Building agents plugins

3,987 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 237cli 123cursor 117agents 115LLM 97skills 84ai-coding 81ai-tools 75agentic-ai 73agent 56agent-orchestration 49agentic-workflow 48claude-code-plugins 45mcp-server 42

skilld

241

skilld-dev/skilld

Plugin Claude Code

Bundles 6 skills · 308 tokens together

The skilld-maintained Skills for Skill generation, review, and skilld CLI use.

not rated 327 +3 changed 7d ago A tokens not measured original MIT

scasella/claude-dynamic-workflows-codex

Plugin Claude Code

Bundles 1 skill · 100 tokens together

Run Claude Code dynamic-workflow scripts on a local Codex App Server — fan out Codex/GPT agents with the agent/parallel/pipeline DSL, sessionful steerable workers, supervised fleets (--multi), live viewers, and run analytics.

not rated 326 +1 3mo ago A tokens not measured original MIT

openlogos

243

miniidealab/openlogos

Plugin Claude Code

Bundles 10 commands, 1 agent · 191 tokens together

OpenLogos methodology plugin — structured AI-driven development with Why → What → How progression.

not rated 322 +98 4d ago A tokens not measured original Apache-2.0

pi-dashboard

244

BlackBeltTechnology/pi-agent-dashboard

Plugin Claude Code

Bundles 2 skills · 107 tokens together

Start and drive the local pi-agent-dashboard from Claude Code: bring the dashboard server up without starting a second instance, then list, prompt, abort and spawn pi sessions through its REST API.

not rated 321 +5 today A tokens not measured original MIT

pskoett-ai-skills

246

pskoett/pskoett-ai-skills

Plugin Claude Code

Bundles 6 hooks

Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service…

not rated 318 +3 changed today A tokens not measured

sage

247

gendigitalinc/sage

Plugin Claude Code

Bundles 1 skill, 1 hook · 39 tokens together

Safety for Agents - Agent Detection & Response (ADR) for AI agents.

not rated 316 +4 changed 5d ago A tokens not measured original Apache-2.0

example-skills

248

lingxling/awesome-skills-cn

Plugin Claude Code

Bundles 12 skills · 692 tokens together

Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.

not rated 312 +6 11d ago A tokens not measured original MIT

CCteam-creator

249

jessepwj/CCteam-creator

Plugin Claude Code

Bundles 1 skill, 1 plugin · 224 tokens together

Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.

not rated 307 6mo ago A tokens not measured original MIT

emulo

250

ohad6k/emulo

Plugin Claude Code

Bundles 8 skills, 1 MCP server · 489 tokens together

Mine real AI coding sessions into a bounded, evidence-backed personal layer.

not rated 297 +3 changed 22d ago A tokens not measured original MIT

watchmen

251

firstbatchxyz/watchmen

Plugin Claude Code

Bundles 1 hook

Surface skill suggestions + workspace context from watchmen sessions intelligence into your Claude Code sessions.

not rated 296 1mo ago A tokens not measured original MIT

karimo

254

opensesh/KARIMO

Plugin Claude Code

Bundles 11 commands, 22 agents · 823 tokens together

Autonomous development methodology: PRD interviews → agent execution → automated review.

not rated 292 +2 5d ago A tokens not measured original Apache-2.0

dspy-agent-skills

255

intertwine/dspy-agent-skills

Plugin Claude Code

Bundles 5 skills · 399 tokens together

Production-grade DSPy 3.2.x skills for coding agents: signatures, modules, evaluation harnesses, GEPA optimization, RLM long-context reasoning, BetterTogether chaining, and a full end-to-end DSPy workflow.

not rated 278 1mo ago A tokens not measured original MIT

super-dev marketplace

256

shangyankeji/super-dev

Plugin Claude Code

An engineering workflow plugin for AI coding tools that organizes work into research, documentation, specifications, implementation, review, testing, and delivery. It includes required checkpoints before continuing between major phases.

not rated 276 +1 4mo ago A tokens not measured original MIT

my-claude-devteam

258

NYCU-Chung/my-claude-devteam

Plugin Claude Code

Bundles 12 agents, 5 hooks · 760 tokens together

An engineering team in a box for Claude Code. 12 specialized subagents (planner, fullstack-engineer, refactor-specialist, migration-engineer, frontend-designer, critic, vuln-verifier, debugger, db-expert, onboarder, tool-expert, web-researcher) plus 15 automation hooks (pre-commit secret scan, MCP health tracking…

not rated 270 6mo ago A tokens not measured original MIT

mcptoon

259

activeing123/mcptoon

Plugin Claude Code

Bundles 1 skill, 1 command, 1 hook, 1 MCP server · 542 tokens together

MCP tool-catalog compression for Claude Code. Compresses the tool discovery payload from 71,929 to 581 tokens (-99.2%). Auto-installs the zero-dependency mcptoon CLI (/mcptoon-setup), wires the serve bridge, and teaches the agent when to compress. MCP 2026-07-28 stateless-first bridge included.

not rated 270 +52 yesterday A tokens not measured original Apache-2.0

guaardvark

260

guaardvark/guaardvark

Plugin Claude Code

Bundles 15 skills · 1,164 tokens together

Drive a self-hosted Guaardvark from your coding agent: local image, video, music-video and Film Crew generation, voice and music, upscaling, LoRA training, Hugging Face model onboarding, agent swarms, local knowledge, code intelligence and supervised outreach, on your own GPU.

not rated 268 +8 changed 6d ago A tokens not measured original MIT

repowire

261

prassanna-ravishankar/repowire

Plugin Claude Code

Bundles 14 skills, 1 plugin · 601 tokens together

Repowire mesh usage skills for AI coding agents: cross-agent review and planning, delegate, usage patterns, and install/update. Backend-agnostic and parameterised on the agent you choose.

not rated 267 +1 yesterday A tokens not measured

bigpowers

262

danielvm-git/bigpowers

Plugin Gemini CLI

81 skills — 73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers.

not rated 267 +6 changed 26d ago 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: