# Claude Agents Team

> AGENT TEAM GENERATOR

Hand it a product description and it writes the whole .claude directory — orchestrator, specialists, skills, rules, hooks — then grades every file before the run exits.

```bash
claude plugin install ./agents-team/plugins/agents-team
```

## Features

### /team-gen

A product spec in, a complete standards-compliant team out: orchestrator, specialists, skills, rules and hooks.

### /meet

A streamed multi-agent meeting on one topic, ending in structured minutes you can act on.

### /evaluate-agent

Score any agent or skill against a rubric where every line cites a published spec or prior art.

### Graded before it ships

The generator lints every file it produced. One reject verdict fails the whole run.

## How it grades

- **Static**: static linter
- **Model**: LLM-as-judge
- **Behaviour**: behavioral harness

## Three pillars

1. Generate a team

```bash
/team-gen ./my-product-spec.md --target .
```

2. Hold a meeting

```bash
/meet "Should we ship the v2 migration this quarter?"
```

3. Lint an agent

```bash
/evaluate-agent .claude/agents/code-reviewer.md
```

## Why it exists

Three large agent teams — sentra-hub at ~14 agents, orch at ~42, the Orchestra team at ~40 — were hand-rolled from scratch. This plugin extracts the patterns that worked and refuses the ones below standard.

Source: https://github.com/fadymondy/agents-team