LLM plugins

536 tagged LLM, measured the same way as everything else here.

Browse within: prompt-engineering 54Science 30agents-md 30knowledge-base 21local-first 18openai 17self-hosted 14gemini 13agent-memory 12agentic 12LangChain 10cli-agent 10code-agent 10knowledge-graph 10

lid-experimental

121

jszmajda/lid

Plugin Claude Code

Experimental LID skills with opt-in installation and explicit lifecycle (promotion or retirement). Layers on top of linked-intent-dev and arrow-maintenance.

100 21d ago A tokens not measured original MIT

skills

122

denoland/skills

Plugin Claude Code ✓ vendor

Modern Deno development knowledge: dependency management, npm and JSR packages, permissions, the built-in toolchain, migrating from Node/npm/yarn/pnpm/bun, Fresh, and Deno Deploy.

96 1mo ago A tokens not measured original MIT

mb

123

frankchu91/mindbase-llm-wiki

Plugin Claude Code

Karpathy's LLM-Wiki pattern as a Claude Code plugin. Build and maintain a persistent, AI-tended research wiki from sources, capture daily thoughts, query what you know, lint for orphans and contradictions. Operations: /mb:init, /mb:contribute, /mb:build, /mb:ask, /mb:lint, /mb:status, /mb:research, /mb:daily-brief…

91 +2 8d ago A tokens not measured original MIT

mcp-stata

125

tmonk/mcp-stata

Plugin Claude Code

mcp-stata - an agentic toolkit for empirical researchers. Gives AI agents native control over a local Stata installation, allowing agents to run do-files, inspect data, check stored results, and export graphs.

81 3mo ago A tokens not measured AGPL-3.0

komi-learn

126

kurikomi-labs/komi-learn

Plugin Claude Code

A continuous, zero-friction learning layer: the agent learns about you and improves its own skills across every session, and can share anonymized, provenance-verified learnings to a global pool. Inspired by Hermes Agent.

79 2mo ago A tokens not measured original MIT archived

frontier

127

apoorvjain25/frontier

Plugin Claude Code

Standards written and audited by Claude Fable 5: make Opus, Sonnet, GPT, or Gemini produce work close to its bar. 21 craft rubrics, best-of-N candidates, convergence sweeps, a taste gate with permanent distillation.

79 +1 1mo ago A tokens not measured original MIT

skills

128

serac-labs/serac

Plugin Claude Code

400+ snow MCP tools for ServiceNow, plus the 70 skill guides that teach an agent to use them.

78 7d ago A tokens not measured original Apache-2.0

fire-flow

129

ThierryN/fire-flow

Plugin Claude Code

Research-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and adversarial review. 51 commands, 15 agents across 7 departments.

77 20d ago A tokens not measured original MIT

claude-code

131

synadia-ai/synadia-agents

Plugin Claude Code

NATS channel plugin for Claude Code — bridges NATS messaging to Claude Code sessions.

76 3d ago A tokens not measured original Apache-2.0

test-plugin

132

genai-io/san

Plugin Claude Code

A test plugin for UI/UX comparison testing between Claude Code and San.

75 5d ago A tokens not measured original Apache-2.0

jmagar/claude-homelab

Plugin Claude Code

Plugin marketplace listing 26 plugins: homelab-core, overseerr-mcp, unraid-mcp, unifi-mcp, gotify-mcp.

73 28d ago A tokens not measured original MIT

claude-homelab

134

jmagar/claude-homelab

Plugin Claude Code

Core homelab agents, commands, and setup/health skills for self-hosted service management. Includes interactive credential setup wizard and unified service health dashboard.

73 28d ago A tokens not measured original MIT

claude-code

136

major7apps/pensyve

Plugin Claude Code

Universal memory runtime — ambient working-memory substrate for Claude Code. Memory is not a feature you invoke — it's the substrate the agent operates on.

72 4d ago A tokens not measured

cowork-os

137

yempik-ai/cowork-os

Plugin Claude Code

Turn a Claude Cowork project into a company brain your team owns: guided setup, a Memory Update protocol, a knowledge-transfer interview, a senior strategy skill, a decision lifecycle with daily signal sweeps and a weekly Decision Radar, a sales/pipeline follow-up layer, a LinkedIn editor, mission mode, and recurring…

70 +2 1mo ago A tokens not measured original MIT

llm-wiki-manager

138

sametbrr/llm-wiki-manager

Plugin Claude Code

Personal LLM-managed wiki: ingest sources, cross-reference pages, query with citations, and lint your markdown knowledge base.

69 +1 2mo ago A tokens not measured original MIT

string

140

string-os/string

Plugin Claude Code

Use String apps and the web through one MCP tool. Install an app from a GitHub URL, read pages as markdown, run typed actions on documents — the whole String runtime exposed as a single mcpstringstring tool, with a skill that teaches Claude when and how to use it.

66 +1 14d ago A tokens not measured original MIT

Satori

141

MetcalfSolutions/Satori

Plugin Claude Code

Clinically informed wisdom companion for navigating the inner life — emotions, meaning, grief, purpose, relationship, identity. Draws on eight wisdom traditions and modern clinical psychology to create conversations that produce real insight and real movement.

66 +3 4mo ago A tokens not measured original Apache-2.0

marketplace

143

magnus919/agent-skills

Plugin Claude Code

AI agent skills — reusable workflows, protocols, and knowledge packs for agentic systems.

64 3d ago A tokens not measured original MIT

free-search

144

sweetcornna/free-search-mcp

Plugin Claude Code

Local-first, no-API-key web search, fetching, and document reading — 11 MCP tools, no signup and no key.

61 +2 3d ago A tokens not measured original MIT