Building agents plugins

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

Browse within: claude-plugin 8claude-code-skill 7hooks 6copilot 5subagents 5

skill-seekers

25

yusufkaraaslan/Skill_Seekers

Plugin Claude Code

Transform 18 source types (docs, GitHub, PDFs, videos, Jupyter, Confluence, Notion, Slack, and more) into AI-ready skills and RAG knowledge for 21+ AI platforms.

15k +18 2d ago A tokens not measured original MIT

ifixai-community

26

ifixai-ai/iFixAi

Plugin Claude Code

iFixAi tools for Claude Code. Claude guides you through an independent, open-source audit of your own agent: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by the judge(s) of your choice.

12k +889 4d ago A tokens not measured original Apache-2.0

ifixai

27

ifixai-ai/iFixAi

Plugin Claude Code

Independent auditing for AI agents, open source. Claude investigates your agent, authors an iFixAi fixture from its setup, and audits it against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Adversarial depth, assurance discipline. Test any…

12k +889 4d ago A tokens not measured original Apache-2.0

ida-pro-mcp

28

mrexodia/ida-pro-mcp

Plugin Claude Code

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

12k +55 4d ago A tokens not measured original MIT

mcp-use

29

mcp-use/mcp-use

Plugin Claude Code

Plugin marketplace listing 5 plugins: all-skills, mcp-builder, chatgpt-app-builder, mcp-apps-builder, openapi-to-mcp.

11k +11 today A tokens not measured original MIT

gsd-core

30

open-gsd/gsd-core

Plugin Claude Code

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

9.0k +90 today A tokens not measured original MIT

gsd-core

31

open-gsd/gsd-core

Plugin Claude Code

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

9.0k +90 today A tokens not measured original MIT

harness

32

revfactory/harness

Plugin Claude Code

The team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation). Claude Code용 팀 아키텍처 팩토리: 도메인 한 문장을…

8.9k +17 1mo ago A tokens not measured original Apache-2.0

superpowers-zh

33

jnMetaCode/superpowers-zh

Plugin Claude Code

A Chinese-language collection of 20 coding-agent skills for tools such as Claude Code, Cursor, and Qoder. The input identifies it as an enhanced Chinese edition, but does not describe each skill’s individual jobs.

7.9k +41 14d ago A tokens not measured original MIT

waza

34

tw93/Waza

Plugin Claude Code

Personal skill collection for Claude Code, Codex, Antigravity, OpenCode, and Pi: think, check, hunt, ui, read, write, learn, and health for agent config and AI maintainability audits.

6.9k +11 today A tokens not measured original MIT

webnovel-writer

35

lingfengQAQ/webnovel-writer

Plugin Claude Code

A long-form web-novel writing system made of reusable instructions, helper agents, linked data, and retrieval tools. Retrieval means finding relevant stored material while writing.

6.9k +39 yesterday A tokens not measured GPL-3.0

gepa

36

gepa-ai/gepa

Plugin Claude Code

Official GEPA Claude Code plugins.

6.3k +45 today A tokens not measured original MIT

gepa-ai/gepa

Plugin Claude Code

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.

6.3k +45 today A tokens not measured original MIT

engram

38

Gentleman-Programming/engram

Plugin Claude Code

Persistent memory for AI coding agents. Survives across sessions and compactions.

6.3k +34 changed today A tokens not measured original MIT

eigenwise

39

Eigenwise/atomic-agents

Plugin Claude Code

Official plugins for the Atomic Agents framework - a lightweight, modular system for building AI agents with Pydantic and Instructor.

6.2k +5 8d ago A tokens not measured original MIT

atomic-agents

40

Eigenwise/atomic-agents

Plugin Claude Code

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.

6.2k +5 8d ago A tokens not measured original MIT

autoresearch

44

uditgoenka/autoresearch

Plugin Claude Code

Claude Autoresearch — autonomous goal-directed iteration for Claude Code. 14 commands: iterate, plan, debug, fix, security, ship, scenario, predict, learn, reason, probe, evals, improve, regression.

6.0k +9 20d ago A tokens not measured original MIT

claude-plugin

45

uditgoenka/autoresearch

Plugin Claude Code

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

6.0k +9 20d ago A tokens not measured original MIT

ccg

46

fengshao1227/ccg-workflow

Plugin Claude Code

Plugin marketplace listing 1 plugin: ccg.

5.9k +4 3d ago A tokens not measured original MIT

google-agents-cli

47

google/agents-cli

Plugin Claude Code

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

5.8k +22 changed today A tokens not measured original Apache-2.0

ouroboros

48

Q00/ouroboros

Plugin Claude Code

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…

5.7k +17 changed today A tokens not measured original MIT