Building agents plugins

3,758 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 276cli 122cursor 103agents 102ai-coding 87LLM 86agentic-ai 75ai-tools 70skills 70agent-orchestration 53agent 50agentic-workflow 45claude-code-plugins 43Multi-Agent 42

skillcp

2713

lum1n/skillcp

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 46 tokens together

One library for Agent Skills and MCP servers, synced to every AI coding harness, plus a localhost GUI.

not rated 0 23d ago A tokens not measured original MIT

mcp-questionnaire

2716

JakubMMazurek/MCP-Questionnaire

Plugin Claude Code

Bundles 1 skill · 100 tokens together

Structured input surfaces inside the Claude conversation — prefilled forms, assumption ledgers, review matrices — instead of clarifying questions as prose. Connector + skill in one install.

not rated 0 changed 4d ago A tokens not measured

sexai

2718

sxaidev/sxai-mcp

Plugin Claude Code

Bundles 1 MCP server

SEXAI — where AI agents breed. Discover agents, publish yourself (or import a GitHub repo as an agent), breed (mix 2+ → a new agent that inherits both parents' skills/MCPs/soul), export an agent back to a standard repo, and optionally register an ERC-8004 on-chain identity. 18 tools; the tool definitions are the…

not rated 0 1mo ago A tokens not measured original MIT

engineering-board

2719

GhostlyGawd/engineering-board

Plugin Claude Code

Bundles 6 skills, 21 commands, 8 agents, 4 hooks, 2 MCP servers · 1,631 tokens together

Git-committed pattern intelligence for engineering agents. Bounded context retrieval surfaces systemic evidence before a fix. Explicit H### outcomes improve later L### Learning state. Includes passive capture, stable P### identities, atomic claims, and a zero-dependency 19-tool MCP server over canonical Markdown.

not rated 0 changed 4d ago A tokens not measured original MIT

aiss-consult

2720

Un3x/ai-success-story

Plugin Claude Code

Bundles 1 skill, 1 hook, 1 MCP server · 55 tokens together

Consult prior AI war-stories before answering coding/deploy/debug/refactor/review tasks. Bundles the AI Success Story MCP server (searchstories, fetchstory).

not rated 0 3mo ago A tokens not measured original MIT

eskill

2723

hedralab/eskill

Plugin Claude Code

Bundles 3 skills · 254 tokens together

Quy trình tạo Agent Skill chuẩn top-1.

not rated 0 20d ago A tokens not measured

claude-session-bus

2726

exalsch/claude-session-bus

Plugin Claude Code

Bundles 1 hook

Broadcast bus for peer Claude Code sessions: a broadcast() MCP tool to send and a UserPromptSubmit hook to receive, over JSONL mailboxes scoped to one project, a group of projects, or the whole machine.

not rated 0 28d ago A tokens not measured GPL-3.0

aris4u

2727

aris4u-dev/aris4u

Plugin Claude Code

Bundles 25 skills, 15 agents, 7 hooks, 1 MCP server · 4,063 tokens together

Amplificador consciente del modelo sobre Claude Code: rutea Fable/Opus/Sonnet/Haiku por dificultad de subtarea (auto-inyecta model=), mide costo/disciplina de routing, adapta el recall al modelo, y guarda su propia memoria (texto propio, desacoplado de claude-mem). 24 hooks (7 eventos), 7 MCP tools, guards 2…

not rated 0 2mo ago A tokens not measured

agentmods marketplace

2728

iOSDevSK/find-mods

Plugin Claude Code

Lists 1 plugin

The agentmods.dev catalogue, reachable from inside your agent: every mod measured for what it costs you per session, scanned for what it does, and traced to whoever wrote it first.

not rated 0 changed 5d ago A tokens not measured original MIT

agentic-commerce-tools

2730

f-tiger/sellSomething

Plugin Gemini CLI

Agentic-commerce readiness tools: scan any website for AI-agent visibility and health-check remote MCP servers, via the agiscorecard remote MCP endpoint.

not rated 0 yesterday A tokens not measured

agent-delegation

2733

artcar12/agent-delegation-mcp

Plugin Claude Code

Bundles 2 MCP servers

Delegates long-running coding and research tasks to the OpenCode and Antigravity (agy) CLIs as unattended MCP subagents. Fails fast on provider quota walls instead of blocking for the full hour, kills hung delegates on an idle timer, and reports whatever the delegate wrote to .agent-runs/ on every exit path.

not rated 0 changed 2d ago A tokens not measured copy · 89% MIT