20,861 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
cyanheads/wikipedia-mcp-server
Plugin Claude Code
Bundles 33 skills, 1 MCP server · 2,455 tokens together
Search Wikipedia articles, read summaries and full text, target sections, find nearby pages, and list language editions via MCP. STDIO or Streamable HTTP.
Plugin Claude Code
Bundles 33 skills, 1 MCP server · 2,458 tokens together
Search and retrieve researcher profiles, works, affiliations, funding, and peer review records from the ORCID registry via MCP. STDIO or Streamable HTTP.
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Search and query government open-data portals (Socrata SODA API) via MCP. STDIO or Streamable HTTP.
jbechtel-97/dealflowpro-mcp-server
Plugin Claude Code
Multifamily real estate underwriting — cap rate, DSCR, cash-on-cash, IRR, DFP Score (0-100), max offer price, and market intelligence for 2-200 unit properties, plus access to your saved deals, buy-box criteria, and portfolio.
Plugin Claude Code
Bundles 7 skills, 1 hook · 1,444 tokens together
The integration layer a product needs once it has users: Stripe subscription billing reconciled into your own database, crypto payments that survive over-payment and duplicate webhooks, ad and conversion tracking under Consent Mode v2, Google sign-in with the account-linking guards, the wider Google auth surface, and…
Plugin Claude Code
Bundles 11 skills, 1 agent · 673 tokens together
AI sales rep that runs your outbound from Claude Cowork or Claude Code. Point it at your homepage: it builds a prospect list, reads each company's site, writes and sends one email per company from your own mailbox (Gmail, Google Workspace or SMTP), and turns every reply and rejection into structured data that sharpens.
Plugin Claude Code
Bundles 1 skill · 182 tokens together
Second opinions: iterative adversarial debates between Claude and Codex over any subject, from specs, designs, and code to non-technical positions, ending in genuine agreement or a documented dispute.
Plugin Claude Code
Bundles 1 skill, 5 hooks · 61 tokens together
Local cat-GIF break reminder banners for long vibe-coding sessions.
Plugin Claude Code
Bundles 1 skill · 34 tokens together
A connector for operating Fugaku, a Japanese supercomputer operated by RIKEN, through plain-language requests. It uses Fugaku's official web service and an X.509 certificate, a file used to prove your identity securely.
Plugin Claude Code
Bundles 9 skills, 3 MCP servers · 261 tokens together
AdsAgent tri-channel Claude plugin: hosted MCP connections (Meta, Google Ads, TikTok) plus behavior skills for safer ad operations.
Plugin Claude Code
Bundles 4 skills · 931 tokens together
Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent…
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 123 tokens together
NVEIL is an AI-powered data-processing and visualization toolkit — describe joins, aggregations, pivots, resampling, geocoding, time-series analysis, feature engineering, 2D/3D charts, geospatial maps, voxel/volume rendering, medical imaging, and more in plain language; the toolkit plans remotely and executes entirely.
Plugin Claude Code
Bundles 5 skills, 1 MCP server · 223 tokens together
Skills and hosted MCP server for BlitzReels editing, generation, clipping, X-to-video workflows, and carousels.
Plugin Claude Code
Tree of Thoughts reasoning, deep planning, and plan management for Claude. Adds sequentialthinking, deepplanning, listplans, getplan, promoteplan, archiveplans.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
MCP server for FTP/FTPS/SFTP operations — full FileZilla feature set for AI agents. 36 tools for connecting, navigating, transferring, syncing, searching, and managing remote file servers.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 48 tokens together
An MCP control plane for Claude Code: swallow other MCP servers through one gateway, delegate to Codex/Gemini/Claude on your own CLI subscriptions, plus a RAG memory graph, reference study, and cross-session handoffs. Optional all the way down, secret-free, fail-closed.
Plugin Claude Code
Bundles 1 skill, 2 commands, 1 MCP server · 241 tokens together
Finn og hent norske offentlige data fra data.norge.no, rett fra Claude Code. MCP-server + /finn-datakilde-skill som leter iterativt i Felles datakatalog og alltid henter fram lisens- og krediteringskrav.
Plugin Claude Code
Bundles 6 skills · 435 tokens together
6 skills, 108 palettes, 53 styles, 14 layouts, a 29-rule detector, and one house motion language. The opposite of generic AI slop.
benigeri/braintrust-claude-plugin
Plugin Claude Code
Bundles 1 skill, 1 command · 43 tokens together
Claude runtime adapter for shared Braintrust CLI commands.
Plugin Claude Code
Bundles 32 skills · 3,780 tokens together
Skills for presales and demo engineers running Dynamicweb 10 demos. The skills are the substrate; the build is driven by a swappable orchestrator (GSD primary, or the native /demo: command set) — see dw-demo-base/references/orchestrator.md.
gautam-achieveai/ClaudePlugins
Plugin Claude Code
Bundles 11 skills, 2 commands, 1 agent · 551 tokens together
Development methodology toolkit: design-first brainstorming, autonomous design with review-planning and implementation-handoff steps, test-driven development, parallel subagent-driven execution with review gates, evidence-based completion verification, severity-and-cost triage for acting on received code review…
Plugin Claude Code
Bundles 2 skills · 196 tokens together
Automatated testing framework.
Plugin Claude Code
Bundles 1 skill, 7 commands · 182 tokens together
High-signal technical learning. Language mastery, system design, codebase dissection, and deliberate practice.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Manual QA runs driven through a browser — derive the scenarios from the ticket and the diff or execute the list you were handed, write them down as a scenario file under docs/qa/ / with the test data they need, preconditions and dependencies, execute them with Playwright in a QA window that stays open between runs.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: