Claude Code plugins

Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.

archhub

claude

국토교통부 건축HUB → MCP. 건축물대장·건축인허가·주택인허가 + 법정동코드 + 용도지역 포함 종합카드 + 층별 구성 + 동 단위 통계·규모 벤치마크 + 노후건축물 + 공시가격 시계열 + 철거멸실(석면) + 인허가 파이프라인. URL만 등록하는 remote 커넥터

1 MCP server

chrisryugj/archhub-mcp 77

Source-cited Obsidian brain for YouTube across three pillars: creator growth and strategy (recommendation, retention, packaging, Shorts, monetization, analytics, community), the developer API (Data, Analytics, Reporting, Live Streaming), and paid advertising (Google Ads, Demand Gen, bidding, targeting, brand suitability).

1 skill

AgriciDaniel/youtuber 77

One topic in, one ranked YouTube research workbook out. Searches YouTube Data API v3, ranks videos by views, engagement, momentum, or breakout, and writes Videos, Channels, Summary, Comments, and Transcripts sheets with hooks and replay hotspots.

1 skill

AgriciDaniel/youtube-scout 77

Asana

claude

Access Asana tasks, projects, sections, and comments — list, search, create, and update.

1 skill

anthropics/claude-tag-plugins 77

abnormal

claude

The full Abnormal Security REST API as an agent-native CLI — with a local threat store, ranked SOC triage, and one-shot reporting no SOAR pack offers.

1 skill

Servosity/msp-skills 77

acronis

claude

The first real CLI for the Acronis Cyber Protect Cloud platform — every tenant, agent, and usage metric mirrored locally, with cross-tenant rollups no single API call returns.

1 skill

Servosity/msp-skills 77

action1

claude

Every Action1 endpoint, plus the fleet-wide patch and vulnerability views the org-siloed API cannot give you.

1 skill

Servosity/msp-skills 77

Search the web and primary sources, read pages behind your logins, verify citations. Runs locally. Lenses for trusted sites, plus SEC filings, court records, patents, clinical trials and full-text papers. Opt-in encrypted logins let it read pages you can already open, such as LinkedIn or X. Checks that each citation exists, was not retracted, and says what is claimed. Keeps sessions, saved searches and memory across chats.

1 MCP server

zoharbabin/web-researcher-mcp 77

lakutata

claude

The official skill of the lakutata framework: writing, testing and upgrading applications built on lakutata 3.x

1 skill

lakutata/lakutata 77

Multi-agent orchestration - spawn and control parallel Claude sessions

QuivrHQ/247-claude-code-remote 77

honcho

claude

Persistent memory for Claude Code sessions using Honcho

plastic-labs/claude-honcho 77

Complete system: 15 problem-shaped skills backed by 97 genius agents, 86 skills total, 30 commands, 71 tools, 36 hooks, authoritative coding-standards rules, goal-driven and autonomous build loops, and the shared Claude Code and Codex gates

21 skills · 30 commands · 1 MCP server · hooks

cdeust/Cortex 76

Cortex — persistent memory and cognitive profiling for Claude Code (renamed from the 'cortex' plugin in v4.15.0 to match the PyPI/MCP-registry identity hypermnesia-mcp) — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. These mechanisms are implemented and inspectable; committed ablations do not establish a retrieval gain from all 36 mechanisms. 57 MCP tools (60 with the optional ai-architect-mcp-codebase + ai-architect-mcp-spec integrations) with enriched schemas (visualization extracted to the standalone Hypermnesia MCP Viz server). PostgreSQL + pgvector in CLI mode; automatic SQLite fallback in Cowork/sandboxed mode. v3.17.0 — autonomous per-project wiki: SessionStart auto-spawns a 6-hour consolidate cycle; a headless `claude -p` worker drains the curation-gap queue, calls codebase-intelligence MCP tools to ground each section in the real call graph, and authors missing anchor pages (architecture / services / api / data-flow / operations / decisions / PRD) per project from the source tree. 15 canonical scopes × 13 file sections; per-project dashboards under `wiki/_dashboards/`. Mermaid diagrams have a 🔍 lens with zoom + pan. Workflow graph with caller-qualified CALLS chains rendering full method-to-method dependencies (native tree-sitter, no AP required). Side panel humanized for non-technical users. Ingests codebase analysis (ai-architect-mcp-codebase) and PRDs (ai-architect-mcp-spec) into wiki + memory + knowledge graph. Docker image available.

13 skills · 3 commands · 1 MCP server · hooks

cdeust/Cortex 76

crg

claude

Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

7 skills · 1 MCP server · hooks

n24q02m/crg 76

sous-chef

claude

Claude orchestrates and reviews; Sonnet, Codex, GLM, or Grok implements. Your head chef doesn't chop onions.

7 skills

tomascupr/sous-chef 76

Persistent local memory: temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. 79 MCP tools, zero LLM calls in the hot path, nothing leaves the machine.

5 skills · 1 MCP server · hooks

vbcherepanov/total-agent-memory 76

Six Spytrend workflows for advertising intelligence, advertiser research, webmaster analysis, website review, keyword search, and shop discovery.

6 skills · 1 MCP server

Spytrend/spytrend-mcp 76

pensieve

claude

Semantic search over your repos, documents and past agent sessions, for Claude Code.

4 skills · 1 MCP server · hooks

TedHaley/pensieve 76

Canonical Claude Code publication for the standalone Hypermnesia MCP Viz server — a live neural-graph galaxy of every project, file, symbol, memory, discussion and wiki page, plus a per-session execution trace, a consolidation kanban, and a curated knowledge/wiki browser. Read-only bridge over Cortex's shared PostgreSQL store and the ~/.claude artifacts; it renders, it never remembers. Restores the open_visualization and get_methodology_graph tools removed from Cortex; launch with /cortex-visualize.

1 skill · 1 MCP server · hooks

cdeust/Cortex 76

adsctl

claudecodex

Set up adsctl and inspect, report on, monitor, and manage Meta advertising.

3 skills

imrenagicom/adsctl 76

Official Gradle skills for AI coding agents: audit a build against Gradle best practices, and upgrade the Gradle wrapper.

2 skills

gradle/gradle-skills 76

Runs ipybox without sandbox-runtime

1 skill

gradion-ai/ipybox 76

Runs ipybox with sandbox-runtime

1 skill

gradion-ai/ipybox 76

Runs ipybox as a Docker container

1 skill

gradion-ai/ipybox 76

Operating doctrine for AI-era enterprise sales. Use when an agent works on accounts, deals, outreach, coaching, or pipeline — any revenue-affecting decision.

1 skill

vonarmen-wq/forward-deployed-selling 76

skills

claude

Ishu Agrawal's Agent Skills (video-by-reference, ...)

1 skill

ishuagrawal/skills 76

Vídeos de motion design por código com trilha, narração e QA automático.

1 skill

dev-isaacmello/extreme-motion-design 76

818 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more. Mapped to 6 frameworks.

200 skills

costrict-plugins-repo/mukul975-anthropic-cybersecurity-skills-cybersecurity-skills 75

ase

claudecodex

Agentic Software Engineering (ASE)

60 skills · 11 agents · 1 MCP server · hooks

rse/ase 75

Free open-source OSINT and investigation toolkit for Claude Code: case workflow, 54 OSINT adapters, structured analysis, chain-of-custody evidence capture, threat-intel MCP servers.

6 skills · 24 commands · 1 agent · hooks

assafkip/investigators-copilot 75