Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Any website as a verified JSON CLI and MCP server for agents
Hosted by authorMITFew starsNo key
Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillation (FABLE_CODE.md), measured playbook, verification hooks,
MCPLink only★ 17
800 tool-description injection attacks (MCPTox) against Claude Opus 5, Opus 4.8, Sonnet 5 and Haiku 4.5. Deterministic scorer validated against the benchmark's 7,368 human labels.
MCPLink onlyFew stars
An open job protocol on Monad: escrow-backed tasks, any agent can work, portable reputation. Monad Metropolis hackathon.
Hosted by authorMITFew starsNo key
Codex skill for supervised multi-session plan execution with optional Claude Opus 5 review
SkillLink only★ 5
Instagram DM MCP server - built entirely by Claude (Opus 4.5) in ~3 hours with mass auto-accept enabled. ultrathink ultraplan ultraanalyse ultraimplement
MCPLink only★ 3Few stars
Local /ultrareview skill — 3-stage Opus pipeline with live logs and implementation plan
SkillLink only★ 8
Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..
Hosted by authorNo licenseFew starsNo key
Viral hook detector and short video clip curator (Opus Clip style)
SkillLink only★ 8
MCP server that lets weaker coding agents ask Claude Opus via OpenRouter for expert guidance, with text file and image attachments.
MCPLink onlyFew stars
First-3-second shortform video hook retention scorer (Submagic / Opus Clip)
MCPLink only★ 9
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
Hosted by authorNo licenseFew starsNo key
∅ AXIOM Kit — Reproducible cognitive architecture for Claude Code (Opus 4.6). Persistence system built from published mechanistic interpretability research.
SkillLink onlyFew stars
Autonomous agent for processing Jira tickets using Claude Opus 4.5
MCPLink only★ 2Few 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
claude-opus-4-5-20251101-high-32k is #49 overall but #14 in coding. gpt-5.6-terra-xhigh is #52.
Hosted by authorNo licenseFew starsNo key
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
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
Autonomous agentic system for the IOAI 2026 AI Models Track (Claude Opus 4.8)
SkillLink only★ 1Few stars
Who stands behind it
