MCP servers and skills: search, filter by where they run, and compare.
49–72 of 111 tools for “opus”
Clear allDrop-in production trace collector for LLM agents (Go). Streams traces to your Mirrors backend.
Hosted by authorMITFew starsNo key
Claude Code skill: orchestrate work as a dependency graph across a cheap-Haiku swarm, steered by Sonnet, escalating to Opus only when needed
SkillLink only★ 2Few stars
A Claude Code plugin that classifies task complexity and facilitates running subagent work on a cost-appropriate Claude model (Haiku / Sonnet / Opus) rather than always the session default.
SkillLink only★ 2Few stars
Security-first agentic AI on AWS — Strands agent + Claude Opus 4.6 on Bedrock AgentCore | MCP tools secured via SigV4/IAM, OAuth2 M2M (Cognito + AgentCore Identity vault, zero embedded secrets), and A
MCPLink only★ 1Few stars
Local-first, AST-aware context compiler that sits between Claude Code and the filesystem as an MCP server. Built for Claude Opus 4.7 Hackathon
MCPLink only★ 5
Prompt optimization for Claude 5-generation models (Opus 5 / Sonnet 5 / Fable 5) — installable Claude Code plugin
SkillLink onlyFew stars
Ziarmy — Claude Code plugin: multi-agent dev-team (build) + deploy-team (ship). Sonnet 5 executors, Opus 4.8 reviewers, one Fable 5 advisor, caveman-terse comms.
SkillLink only★ 1Few stars
Three-model multi-agent OpenClaw skill: GPT-5.2 coordinator + Sonnet tester + Opus coder, all with Telegram bots
SkillLink only★ 2Few stars
Claude Code skill: turn any academic paper into a browser-based quiz powered by Claude Opus
SkillLink only★ 2Few stars
Agent skill: round-by-round multi-model debate (Opus, Sol, DeepSeek, Devin) with a visual breakdown. Claude Code + Codex, runs on T3.
SkillLink onlyFew stars
MCP server for avots.ai: image, video, audio, face-swap, talking avatars and chat across 300+ AI models. Works with Claude Desktop, claude.ai, Cursor, Cline, openclaw, LibreChat, Continue.
Hosted by authorMITFew starsNo key
Universal Multi-Agent Swarm Exposer over Model Context Protocol for IDEs
MCPLink onlyFew stars
AI-powered financial fraud detection using MCP + Claude Opus 4.8
MCPLink only★ 1Few stars
A Claude Code skill for orchestrating Opus/Sonnet/Haiku subagents plus a cross-vendor Codex peer
SkillLink only★ 3Few stars
/build - a Claude Code skill that runs a big job as a team: one Claude plans, Opus coder agents build, a read-only verifier checks every claim
SkillLink onlyFew stars
Advisor Strategy skill for AI coding agents, spawns a stronger model as strategic advisor for architecture, security, debugging, and performance. Works with Claude Code, Cursor, Gemini CLI, Cline, Cod
SkillLink only★ 3Few stars
A Claude Code subagent engineering team: architecture and review on Opus 5, implementation and tests on Sonnet 5. Simple, long-lived, robust, no over-design.
SkillLink only★ 1Few stars
Claude Code skill: Auto-clip YouTube videos with Opus Clips & publish to all socials via Blotato
SkillLink only★ 1Few stars
AI-assisted plugin review add-on for the WordPress Plugin Check plugin. Uses OpenRouter (default: Claude Opus 4.7).
MCPLink only★ 1Few stars
Replica of Claude Opus 4.8's dynamic workflow architecture - team-based adversarial convergence with parallel workers and dedicated verifiers
SkillLink only★ 1Few stars
A Claude Code skill that brings Claude Fable 5's engineering discipline to Claude Opus 4.8 and other models: act decisively, ground progress claims in tool output, verify with fresh context, avoid ove
SkillLink only★ 3Few stars
Anthropic — independent third-party profile of a public API surface, by API Evangelist. Anthropic is an AI safety company and creator of the Claude family of large language models (Opus, Sonnet, Haiku
MCPLink onlyFew stars
Who stands behind it
