3,274 tagged ai-agents, measured the same way as everything else here.
Browse within: agentic-ai 236claude-code-plugin 215LLM 190cursor 176cli 133prompt-engineering 111agents-md 107Science 99agents 87ai-coding 81agentic-coding 62ai-tools 62skills 60ai-governance 54
gabonio/agent-operator-toolkit
Plugin Claude Code
Bundles 5 skills · 336 tokens together
An explicitly invoked, token-efficient harness for planning, implementing, and reviewing agent-driven software. It helps technical and non-technical users produce sustainable code through approval-gated specifications, pragmatic repository-aware standards, conditional expert lenses, safe Git workflows, and…
Plugin Claude Code
Claude Code and Codex plugin marketplace for agent skills, MCP integrations, hooks, commands, and companion agents.
Plugin Claude Code
Bundles 4 skills, 3 hooks · 197 tokens together
Apply Semantic Versioning 2.0.0 rules to release decisions and reviews.
Plugin Claude Code
Bundles 3 skills · 211 tokens together
Genetic exploration of solution spaces for AI coding agents — gather a verifiable objective, evolve variants, apply the winner.
Plugin Claude Code
Bundles 1 command · 16 tokens together
Converts vague, messy, or under-specified requests into clearer, efficient AI-ready instructions while preserving user intent. Use before solving complex, ambiguous, or high-risk tasks.
Plugin Claude Code
Bundles 1 skill · 110 tokens together
Implementation-Driven Development skill for isolated probes, human decisions, contracts, and independent verification.
Plugin Claude Code
Bundles 12 skills, 1 command, 4 hooks · 739 tokens together
Odoo SA development skills, hooks, and conventions for PSDU customer work. Principles-first guidance for module development, code review, testing, and continuous skill refinement.
GuoCheng24/breakthrough-harness
Plugin Claude Code
Bundles 1 skill · 107 tokens together
Breakthrough-loop research discipline: hard-to-fool scoring harness + parallel cheap candidate generation, as a Claude Code skill.
Plugin Claude Code
Bundles 36 skills, 11 commands, 8 agents · 3,103 tokens together
Curated Claude Code skills, agents, and commands for .NET/C# backend, .NET MAUI mobile, and React + TypeScript frontend workflows.
Plugin Claude Code
Bundles 5 skills · 399 tokens together
Multi-CLI role skills for batonq autonomous coding agents — worker, judge, pr-runner, explorer, reviewer.
runwhen-contrib/runwhen-platform-mcp
Plugin Claude Code
Bundles 15 skills, 3 agents, 1 MCP server · 1,533 tokens together
Infrastructure automation for RunWhen — monitor, troubleshoot, and automate with AI agents. Build health checks, investigate issues, and manage SRE tasks across Kubernetes and cloud environments.
Plugin Claude Code
Bundles 1 skill, 6 commands, 1 MCP server · 227 tokens together
Patent-pending zero-IPC E2E test runtime for AI agents. Drive a real browser in plain English, enforce the VITRON-EA1 fail-closed safety gate, audit WCAG 2.1 AA and NIST SP 800-53, and export signed evidence packs. Local-first, zero telemetry.
Plugin Claude Code
Bundles 5 skills · 76 tokens together
Agent sidecar proxy — policy enforcement, tracing, and approval for AI agents.
Plugin Claude Code
Bundles 1 skill, 5 commands, 2 hooks · 89 tokens together
Autonomous Nervous System for AI Agents with RRF Search and Active Coercion.
michelgrolet/people-memory-mcp
Plugin Claude Code
Bundles 6 skills, 1 MCP server · 588 tokens together
A private people graph that gives your agent durable memory of everyone you know. MCP tools to search, remember and connect people, plus skills that retrieve and record them during ordinary conversation.
Plugin Claude Code
Fact-check every agent turn against the real code, the working-tree git diff, and recorded test runs. Deterministic, cited Supported/Contradicted/Refused verdicts — contradictions block the turn so the agent corrects itself before you read it. Requires the truth binary (the SessionStart hook tells you how to install…
Plugin Claude Code
Bundles 3 skills, 1 MCP server · 203 tokens together
MCP server for EVM security analysis, gas profiling, compiler diagnostics, and transaction simulation. Provides autonomous coding agents with deterministic, schema-validated tools for Ethereum smart contract development.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 99 tokens together
Delegate heavy dev tasks from an Opus supervisor to an autonomous worker on a cheaper model, via MCP.
Plugin Claude Code
Bundles 8 skills · 0 tokens together
Live control of one Discord server used as a lab for bots and programming experiments. Read the server, build systems as Registry data, run test sessions, schedule work, and gate anything irreversible behind a written preview.
Plugin Claude Code
Bundles 2 skills, 2 hooks, 1 MCP server · 137 tokens together
Payment firewall for AI agents: a signed, verifiable verdict on every money-moving action. Blocks wrong/lookalike payee, over-cap, and duplicate-invoice fraud before it settles. Non-custodial, local-first.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 142 tokens together
Edit, draft, search, summarize, and export styled documents (.docx / PDF / HTML / Markdown / plain text) via the SuperDocs MCP server. Single install bundles 38 MCP tools, 4 user-invocable workflow prompts, and a skill that auto-loads when document work is requested.
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Search movies, TV, and people on The Movie Database (TMDB) — credits, ratings, trailers, images, recommendations, and region-aware streaming availability via MCP. STDIO or Streamable HTTP.
cyanheads/osv-advisory-mcp-server
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Query OSV.dev for package vulnerabilities, batch-audit dependency lists, and fetch full advisory records via MCP. STDIO or Streamable HTTP.
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Search Jellyseerr/Overseerr, check availability, and create guarded media requests.
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: