Explore
MCP servers and skills: search, filter by where they run, and compare.
25–48 of 2,582 tools for “claude-opus”
Clear allOpusGoLlamaAaronKronberg
LocalGoMIT★ 4Few starsNo key
opus-5-5-devToroFelipe
MCP servers and skills: search, filter by where they run, and compare.
25–48 of 2,582 tools for “claude-opus”
Clear allGoMIT★ 4Few starsNo key
Claude Code skill: working habits to get the most out of Claude Opus 5.5 in development
SkillMIT★ 1Few starsNo key
Claude Fable 5.1 prompting guide as Claude Code skills (KO/EN/ZH). Output quality goes up on Opus 5 and Sonnet 5 too.
SkillMIT★ 58No key
Claude Code plugin: Advisor Strategy — Opus reasons and reviews while Sonnet subagents handle implementation.
SkillMITFew starsNo key
Claude Code skill: Opus plans and writes briefs, Sonnet workers execute - big tasks, fewer expensive tokens.
SkillMITFew starsNo key
Cut Claude Code dynamic-workflow costs: pin the right model + effort on every subagent stage, estimate spend before launch, and block scripts that would silently run every stage on Opus.
SkillMITFew starsNo key
A process that fights you—so your code doesn’t. From dreaming to shipping to cleanup, Opus enforces clarity, adversarial review, and context preservation. Shortcuts become bugs. Opus says no.
SkillLink only★ 3Few stars
GoMIT★ 5No key
Hosted MCP connector to manage Google Ads, Meta Ads, Microsoft Advertising, TikTok Ads and LinkedIn Ads from Claude, ChatGPT and any MCP client. Real write actions with approval gates.
Hosted by authorMITFew starsNo key
작업 성격에 따라 모델을 나눠 맡는 Claude Code 멀티모델 팀 플러그인 — Opus/Fable 오케스트레이터 + Opus deep-reasoner + Sonnet fast-worker + Codex 연동
SkillMIT★ 2Few starsNo key
Top 1% AI-native development environment — drop-in Claude Code setup: agents, CARL policy engine, 20 hooks, 78 skills, MCP servers, sanitization-tested
SkillMIT★ 1Few starsNo key
Multi-perspective code review council for Claude Code. 3 advisors by default, 10 agents in deep mode (Opus + Codex). Evidence chains, adversarial self-test, dual-path verdict. Based on Karpathy's LLM
SkillMIT★ 4Few starsNo key
Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком уровне усилий её запускать. Каждый совет со ссылкой на офиц
SkillMIT★ 128No key
costrict-plugins mirror of github-trending-ultracost (auto-generated, do not edit)
SkillMITFew starsNo key
Intelligent model routing for Claude Code — routes haiku/sonnet/opus by complexity. Live HUD with ctx%, rate limits & savings. 10 languages, zero config.
SkillMIT★ 2Few starsNo key
Claude Code plugin: nested 5-level team-lead orchestration (CEO delegates only, opus-only dispatch, author != reviewer, mandatory memory). Ships a skill, subagents, a /team-start command and an opus-e
SkillMITFew starsNo key
SkillMIT★ 3Few starsNo key
Extract Claude Fable 5's reasoning workflow into reusable Agent Skills so cheaper models like Opus 4.8 can inherit its behavior - no fine-tuning required.
SkillMIT★ 1Few starsNo key
AI-native motion video production over MCP: Opus for taste, cheap workers for implementation, HyperFrames for rendering.
SkillMIT★ 1Few starsNo key
🚀 1 Claude MAX + 1 Codex = 5x dev capacity | 一個人當五個工程師用 | 一人で5人分の開発力 — Spec-ops for non-coders
SkillMIT★ 6No key
SkillMIT★ 1Few starsNo key
AI Dev Stack Marketplace - Browse and install 388 agents, skills, MCPs for Web3
SkillMIT★ 1Few starsNo key
Who stands behind it
