Building agents plugins

3,708 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 306agents 99cli 98ai-coding 95LLM 83agentic-ai 82ai-tools 73skills 71Multi-Agent 49agent-orchestration 49agent 46agentic-workflow 46claude-code-plugins 42claude-code-skills 37

dcode-agent-kit

482

EliaAlberti/dcode-agent-kit

Plugin Claude Code

Bundles 1 skill · 109 tokens together

Scaffold a Deep Agents (LangChain) agent or a dcode CLI agent from one command (/new-dcode-agent). The agents it builds work with any OpenAI-compatible provider.

not rated 58 2mo ago A tokens not measured original MIT

blueprint-plugin

483

laurigates/claude-plugins

Plugin Claude Code

Bundles 35 skills · 1,362 tokens together

Blueprint Development methodology - structured feature development with PRD/PRP workflow, three-layer architecture (plugin/generated/custom), and documentation-first development.

not rated 58 +1 changed 3d ago A tokens not measured original MIT

trustabl

484

trustabl/trustabl

Plugin Claude Code

Bundles 2 skills, 1 agent, 1 hook, 1 MCP server · 310 tokens together

Self-audit AI agent, tool, and MCP-server code for security and reliability misconfigurations with Trustabl, the agent reliability scanner for the OpenAI Agents SDK, Claude Agent SDK, Google ADK, and MCP. Ships two skills (trustabl-scan and trustabl-enrich) and a subagent (trustabl) that together form a scan → enrich…

not rated 58 +11 2d ago A tokens not measured original Apache-2.0

kkirikkiri

487

fivetaku/kkirikkiri

Plugin Claude Code

Bundles 1 skill, 1 command, 4 hooks · 45 tokens together

Natural language team builder for Claude Code — one sentence becomes an AI team (Agent Teams) or a deterministic agent pipeline (Workflows). User picks the execution substrate; models are tiered (Opus lead/judge, Sonnet workers, cross-model review via Codex/agy).

not rated 57 changed yesterday A tokens not measured original MIT

pomodoro

489

jakedahn/pomodoro

Plugin Claude Code

Bundles 1 skill · 54 tokens together

System Skill reference implementation showing how to build Claude Skills with persistent memory. Demonstrates the CLI + SKILL.md + Database pattern for creating tools that learn and improve over time.

not rated 56 10mo ago A tokens not measured original MIT

skillreaper

493

thousandflowers/skillreaper

Plugin Claude Code

Bundles 2 skills · 104 tokens together

Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.

not rated 56 +1 changed 3d ago A tokens not measured original MIT

workflowx

495

TreeX-X/WorkFlowX

Plugin Claude Code

Bundles 1 plugin

Multi-agent orchestration framework with Socratic requirements discovery, Hybrid Tree PRD management, and structured quality evaluation.

not rated 55 7d ago A tokens not measured original MIT

sc

496

SuperClaude-Org/SuperClaude_Plugin

Plugin Claude Code

Bundles 32 commands, 20 agents · 844 tokens together

Transform Claude Code into a structured development platform with 29 /sc: commands, 23 specialized agents, 7 behavioral modes, and MCP server integration.

not rated 55 16d ago A tokens not measured original MIT

Teradata/teradata-mcp-server

Plugin Claude Code

Bundles 1 skill · 90 tokens together

Build, edit, and debug a semantic layer for the Teradata MCP server — custom tools, cubes, prompts, and glossary entries declared in YAML, plus the profiles.yml that exposes them.

not rated 55 +1 3d ago A tokens not measured original MIT

localvoxtral-remote

503

T0mSIlver/localvoxtral

Plugin Claude Code

Bundles 5 hooks

Publishes Claude Code session context from a REMOTE host to localvoxtral on your Mac, over an SSH RemoteForward tunnel. Command hooks running a bundled POSIX-sh shim that POSTs via curl — needs only sh and curl on the remote host, and fails open silently when either is missing.

not rated 54 changed today A tokens not measured original MIT

parable

504

Parcha-ai/parcha-skills

Plugin Claude Code

Bundles 1 skill, 1 plugin · 115 tokens together

Multi-model orchestration or explicit solo execution: route work across capable models, or run one exact proxy model with delegation disabled.

not rated 54 +34 yesterday A tokens not measured original MIT

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: