ai-agents plugins

3,222 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 236claude-code-plugin 220LLM 183cli 139agents 135agents-md 109prompt-engineering 108Science 99ai-coding 82ai-tools 75agentic-coding 61skills 56mcp-server 53agent-orchestration 51

make-it-real

745

Geo-ff/make-it-real

Plugin Claude Code

Bundles 1 skill · 175 tokens together

Guided discovery skill for turning vague ideas into project specs, delivery scopes, and AI-agent handoffs.

not rated 15 +1 2mo ago A tokens not measured original MIT

tray-api

746

tray-tecnologia/tray-api-ai-plugin

Plugin Claude Code

Bundles 36 skills, 3 commands, 5 agents, 1 MCP server · 2,997 tokens together

Plugin completo para integração com as APIs da Tray. Acelera o desenvolvimento de aplicativos e-commerce por parceiros e comunidade na plataforma Tray, fornecendo documentação detalhada de todos os endpoints, fluxos de autenticação OAuth, webhooks e boas práticas de integração.

not rated 15 +1 25d ago A tokens not measured original MIT

tradecraft

747

mahmoud20138/Tradecraft

Plugin Claude Code

Bundles 58 skills · 5,740 tokens together

169 curated AI skills across trading, AI development, software engineering, Claude Code platform, data acquisition, and domain knowledge. Each skill becomes a slash command like /tradecraft: .

not rated 15 +1 4mo ago A tokens not measured original MIT

axme-code

749

AxmeAI/axme-code

Plugin Claude Code

Bundles 1 MCP server

(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.

not rated 14 19d ago A tokens not measured original MIT

swarm

750

zircote-plugins/claude-team-orchestration

Plugin Claude Code

Bundles 10 skills, 5 agents · 721 tokens together

Multi-agent orchestration for Claude Code. Coordinate teams of agents with shared tasks, messaging, and 7 proven patterns including RLM for large-file analysis beyond context limits.

not rated 14 1mo ago A tokens not measured original MIT

conquistador

751

forsvn-labs/meta-skills

Plugin Claude Code

Bundles 21 skills · 1,248 tokens together

A senior product-marketing and growth teammate with compact capabilities for research, positioning, campaigns, creative, copy, social, search, conversion, measurement, and Vietnamese.

not rated 14 27d ago A tokens not measured original MIT

open-skills

752

allemaar/open-skills

Plugin Claude Code

Bundles 58 skills · 6,912 tokens together

Reusable, inspectable skills for AI coding agents. Every skill has a readable SKILL.md; 40 of 68 also carry a declarative protocol.yon whose structure can be validated with @younndai/yon-parser. Validation does not enforce runtime obedience. A personal project by Alexandru Mares, separate from the YounndAI™ product…

not rated 14 20d ago A tokens not measured original Apache-2.0

analyzer

755

a-ariff/ariff-claude-plugins

Plugin Claude Code

Bundles 1 agent · 30 tokens together

Code analysis and metrics specialist. Use for codebase analysis, complexity metrics, dependency analysis, and generating insights about code quality and structure.

not rated 14 5mo ago A tokens not measured original MIT

uitkit marketplace

758

UitbreidenOS/UitKit

Plugin Claude Code

Lists 3 plugins

The Claude Code knowledge system — 377+ skills, 104 agents, hooks, MCP configs, and project structures across every professional domain.

not rated 14 2mo ago A tokens not measured

magician

759

Alexander-Tyagunov/magician

Plugin Claude Code

Bundles 26 skills, 4 agents, 10 hooks · 1,522 tokens together

Full-stack SDLC plugin with dynamic project inspection, a local code knowledge-graph + cache, cross-session reference memory, self-learning, parallel agent orchestration, and feature comprehend→port/integrate (/transmute).

not rated 14 changed 3d ago A tokens not measured original MIT

product-on-purpose/thinking-framework-skills

Plugin Claude Code

Bundles 68 skills, 10 commands, 1 agent · 7,532 tokens together

An evidence-graded library of agent-executable thinking-method skills (premortem, problem restatement, and more). Each skill is reduced to its working mechanism, graded honestly on how strong its evidence actually is, and produces a concrete artifact rather than prose. Use to reframe a problem, challenge assumptions…

not rated 14 21d ago A tokens not measured original Apache-2.0

codebase-ai-readiness

763

krokoko/cairn

Plugin Claude Code

Bundles 2 skills, 1 hook · 114 tokens together

Assess how AI-friendly a codebase is and produce an autonomy maturity map with scores, blockers, and a roadmap.

not rated 14 +1 3d ago A tokens not measured original Apache-2.0

engine

764

playcanvas/skills

Plugin Claude Code

Bundles 16 skills · 789 tokens together

Skills for building applications with PlayCanvas Engine.

not rated 14 +1 changed 2d ago A tokens not measured original MIT

gregkozakiewicz/roast-my-design-system

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 161 tokens together

Roast your repo's design system with real data: a health score, the receipts behind it (every colour, spacing value, duplicated component and inline style), and the first fixes ranked by payoff. Deterministic scanner, benchmarked against 29 public repos and 10 reputable design systems, one shareable light/dark HTML…

not rated 14 changed yesterday A tokens not measured original MIT

pets

767

TevvvB/termagitchi

Plugin Claude Code

Bundles 2 skills · 65 tokens together

A creature for every agent session, in a den for every git worktree. Its mood tracks how tidy that worktree is, so several agents at once stay tellable apart at a glance.

not rated 14 2d ago A tokens not measured original MIT

pome-coach

768

pome-sh/digital-twins

Plugin Claude Code

Bundles 6 skills · 493 tokens together

The Pome coach skill set — register an agent, author and verify graded tasks, run them against the digital twins, and read the scored report.

not rated 14 yesterday A tokens not measured original Apache-2.0

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: