ai-agents plugins

3,216 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 246claude-code-plugin 231LLM 183cli 143agents 133agents-md 108prompt-engineering 108Science 99ai-coding 89ai-tools 74agentic-coding 61skills 54mcp-server 52agent-orchestration 50

axstream

649

milind-soni/axstream

Plugin Claude Code

Bundles 1 skill, 3 commands, 1 MCP server · 143 tokens together

Fast, verified computer use for coding agents: read the screen as text (200ms), execute batched verified actions, and compile any task done once into a macro that replays in seconds with zero model calls.

not rated 20 28d ago A tokens not measured original MIT

bug-shepherd

651

mshadmanrahman/pm-pilot

Plugin Claude Code

Bundles 5 skills, 1 agent · 296 tokens together

Zero-code bug triage for PMs. Checks in parallel whether old bugs still reproduce, reviews the verdicts, and syncs results back to Jira, Linear, or GitHub Issues.

not rated 20 +1 changed today A tokens not measured original MIT

operator-kit

652

wrg32786/operator-kit

Plugin Claude Code

Bundles 5 agents, 1 hook · 232 tokens together

Five focused, least-privilege Claude Code subagents plus an optional keyword-triggered context loader.

not rated 20 +1 26d ago A tokens not measured original MIT

agents-virtuoso

654

krzysztofsurdy/code-virtuoso

Plugin Claude Code

Bundles 12 skills · 1,109 tokens together

19 agents, 3 pre-composed teams, 7 role skills, and agent workflow skills — delegation patterns, team library, team dispatcher, subagent-driven development, verification discipline, plus all specialist and role agents.

not rated 20 3mo ago A tokens not measured original MIT

compass

656

dshakes/compass

Plugin Claude Code

Bundles 6 hooks, 3 MCP servers

Cost-tiered specialist subagents, workflow commands, guardrail + live-budget-ceiling + auto-quality hooks, a repo-bootstrap skill, a terse output style, and parity MCP servers — for serious polyglot software work.

not rated 19 6d ago A tokens not measured original MIT

omnireach

657

Daily-AC/omnireach

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 85 tokens together

Search and read the login-walled Chinese internet, parse media, and download bounded Douyin videos for AI agents.

not rated 19 changed 3d ago A tokens not measured original MIT

code-navigator

658

GobbyAI/gobby

Plugin Claude Code

Bundles 43 skills · 1,519 tokens together

AST-aware code search, symbol navigation, and dependency graph analysis.

not rated 19 5d ago A tokens not measured

equity-research

659

cyijun/china-financial-services

Plugin Claude Code

Bundles 1 skill · 69 tokens together

A research tool for analysing companies listed on China's A-share stock markets, using data from Tushare, a financial-data provider.

not rated 19 13d ago A tokens not measured original Apache-2.0

webmcp-sdk-skill

661

opentiny/agent-skills

Plugin Claude Code

Bundles 1 skill · 61 tokens together

A plugin containing a development guide for the WebMCP SDK, which helps build agent-facing features for web applications. It covers the listed remote-control, client, server, creation, and browser-extension components.

not rated 19 3d ago A tokens not measured

camunda-skills

662

camunda/skills

Plugin Claude Code

Bundles 13 skills · 2,295 tokens together

Official Camunda skills for AI-assisted Camunda 8 development.

not rated 19 4d ago A tokens not measured original Apache-2.0

palaia-memory

663

byte5ai/palaia

Plugin Claude Code

Bundles 3 skills · 296 tokens together

Makes an agent use palaia's shared memory without being told, and work alongside other agent sessions: when to recall, how to resume work, what deserves capturing, and when to register, check in and reply.

not rated 19 yesterday A tokens not measured original MIT

sync

665

AgriciDaniel/sync

Plugin Claude Code

Bundles 1 skill, 1 agent · 85 tokens together

Sync: Claude and Codex council orchestration. Routes work by role across declared pools, requires current headroom before any capacity claim, coordinates through run directories, gates on executed commands, and evolves policy from recorded outcomes.

not rated 19 7d ago A tokens not measured

erd-designer

666

kajitiluna/erd-designer

Plugin Claude Code

Bundles 1 skill · 60 tokens together

Design and edit ERD Designer (.erd) files with an agent. Provides a bundled CLI and a skill so agents can add tables, columns and relations, and export DDL without the MCP server.

not rated 19 +1 changed 3d ago A tokens not measured original Apache-2.0

aspark

667

a-lottes/aSPARK

Plugin Claude Code

Bundles 10 skills, 7 agents · 1,149 tokens together

An agile AI product team for Claude Code — Specify, Plan, Act, Review, Keep. A Product Owner, Designer, Engineering Manager, Reviewer, QA Tester and Release Manager work your feature through a gated delivery loop.

not rated 19 changed 3d ago A tokens not measured original MIT

wtfp

668

akougkas/wtf-p

Plugin Claude Code

Bundles 4 commands · 65 tokens together

Portable academic research and writing workflows with stable wtfp actions.

not rated 19 7d ago A tokens not measured original MIT

l3a0

669

l3a0/claude-plugins

Plugin Claude Code

Bundles 1 skill · 81 tokens together

l3a0's Claude Code skills. Currently: kindle-highlights — extract a book's Kindle highlights into one verbatim, location-cited Markdown file, recovering everything Amazon's export limit truncates or hides.

not rated 19 +1 7d ago A tokens not measured original MIT

localization-team

670

sodam-ai/SoDam-Agent

Plugin Claude Code

Bundles 3 agents · 50 tokens together

A translation and localisation workflow with separate roles for translation, cultural adaptation, and terminology review. Localisation means adapting wording and references so they fit the target culture, while terminology review keeps important terms consistent.

not rated 19 +3 27d ago A tokens not measured original Apache-2.0

disruptor

671

smixs/disruptor-skills

Plugin Claude Code

Bundles 12 skills · 851 tokens together

12 agent skills for AI-driven software development, stitched into one gated idea-to-ship pipeline: 7w3 design, build-ready spec, executable architecture guardrails, tracer-bullet slicing, an honest review loop, a parallel MVP worker fleet, demo-stand QA and safe server deploy. Cross-agent skills format (Claude Code…

not rated 18 2mo 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: