Agenthub

Looking at this one, the source material is essentially empty, so I can only go by the name. It appears to be a meta-skill for managing or coordinating other AI agents or skills within a hub architecture. You'd presumably use this when you need Claude to orchestrate multiple specialized agents or delegate tasks across a suite of tools rather than handling everything directly. Without actual implementation details though, it's hard to say whether this is a lightweight router, a full agent framework integration, or something else entirely. If you're building multi-agent systems, it might be worth checking out, but verify what's actually included before committing to it in production.

skills.sh installs: 599
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill agenthub --agent claude-code

Installs into .claude/skills of the current project.

Files

AgentHub — Multi-Agent Collaboration

Spawn N parallel AI agents that compete on the same task. Each agent works in an isolated git worktree. The coordinator evaluates results and merges the winner.

Slash Commands

Command	Description
`/hub-init`	Create a new collaboration session — task, agent count, eval criteria
`/agenthub:spawn`	Launch N parallel subagents in isolated worktrees
`/hub-status`	Show DAG state, agent progress, branch status
`/agenthub:eval`	Rank agent results by metric or LLM judge
`/agenthub:merge`	Merge winning branch, archive losers
`/agenthub:board`	Read/write the agent message board
`/hub-run`	One-shot lifecycle: init → baseline → spawn → eval → merge