Agent skill · software engineering · alirezarezvani
agenthub
Run several agents on one task in parallel and keep the best result: faster code, copy variants, research angles. Use whenever the user wants multiple attempts compared or best of N; spawns agents in git worktrees, ranks and merges the winner.
Why this skill is useful
Adds a multi-agent collaboration framework with executable commands for spawning agents and evaluating results that fundamentally extends the AI's capabilities.
What it needs
Requires git installed locally. About 5k tokens when loaded. Last updated 2026-08-05. 23,939 stars on the source repository.
What this skill does
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 Agent Templates When spawning with --template, agents follow a predefined iteration pattern: Template Pattern Use Case ---------- --------- ---------- optimizer Edit → eval → keep/discard → repeat x10 Performance, latency, size refactorer Restructure → test → iterate until green Code quality, tech debt test-writer Write tests → measure coverage → repeat Test coverage gaps bug-fixer Reproduce → diagnose → fix → verify Bug fix approaches Templates are defined in references/agent-templates.md. When This Skill Activates Trigger phrases: "try multiple approaches" "have agents compete" "parallel optimization" "spawn N agents" "compare different solutions" "fan-out" or "tournament" "generate content variations" "compare different drafts" "A/B test copy" "explore multiple strategies" Coordinator Protocol The main Claude Code session is the coordinator. It follows this lifecycle: 1. Init Run /hub-init to create a session. This generates: .agenthub/sessions/{session-id}/config.yaml — task config .agenthub/sessions/{session-id}/state.json — state machine .agenthub/board/ — message board channels 2. Dispatch Run /agenthub:spawn to launch agents. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/agenthub--7b42cb