Building agents plugins

open-gsd/gsd-core

Plugin Claude Code

Bundles 72 skills, 64 agents, 7 hooks · 4,353 tokens together

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

modelcontextprotocol/modelcontextprotocol

Plugin Claude Code ✓ vendor

Bundles 2 skills · 40 tokens together

Claude Code skills for researching and contributing to the MCP specification.

revfactory/harness

Plugin Claude Code

Bundles 2 skills · 368 tokens together

The team-architecture factory for Claude Code v2 — a meta-skill that turns a domain description into an agent team and the skills they use. Three native execution modes (Workflow orchestration, persistent named-agent collaboration, sub-agent delegation), six team-architecture patterns, and workflow-native quality…

strands-agents/harness-sdk

Plugin Claude Code

Bundles 6 skills, 1 MCP server · 320 tokens together

Build, extend, evaluate, and migrate applications with Strands Agents in Python or TypeScript.

jnMetaCode/superpowers-zh

Plugin Claude Code

Bundles 21 skills, 1 hook · 940 tokens together

A Chinese-language plugin containing 20 AI coding skills, including translated and original workflows, for several coding-agent tools. Its listed topics include testing-driven development, debugging, and development practices.

mvschwarz/openrig

Plugin Claude Code

Bundles 19 skills · 1,549 tokens together

OpenRig canonical skills and hooks for cross-runtime agent topology coordination, continuity, and operating discipline.

zenstory-ai/oh-story-claudecode

Plugin Claude Code

Bundles 1 skill, 13 commands · 417 tokens together

A setup tool that installs writing-project rules, hooks, agents, and instruction files, with checks for recovering and validating sessions.

gepa-ai/gepa

Plugin Claude Code

Bundles 1 skill · 206 tokens together

Optimize any scorable text artifact (prompts, code, configs, agent scaffolds, search solutions) with optimizeanything — one evaluator-driven API across the GEPA optimizer (reflective evolutionary search, the default), AutoResearch, and MetaHarness backends, with a best-of-N baseline for comparisons.

uditgoenka/autoresearch

Plugin Claude Code

Bundles 5 hooks

Autonomous improvement engine. 14 commands: iterate, plan, debug, fix, security, ship, scenario, predict, learn, reason, probe, improve, evals, regression.

czlonkowski/n8n-skills

Plugin Claude Code

Bundles 15 skills · 2,389 tokens together

Complete bundle: 14 expert skills for building flawless n8n workflows with the n8n-mcp MCP server — and deploying the self-hosted n8n that runs them (expression syntax, MCP tools usage, workflow patterns, validation, node configuration, JavaScript code, Python code, the AI-agent Custom Code Tool, production error…

microsoft/agent-governance-toolkit

Plugin Claude Code ✓ vendor

Bundles 2 commands, 1 MCP server · 32 tokens together

AGT governance hooks and MCP tools for Claude Code sessions.

huangruiteng/loopx

Plugin Claude Code

Bundles 1 command, 1 hook · 53 tokens together

LoopX adapter for Claude Code: the loopx control-plane MCP (shouldrun / claimtask / completetask) + the /loopx setup command + statusline. The run loop is Claude Code's native /loop, driven by a .claude/loop.md that /loopx writes; the optional shouldrun PreToolUse gate (hooks/goalpolicy.py) is added deliberately v.

Eigenwise/atomic-agents

Plugin Claude Code

Bundles 7 skills, 2 agents · 891 tokens together

Skills plus explorer and reviewer subagents for building, scaffolding, debugging, understanding, and auditing applications with the Atomic Agents Python framework. Includes the umbrella framework skill, action-oriented create-atomic-schema / create-atomic-agent / create-atomic-tool / create-atomic-context-prov.

Q00/ouroboros

Plugin Claude Code

Bundles 23 skills, 3 hooks, 1 MCP server · 818 tokens together

Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the…

FlorianBruniaux/claude-code-ultimate-guide

Plugin Claude Code

Bundles 1 skill · 37 tokens together

Comprehensive TUI/Web dashboard for Claude Code monitoring and management.

google/agents-cli

Plugin Claude Code ✓ vendor

Bundles 8 skills · 1,036 tokens together

Scaffold, develop, evaluate, and deploy AI agents with Google ADK. Bundles skills for the agent development lifecycle.

humanlayer/skills

Plugin Claude Code

Bundles 1 skill · 44 tokens together

Interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) for their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow.

entireio/cli

Plugin Claude Code

Bundles 3 commands · 36 tokens together

Multi-phase toolkit for integrating a new AI coding agent with the Entire CLI.

langwatch/langwatch

Plugin Claude Code

Bundles 1 skill, 1 hook · 66 tokens together

Records which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.

darrenhinde/OpenAgentsControl

Plugin Claude Code

Bundles 12 skills, 6 commands, 7 agents, 1 hook · 1,029 tokens together

OpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.

WorldFlowAI/everything-claude-code

Plugin Claude Code

Bundles 11 skills, 15 commands, 9 agents, 6 hooks · 746 tokens together

Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use.

BuilderIO/skills

Plugin Claude Code

Bundles 25 skills, 1 command, 1 MCP server · 1,270 tokens together

Public Builder skills for docs-first discipline, autonomous execution, cross-agent review, local-first Rewind memory, efficient agent workflows, clear status recaps, Agent-Native workflow apps, and experimental configurable software factory workflows.

mixedbread-ai/mgrep

Plugin Claude Code

Bundles 1 skill · 64 tokens together

Search your local files using Mixedbread.

langroid/langroid

Plugin Claude Code

Bundles 2 skills · 82 tokens together

Design patterns for the Langroid multi-agent LLM framework.