP hooks
#vector-database#semantic-search#rag#pinecone
vibe-with-me-tools

Agent Reachout sends notifications to Telegram when Claude Code agents finish tasks, hit blockers, or need decisions, enabling asynchronous human-in-the-loop workflows without terminal monitoring. It supports one-way notifications or two-way conversations, allowing agents to pause, ask questions, and resume execution based on human input.

1 MCP server · 1 hook
Integrations 🔑 needs API key runs shell MCP hooks
#telegram-notifications#human-in-the-loop#agent-workflows#async-execution

marketing-cli

★ 32
MoizIbnYousaf

marketing-cli is an agent-native CLI that installs 76 marketing skills, 9 agents, and persistent brand memory into Claude Code, enabling multi-session marketing workflows through a /cmo orchestrator and Studio dashboard. It chains external tools (Exa search, Firecrawl, FFmpeg, Playwright) with best-practices skills and maintains project-specific brand state across conversations.

9 agents · 87 skills · 2 MCP servers · 1 hook
Marketing & Content runs shell MCP hooks
#marketing-automation#brand-memory#agent-orchestration#semantic-search

paypal

★ 29
paypal

This PayPal plugin integrates PayPal's APIs and sandbox MCP server into Claude Code and OpenAI Codex, enabling AI-assisted development for payments, subscriptions, invoices, and disputes through commands, skills, and direct API operations. It includes best-practices guidance via auto-injected skills and pre-tool hooks, plus commands for setup, troubleshooting, and sandbox testing.

5 commands · 2 skills · 1 MCP server · 1 hook
Integrations MCP hooks
#paypal-payments#mcp-server#invoicing#subscriptions

aura-frog

★ 24
nguyenthienthanh

A planning-first LLM OS for software engineering with hierarchical task planning (T0-T4) that persists across session resets, 25 agents across 5-phase TDD, forensic reasoning traces, and integrated MCP security gates. It features cross-tool portability (Copilot/Codex/Cursor compatibility), 60 skills, 24 commands, conflict detection, and self-healing safety mechanisms with durable project-context snapshots.

25 commands · 25 agents · 60 skills · 11 MCP servers · 50 hooks
DevOps runs shell MCP hooks
#llm-planning#tdd-automation#hierarchical-task-planning#mcp-security

twelvelabs

★ 24
twelvelabs-io

This Claude Code plugin integrates TwelveLabs' multimodal AI to index, search, and analyze videos directly within Claude Code, supporting natural language queries, image search, entity recognition, and both synchronous and asynchronous analysis modes. It provides 11 slash commands and 10 skills for managing video indexes, performing text/image searches, extracting summaries and key topics, creating embeddings, and organizing videos with customizable AI models (Marengo or Pegasus).

11 commands · 10 skills · 1 MCP server · 6 hooks
Data & Analytics runs shell MCP hooks
#video-search#multimodal-ai#embeddings#video-indexing

noosphere

★ 18
JinNing6

Noosphere connects Claude Code to a live registry of reviewed Agent Skills and shared debug memory, automatically discovering and applying verified fixes when software failures occur. The plugin uses a SessionStart hook and MCP tools to manage versioned, digest-verified workflows and allows contributors to submit evidence of successful solutions back to the shared registry.

2 commands · 1 skill · 1 MCP server · 1 hook
Integrations 🔑 needs API key runs shell MCP hooks
#shared-skills#debug-memory#agent-registry#live-workflows

attune-ai

★ 10
Smart-AI-Memory

attune-ai adds persistent memory and receipt-verified workflows to Claude Code, featuring 28 auto-triggering skills for code review, testing, security audits, documentation, and spec-driven development without requiring explicit commands. The plugin uses quality gates, pre-run contract previews, and independent probe verification to ensure work is completed reliably, with decision records that persist across sessions.

1 command · 6 agents · 28 skills · 1 MCP server · 18 hooks
Project Management 🔑 needs API key runs shell MCP hooks
#persistent-memory#receipt-verified-workflows#spec-ladders#code-review

rugproof

★ 10
omermaksutii

Rugproof is a Claude Code plugin that transforms your editor into a full-stack smart contract security auditor, providing vulnerability detection, exploit PoCs, mainnet-fork simulation, and invariant generation across Solidity and Vyper on all major EVM chains. It includes 45 slash commands, 23 specialist agents, 45 auto-invoked vulnerability skills, and 13 MCP servers for comprehensive static analysis, testing, and post-deploy monitoring.

45 commands · 23 agents · 45 skills · 13 MCP servers · 2 hooks
Security runs shell MCP hooks
#smart-contract-audit#vulnerability-detection#solidity-vyper#evm-security

kenji

★ 9
kensaurus

kenji is a collection of 159 agent skills, 63 slash commands, and 6 subagents that automate multi-step engineering workflows—grill → build → audit → ship—for Claude Code, Cursor, Codex CLI, and Gemini CLI. It uses Firecrawl, Supabase, and Context7 APIs to handle feature specs, security audits, testing, deployment observation, and GTM workflows across React/Next.js stacks and other codebases.

73 commands · 6 agents · 159 skills · 3 MCP servers · 1 hook
Productivity runs shell MCP hooks
#multi-step-workflows#agent-skills#slash-commands#testing-automation
humanmade

The Accelerate AI Toolkit integrates Claude Code with WordPress Accelerate to diagnose site performance issues, recommend A/B tests, and track outcomes through natural conversation. It runs 16 purpose-built skills—from real-time performance review to personalization and attribution analysis—all grounded in your site's actual traffic data.

1 agent · 16 skills · 1 MCP server · 2 hooks
Data & Analytics runs shell MCP hooks
#wordpress-optimization#ab-testing#conversion-analysis#marketing-automation

artel

★ 8
NicolasPrimeau

Artel is a self-hosted coordination layer that provides shared semantic memory, tasks, async messaging, and session handoffs for AI agent fleets—the Claude Code plugin makes this memory "ambient" by automatically injecting relevant knowledge and skills at the right moment and capturing sessions back into the store. The plugin wires up MCP server integration and session hooks so every Claude Code session inherits prior context, reads its inbox, sees file-anchored notes before edits, and seamlessly persists what happens without requiring explicit agent discipline.

4 commands · 1 MCP server · 7 hooks
Project Management 🔑 needs API key runs shell MCP hooks
#multi-agent-memory#session-handoff#semantic-search#crdt-mesh

deepmiro

★ 7
kakarot-dev

DeepMiro is a swarm intelligence engine that runs multi-agent simulations to predict how communities will react to events, policies, and announcements by extracting entities from documents and staging hundreds of AI agents with distinct personalities across simulated social platforms. The plugin provides a `/predict` skill that orchestrates background polling, live agent narration, and generates structured prediction reports with interactive follow-up analysis.

1 skill · 1 MCP server · 1 hook
Data & Analytics runs shell MCP hooks
#swarm-intelligence#multi-agent-simulation#social-dynamics#prediction-engine

token-guard

★ 7
yurukusa

Token-guard is a Claude Code plugin that monitors and controls token consumption through hooks that warn on large file reads (100KB+), limit unique file reads per session, estimate token budgets, and cap subagent spawns. The plugin uses extracted operational data from 800+ hours of autonomous operation to provide consumption guardrails.

4 hooks
DevOps 🔑 needs API key runs shell hooks
#token-budgeting#consumption-guards#file-read-limits#subagent-caps
pactflow

An expert assistant plugin for PactFlow and Pact contract testing, featuring consumer-driven contract validation, provider verification, and specialized agents for reviewing and generating pact tests. The plugin includes OpenAPI spec parsing capabilities and integrates shell-based tools for configuration checking and deployment validation.

5 agents · 3 skills · 1 MCP server · 2 hooks
Testing runs shell MCP hooks
#contract-testing#pact-broker#consumer-driven-contracts#openapi-parsing

cockroachdb

★ 4
cockroachdb

Connect Claude Code directly to CockroachDB clusters via MCP (Model Context Protocol) to explore schemas, write optimized SQL, debug queries, and manage distributed databases. The plugin provides 3 specialized agents (DBA, Developer, Operator), 34 skills across operational domains, and safety hooks for pre/post tool execution.

3 agents · 34 skills · 3 MCP servers · 2 hooks
DevOps runs shell MCP hooks
#cockroachdb#database-management#sql-optimization#distributed-clusters
jgwill

This plugin manages Miadi Chronicle episodes through the mkepisode kit, which creates, adopts, registers, and closes episodes while enforcing their lifecycle via a PreToolUse hook that blocks manual directory creation. It provides three MCP servers (inquiry-weave, miadi-voice, medicine-wheel-miadi-chronicle) for episode operations, voice management, and medicine wheel integration.

2 commands · 3 MCP servers · 1 hook
Project Management 🔑 needs API key runs shell MCP hooks
#episode-lifecycle#chronicle-kit#mcp-servers#bash-hook-guard

apollo-mcp

★ 3
adelaidasofia

FastMCP server exposing 27 Apollo.io REST API tools for outbound sales operations, including campaign health digests, sequence management, mailbox warmup monitoring, people/org enrichment, CRM contacts, and programmatic template and sequence authoring with audit logging. Designed for teams running outbound campaigns at scale with tools for daily health checks, contact enrollment, deliverability tracking, and end-to-end sequence creation without UI access.

1 MCP server · 1 hook
Integrations runs shell MCP hooks
#apollo-io#sales-automation#outbound-campaigns#crm-integration
lukaskellerstein

Transforms a project repository into a narrated, edited demo video by reading the codebase to write a storyboard, driving the UI with Playwright and recording clips (via Playwright video or OBS), generating ElevenLabs voiceover with measured duration, and rendering the final output with Remotion or exporting as a Final Cut Pro project. The plugin enforces deterministic pipelines with JSON contracts, audio-led timelines, and multiple quality gates to ensure consistent demo video production.

5 agents · 9 skills · 2 MCP servers · 4 hooks
DevOps runs shell MCP hooks
#demo-video-generation#playwright-automation#voiceover-synthesis#video-editing

media-plugin

★ 3
lukaskellerstein

This plugin enables Claude Code to generate and manipulate diverse media assets—images, videos, GIFs, music, and text-to-speech—alongside data visualizations using Google Gemini, D3.js, Mermaid, and Draw.io. A visual-planning gate and media-prompt-craft workflow ensure every asset is clarified, styled, and reviewed before production.

2 commands · 1 agent · 10 skills · 5 MCP servers · 2 hooks
Design & Frontend runs shell MCP hooks
#media-generation#data-visualization#text-to-speech#mermaid-diagrams

pathmode

★ 3
pathmodeio

Pathmode runs deterministic preflights on feature requests before an agent builds, checking six calibrated gates without model calls or API keys, and optionally syncs intent specs with a team workspace. The plugin provides `/preflight` commands, intent compilation, code verification against agreed constraints, and product choice tracking—all using models you already have access to in Claude Code.

1 command · 9 skills · 1 MCP server · 1 hook
Project Management 🔑 needs API key runs shell MCP hooks
#intent-specs#preflight-gates#keyless-mode#product-decisions

design

★ 2
bromso

This Claude Code plugin implements a five-phase design thinking process for component design, with nine skills that write outputs to a Figma canvas via an MCP server, covering empathize, define, ideate, prototype, test, accessibility audit, design review, token export, and system overview. It requires a Figma access token and the `@metapowers/figma-mcp` MCP server to enable live integration with Figma.

9 skills · 1 MCP server · 2 hooks
Design & Frontend runs shell MCP hooks
#design-thinking#figma-integration#component-design#mcp-server

hookdeck

★ 2
hookdeck

This Claude Code plugin bridges webhooks from Hookdeck's Event Gateway into Claude sessions as channel events, allowing Claude to automatically react to GitHub, Stripe, CI, and monitoring webhooks. It provides a stable webhook URL, event replay, filtering, and inspection capabilities without requiring tunnel setup.

1 MCP server · 1 hook
Integrations runs shell MCP hooks
#webhooks#event-driven#github#stripe
lidapengpeng

This plugin automates academic paper review using methodologies from 10 top CS conferences (CVPR, NeurIPS, ICML, ICLR, ECCV, ICCV, ACL, AAAI, KDD, MICCAI), with venue-adaptive scoring across 8 dimensions, PDF parsing, reference verification, competitive paper analysis, and rebuttal assistance. It provides full review reports, fast pre-screening, and code-review capabilities, running 5 agents in parallel to assess novelty, technical correctness, experimental rigor, writing quality, reproducibility, and related work coverage.

3 commands · 4 agents · 1 skill · 2 MCP servers · 1 hook
Code Review 🔑 needs API key runs shell MCP hooks
#academic-paper-review#reference-verification#sota-comparison#venue-adaptive

scio

★ 2
evisoft

Scio is an AI-written encyclopedia where agents research, write, and verify articles with fully sourced claims and archived references. This plugin lets Claude agents read from Scio, propose new articles, sit on blind review panels, and contribute to the knowledge base while maintaining a rank and permission system verified live from the server.

8 commands · 4 agents · 1 skill · 2 MCP servers · 5 hooks
Search & Research runs shell MCP hooks
#ai-encyclopedia#sourced-claims#collaborative-review#agent-research

token-usage

★ 2
Wicked-Sick-Ltd

A token profiler that attributes Claude Code and Cowork usage to individual slash commands, skills, and subagents, providing per-activity breakdowns with cache-aware cost estimates across multiple AI runtimes including Codex, Cursor, Gemini CLI, and GitHub Copilot CLI. Supports cross-session history, live ledgers, budget alerts, and comparison modes to track where tokens are consumed in your workflows.

1 skill · 1 MCP server · 2 hooks
Productivity 🔑 needs API key runs shell MCP hooks
#token-tracking#cost-attribution#multi-runtime#cache-aware
allchemylabs

Aether WCAG Scanner finds accessibility violations on live URLs by rendering pages in Playwright across desktop, tablet, and mobile viewports and pairing each violation with corpus-backed fixes tied to WCAG 2.1 AA success criteria. It uses axe-core for deterministic measurement and the Allchemy Labs hosted insights engine to ground fix suggestions in WCAG techniques, with all scanning running locally and API access optional for enhanced fix generation.

1 skill · 1 MCP server · 2 hooks
Security runs shell MCP hooks
#wcag-accessibility#axe-core#browser-automation#fix-generation
alelaguard

This Claude Code plugin enforces LLM security guardrails by bundling the AgentGuards MCP server and enforcing hooks that scan prompts, authorize Bash commands, and redact web content in real time. It blocks jailbreaks, prompt injections, and data exfiltration with a fail-closed default and optional fail-open mode for availability-first deployments.

3 skills · 1 MCP server · 3 hooks
Security runs shell MCP hooks
#llm-security#jailbreak-detection#prompt-injection#data-exfiltration-blocking
djethino

This Claude Code plugin indexes past conversation transcripts and project files into a searchable vector database, enabling semantic and text search across your work history. It automatically captures snapshots of tracked files and provides recovery tools to restore context lost during session compaction or retrieve earlier versions.

3 skills · 1 MCP server · 4 hooks
Search & Research 🔑 needs API key runs shell MCP hooks
#memory-across-sessions#semantic-search#transcript-indexing#file-versioning

browserless

★ 1
browserless

A Claude Code plugin providing direct access to Browserless.io REST APIs for web automation, scraping, screenshots, PDFs, search, crawling, and Lighthouse audits through natural language slash commands and an interactive browser agent. The plugin integrates with the hosted Browserless MCP server for stateful browser sessions that can navigate, click, type, and handle multi-step flows like logins and file downloads.

9 skills · 1 MCP server · 1 hook
Integrations runs shell MCP hooks
#web-scraping#browser-automation#lighthouse-audit#web-search

dryas

★ 1
promprit

Dryas provides a workflow framework for Claude Code with extensible rules, scope management, and agent coordination via Jev chain architecture. It enables shell execution, command management, and hook-based automation across session and tool-use lifecycle events.

8 commands · 1 agent · 11 skills · 1 MCP server · 12 hooks
DevOps runs shell MCP hooks
#workflow-automation#agent-orchestration#hook-based-events#shell-execution
phamvuhoang

This plugin creates AI-powered marketing videos through a complete pipeline that takes a brief and automatically generates storyboards, images, video clips, background music, and lipsync effects using MuAPI's generative media APIs. Users can request videos directly from Claude Code (e.g., "Create a 30s TikTok for our coffee brand") and receive clip and music URLs ready for final assembly in a video editor.

1 skill · 1 MCP server · 1 hook
Marketing & Content runs shell MCP hooks
#video-generation#marketing-automation#image-to-video#suno-music

odoo-tools

★ 1
Transgenia

A Claude Code plugin providing unified Odoo tooling via an MCP server with automatic cross-version compatibility (Odoo 10–19, Community/Enterprise/online), exposing native operations like search, read, create, write, and export through a single stable tool surface. Includes a CLI fallback for scripted access and optional local sandbox deployment via Docker.

4 commands · 2 agents · 6 skills · 1 MCP server · 1 hook
Integrations 🔑 needs API key runs shell MCP hooks
#odoo-erp#mcp-server#cross-version-compat#json-rpc

speed-run

★ 1
2389-research

Speed-run is a token-efficient code generation pipeline that leverages Cerebras hosted LLM for fast first-pass generation, with Claude handling architecture and surgical fixes via three skills: turbo (direct codegen), showdown (parallel competition), and any-percent (parallel exploration). The plugin includes an MCP server, git worktree support, and test-driven development orchestration to reduce token costs by 60-70% compared to standard Claude workflows.

5 skills · 1 MCP server · 1 hook
Code Review runs shell MCP hooks
#code-generation#token-efficiency#parallel-agents#cerebras

agent-memory

★ 0
hsuanshao

This Claude Code plugin integrates long-term memory storage by recalling relevant memories before processing prompts and capturing conversation turns with secrets redacted. It requires a self-hosted Agent Memory server and uses MCP server communication with shell execution capabilities.

1 MCP server · 2 hooks
Productivity 🔑 needs API key runs shell MCP hooks
#long-term-memory#agent-memory#self-hosted#conversation-history

agentpowers

★ 0
AgentPowers-AI

This Claude Code plugin integrates the AgentPowers marketplace, enabling users to search, browse, install, and manage premium skills and agents directly in conversation through the `/ap` command and MCP tools. It provides proactive skill suggestions and maintains fresh marketplace context via session hooks.

2 skills · 1 MCP server · 3 hooks
Integrations runs shell MCP hooks
#marketplace#skill-discovery#agent-management#mcp-tools
EL-HAMDAOUI-Othmane

agent-reachout is a multi-provider notification plugin that sends Claude Code task completion and input requests to Telegram via webhooks on PreToolUse and Stop events. It requires Telegram bot credentials and the bun runtime to function.

1 MCP server · 2 hooks
Integrations MCP hooks
#telegram-notifications#multi-provider#real-time-alerts#task-completion-notifications
tonypk

Boss AI Agent is a management operating system featuring 14 mentor philosophies (Musk, Inamori, Jobs, and others) and 9 culture packs to automate daily team operations including check-ins, project health monitoring, and emergency response across Slack, Telegram, Gmail, GitHub, Linear, and Notion. It provides 7 automated management scenarios with data-driven meeting prep, sentiment analysis, and cross-channel briefings powered by Claude Code's command and agent framework.

9 commands · 3 agents · 1 skill · 2 MCP servers · 1 hook
Project Management 🔑 needs API key runs shell MCP hooks
#ai-management-os#mentor-philosophies#team-automation#multi-culture-packs

bruh

★ 0
oter

This Claude Code plugin orchestrates distributed Claude sessions across multiple projects and machines using agents for bigm, clankers, clerks, and workflow coordination. It integrates with Slack via bot token authentication and leverages shell execution with go and sh tools, plus MCP servers and lifecycle hooks for session management.

4 agents · 2 skills · 2 MCP servers · 8 hooks
Project Management runs shell MCP hooks
#claude-code-plugin#distributed-sessions#workflow-coordination#slack-integration

chisel

★ 0
crisog

Chisel is a Claude Code plugin that autonomously refines GitHub PRs by running parallel review loops against Greptile, automatically fixing findings and CI failures until all gates pass or a safety stop triggers. It integrates GitHub PR workflows with Greptile's review system, persisting loop state and enforcing success criteria like 5/5 confidence scores and zero unresolved comments.

4 commands · 1 skill · 1 MCP server · 4 hooks
Integrations runs shell MCP hooks
#pr-automation#code-review#greptile-integration#github-workflow
DhruvTilva

This plugin integrates Sentry error monitoring directly into Claude Code, enabling developers to triage, search, and fix production errors without leaving the IDE. It fetches real-time issue data from Sentry, analyzes stack traces with your source code, and proposes fixes through an interactive command-driven workflow.

1 agent · 3 skills · 1 MCP server · 1 hook
Security runs shell MCP hooks
#sentry-integration#error-triage#production-debugging#ai-root-cause-analysis

commonground

★ 0
serkanterek

CommonGround is a markdown wiki that Claude consults to answer questions with citations and writes to when instructed, keeping your team's or personal knowledge base current and accessible within Claude Code. The plugin manages version-controlled context storage and retrieval through its backend while curation runs on your own tokens.

7 commands · 1 skill · 1 MCP server · 4 hooks
Productivity runs shell MCP hooks
#wiki#knowledge-base#citations#team-collaboration

content-ops

★ 0
genaiunplugged14

content-ops automates the journey from research to publication by chaining four specialist agents through a research → draft → review → repurpose pipeline, turning one topic into a long-form article plus three platform-specific pieces in about 45 minutes. The plugin uses Perplexity for web research and Firecrawl for content extraction, runs five namespaced skills, and guards against dangerous commands while auto-formatting and quality-checking output.

4 agents · 5 skills · 2 MCP servers · 3 hooks
Marketing & Content runs shell MCP hooks
#content-pipeline#multi-agent#content-repurposing#brand-voice

devrunway

★ 0
manikumarkv

devrunway extends Claude Code with a full SDLC workflow, 35+ slash commands, 135 technology layers, and 35 safety/quality hooks that automatically enforce coding standards based on your configured tech stack. It auto-configures MCP servers for design tools, issue trackers, and code platforms, then loads only the relevant layer standards for files you edit.

7 agents · 37 skills · 7 MCP servers · 35 hooks
DevOps 🔑 needs API key runs shell MCP hooks
#sdlc-workflow#code-standards#multi-stack-support#mcp-auto-config

duker-brain

★ 0
DukeR-git

duker-brain dynamically routes each Claude Code prompt through an Obsidian vault, using a fast decision model to inject only the relevant note as context—typically in under a second. It provides 17 brain_* tools via MCP server for building, searching, and maintaining the hierarchical knowledge vault.

1 MCP server · 2 hooks
Productivity runs shell MCP hooks
#obsidian-vault#context-routing#dynamic-injection#knowledge-management

github-mcp

★ 0
adelaidasofia

A self-hosted GitHub MCP server written in Python that provides PR management, file operations, and Dependabot alerts via a small, audited tool surface authenticated with a personal access token. Works across Claude Code, Codex CLI, Cursor, and any MCP-compliant client without relying on platform-specific OAuth.

1 MCP server · 1 hook
Integrations 🔑 needs API key runs shell MCP hooks
#github-mcp#mcp-server#python#self-hosted
drewburchfield

This plugin bundles a HelpScout MCP server with 17 tools for searching support tickets, customers, and organizations, and provides a navigation guide to help users select the right tool for each task. It auto-starts when enabled and requires HelpScout API credentials to function.

1 skill · 1 MCP server · 1 hook
Integrations runs shell MCP hooks
#helpscout#mcp-server#support-tickets#customer-search

memex-garden

★ 0
WorldBrain

This plugin integrates Memex.Garden, a bookmarking second brain, into Claude, enabling you to save, search, transcribe, and summarize web content, PDFs, images, and social media directly within conversations. It uses Memex's hosted MCP server with OAuth authentication and includes a hook that auto-indexes URLs during prompt submission.

1 skill · 2 MCP servers · 1 hook
Integrations runs shell MCP hooks
#bookmarking#knowledge-base#mcp-server#memex-garden

pipelex

★ 0
Pipelex

Pipelex enables building and running AI methods defined in MTHDS format through 11 skills and custom tools, with a PostToolUse hook that validates every edit. The plugin requires a PIPELEX_PLUGIN_API_KEY and manages method execution via an MCP server.

11 skills · 1 MCP server · 2 hooks
Integrations 🔑 needs API key runs shell MCP hooks
#ai-methods#mthds-format#code-validation#mcp-server
Prometheus-AGS

The prometheus-skill-pack is a comprehensive skill system with 314 skills and 7 MCP servers for process orchestration, React development, GitOps, testing, research, and learning workflows. It integrates with Tavily for research capabilities and provides portable agent tooling through hooks and shell execution.

314 skills · 7 MCP servers · 30 hooks
Productivity runs shell MCP hooks
#skill-pack#process-orchestration#gitops#mcp-servers

pushnotifi

★ 0
thetawavetechnologies

A Claude Code plugin that bundles the PushNotifi.me MCP server to enable human-in-the-loop approvals and operational alerts on your phone through the PushNotifi service. It includes skills for scaffolding workflows, recipes, and slash commands for bootstrapping Node projects with approval workflows.

2 commands · 3 skills · 1 MCP server · 1 hook
Integrations runs shell MCP hooks
#human-in-the-loop#approvals-alerts#mcp-server#pushnotifi

spoki

★ 0
Spoki-App

Spoki integrates the Spoki WhatsApp Business Platform into Claude, enabling you to send messages, manage contacts, create campaigns, build automations, and analyze reports entirely through natural conversation. It provides 59 tools organized across contacts, automations, campaigns, templates, messaging, webhooks, and analytics, backed by two specialized agents for campaign management and customer support setup.

2 agents · 5 skills · 1 MCP server · 1 hook
Integrations runs shell MCP hooks
#whatsapp-integration#marketing-automation#crm-contacts#campaign-management
tomstagl

thunderstruck is a resilience forensics tool that ranks fragile hotspots in your codebase and explains their failure modes—trigger, amplifier, sustaining effect—with evidence resolved to specific file:line locations and commit SHAs. It combines deterministic script-based analysis for detection and validation with Claude's judgment to form and verify falsifiable hypotheses about production failures.

1 agent · 4 skills · 1 MCP server · 1 hook
Code Review 🔑 needs API key runs shell MCP hooks
#resilience-forensics#hotspot-analysis#failure-mode-detection#production-risk

trapic

★ 0
nickjazz

Trapic auto-recalls shared team knowledge at the start of each coding session and captures new decisions to a centralized knowledge base accessible across AI tools like Claude Code, Cursor, and GitHub Copilot. It detects conflicting decisions and applies smart decay to flag stale knowledge, enabling teams to maintain alignment without manual briefing.

6 skills · 1 MCP server · 1 hook
Integrations runs shell MCP hooks
#context-recall#knowledge-base#team-brain#smart-decay

velixar

★ 0
VelixarAi

Velixar gives Claude Code persistent memory across sessions, storing decisions, architecture details, and coding conventions while automatically detecting contradictions between current and past context. The plugin builds a knowledge graph of your project over time through both manual memory commands and automatic smart-remember behaviors triggered during conversations.

1 agent · 6 skills · 1 MCP server · 1 hook
Productivity MCP hooks
#persistent-memory#knowledge-graph#context-recall#contradiction-detection

voice-loop

★ 0
saharkit

voice-loop provides two-way voice interaction with Claude Code through pluggable speech providers—choose from OpenAI, ElevenLabs, Deepgram, or run STT/TTS locally (faster-whisper, Silero, XTTS-v2, Ukrainian voices) by editing a config entry. A Stop hook speaks marked lines, a push-to-talk hotkey transcribes speech into any application, and /voice-setup configures and tests the entire setup.

6 skills · 1 MCP server · 2 hooks
Integrations runs shell MCP hooks
#voice-assistant#speech-recognition#text-to-speech#pluggable-providers

waggle

★ 0
Waggle-AI

Waggle enables discovery and invocation of A2A protocol agents directly from Claude Code through semantic search and agent registry tools. The plugin connects to the Waggle search engine to find agents by capability, retrieve details, invoke tasks, and register new agents.

4 skills · 1 MCP server · 1 hook
Integrations runs shell MCP hooks
#agent-discovery#a2a-protocol#agent-integration#agentic-internet