MCP servers and skills: search, filter by where they run, and compare.
First-3-second shortform video hook retention scorer (Submagic / Opus Clip)
MCPLink only★ 9
∅ AXIOM Kit — Reproducible cognitive architecture for Claude Code (Opus 4.6). Persistence system built from published mechanistic interpretability research.
SkillLink onlyFew stars
First-3-second shortform video hook retention scorer (Submagic / Opus Clip)
MCPLink only★ 8
Audio silence detector calculating video jumpcut cadences & pacing (Opus Clip / Descript)
MCPLink only★ 8
Audio silence detector calculating video jumpcut cadences & pacing (Opus Clip / Descript)
MCPLink only★ 8
Claude Code workflow: Opus designs, Sonnet leads, Haiku builds. Measured cost findings included.
SkillLink only★ 1Few stars
Plan-only multi-model Fusion for Claude Code: Opus 4.8 + GPT-5.5 (Codex) answer in parallel, Opus judges into one executable PLAN. Mythos-tier judgment distilled into the subscriptions you already pay
SkillLink onlyFew stars
An MCP (Model Context Protocol) server that lets Claude/Codex/Cursor drive an OpenCode instance and delegate work to its subagents — so orchestrator models like Opus/Fable/GPT5.6 Sol can hand off task
MCPLink only★ 3Few stars
A Claude Code skill that fans one hard question out to several frontier models (GPT-5.5, Gemini, Kimi, GLM) blind and in parallel, then has Opus 4.8 judge and synthesize one grounded answer. Multi-mod
SkillLink onlyFew stars
Lean agent harness for Claude Code (Opus 4.6) — adversarial reviewers, scoring rubrics, and spec planning without the bloat
SkillLink only★ 1Few stars
A Fable written Claude MD for Opus/Sonnet to give it some of the quality methodology that Fable uses
SkillLink only★ 7
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
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
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
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
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
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
