Skip to main content
plugin CX Codex

agent-teams — Claude Code plugin: multi-agent teams, install

Runs several Claude agents at once for parallel code review, hypothesis-driven debugging and coordinated feature work.

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add wshobson/agents
/plugin install agent-teams@claude-code-workflows
Open on GitHub

What agent-teams does

agent-teams splits work across agents with fixed roles. team-lead decomposes the job and merges results, team-reviewer covers one review dimension, team-debugger gathers evidence for or against a hypothesis, and team-implementer writes code inside strict file ownership boundaries.

Seven slash commands ship with it: /team-spawn, /team-status, /team-shutdown, /team-review, /team-debug, /team-feature, /team-delegate. Presets cover review, debug, feature, fullstack, research, security and migration; custom composition is available too. Six skills explain team sizing, task decomposition, parallel debugging and the messaging protocol between agents.

All of it runs on the experimental Agent Teams feature, so you enable it with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Teammate display is set in ~/.claude/settings.json under teammateMode: tmux, iterm2 or in-process. Keep teams at 2–4 members — coordination overhead grows fast past that. For feature work the author advises --plan-first so you approve the decomposition before implementers start.

What it helps with

  • review code in parallel across security, performance and architecture
  • trace a bug through competing hypotheses and collected evidence
  • split a feature into work streams with file ownership boundaries
  • run a security audit over OWASP, auth and dependencies
  • migrate a codebase in parallel streams and verify correctness

Example prompts for the agent

  • /team-review src/ --reviewers security,performance,architecture
  • /team-debug "API returns 500 on POST /users with valid payload" --hypotheses 3
  • /team-feature "Add user authentication with OAuth2" --team-size 3 --plan-first

How to install agent-teams

Plugin marketplace

/plugin marketplace add wshobson/agents
/plugin install agent-teams@claude-code-workflows

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about agent-teams

How do I install agent-teams in Claude?

Add the marketplace first: /plugin marketplace add wshobson/agents. Then install the plugin: /plugin install agent-teams@claude-code-workflows.

What does agent-teams do?

It spawns multi-agent teams for parallel code review, hypothesis-driven debugging and coordinated feature development. Roles go to team-lead, team-reviewer, team-debugger and team-implementer.

What has to be enabled before using the commands?

The experimental Agent Teams feature: export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Teammate display mode is configured in ~/.claude/settings.json via teammateMode.

Source text

agent-teams · MIT
# Agent Teams Plugin

Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's experimental [Agent Teams](https://code.claude.com/docs/en/agent-teams) feature.

## Setup

### Prerequisites

1. Enable the experimental Agent Teams feature:

```bash
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
```

2. Configure teammate display mode in your `~/.claude/settings.json`:

```json
{
  "teammateMode": "tmux"
}
```

Available display modes:

- `"tmux"` — Each teammate runs in a tmux pane (recommended)
- `"iterm2"` — Each teammate gets an iTerm2 tab (macOS only)
- `"in-process"` — Teammates run in the same process (default)

### Installation

First, add the marketplace (if you haven't already):

```
/plugin marketplace add wshobson/agents
```

Then install the plugin:

```
/plugin install agent-teams@claude-code-workflows
```

## Features

- **Preset Teams** — Spawn pre-configured teams for common workflows (review, debug, feature, fullstack, research, security, migration)
- **Multi-Reviewer Code Review** — Parallel review across security, performance, architecture, testing, and accessibility dimensions
- **Hypothesis-Driven Debugging** — Competing hypothesis investigation with evidence-based root cause analysis
- **Parallel Feature Development** — Coordinated multi-agent implementation with file ownership boundaries
- **Parallel Research** — Multiple Explore agents investigating different questions or codebase areas simultaneously
- **Security Audit** — Comprehensive parallel security review across OWASP, auth, dependencies, and configuration
- **Migration Support** — Coordinated codebase migration with parallel implementation streams and correctness verification
- **Task Coordination** — Dependency-aware task management with workload balancing
- **Team Communication** — Structured messaging protocols for efficient agent collaboration

## Commands

| Command          | Description                                                |
| ---------------- | ---------------------------------------------------------- |
| `/team-spawn`    | Spawn a team using presets or custom composition           |
| `/team-status`   | Display team members, tasks, and progress                  |
| `/team-shutdown` | Gracefully shut down a team and clean up resources         |
| `/team-review`   | Multi-reviewer parallel code review                        |
| `/team-debug`    | Competing hypotheses debugging with parallel investigation |
| `/team-feature`  | Parallel feature development with file ownership           |
| `/team-delegate` | Task delegation dashboard and workload management          |

## Agents

| Agent              | Role                                                                              | Color  |
| ------------------ | --------------------------------------------------------------------------------- | ------ |
| `team-lead`        | Team orchestrator — decomposes work, manages lifecycle, synthesizes results       | Blue   |
| `team-reviewer`    | Multi-dimensional code reviewer — operates on assigned review dimension           | Green  |
| `team-debugger`    | Hypothesis investigator — gathers evidence to confirm/falsify assigned hypothesis | Red    |
| `team-implementer` | Parallel builder — implements within strict file ownership boundaries             | Yellow |

## Skills

| Skill                          | Description                                                              |
| ------------------------------ | ------------------------------------------------------------------------ |
| `team-composition-patterns`    | Team sizing heuristics, preset compositions, agent type selection        |
| `task-coordination-strategies` | Task decomposition, dependency graphs, workload monitoring               |
| `parallel-debugging`           | Hypothesis generation, evidence collection, result arbitration           |
| `multi-reviewer-patterns`      | Review dimension allocation, finding deduplication, severity calibration |
| `parallel-feature-development` | File ownership strategies, conflict avoidance, integration patterns      |
| `team-communication-protocols` | Message type selection, plan approval workflow, shutdown protocol        |

## Quick Start

### Multi-Reviewer Code Review

```
/team-review src/ --reviewers security,performance,architecture
```

Spawns 3 reviewers, each analyzing the codebase from their assigned dimension, then consolidates findings into a prioritized report.

### Hypothesis-Driven Debugging

```
/team-debug "API returns 500 on POST /users with valid payload" --hypotheses 3
```

Generates 3 competing hypotheses, spawns investigators for each, collects evidence, and presents the most likely root cause with a fix.

### Parallel Feature Development

```
/team-feature "Add user authentication with OAuth2" --team-size 3 --plan-first
```

Decomposes the feature into work streams with file ownership boundaries, gets your approval, then spawns implementers to build in parallel.

### Parallel Research

```
/team-spawn research --name codebase-research
```

Spawns 3 researchers to investigate different aspects in parallel — across your codebase (Grep/Read) and the web (WebSearch/WebFetch). Each reports findings with citations.

### Security Audit

```
/team-spawn security
```

Spawns 4 security reviewers covering OWASP vulnerabilities, auth/access control, dependency supply chain, and secrets/configuration. Produces a consolidated security report.

### Codebase Migration

```
/team-spawn migration --name react-hooks-migration
```

Spawns a lead to plan the migration, 2 implementers to migrate code in parallel streams, and a reviewer to verify correctness of the migrated code.

### Custom Team

```
/team-spawn custom --name my-team --members 4
```

Interactively configure team composition with custom roles and agent types.

## Best Practices

1. **Start with presets** — Use `/team-spawn review`, `/team-spawn debug`, or `/team-spawn feature` before building custom teams
2. **Use `--plan-first`** — For feature development, always review the decomposition before spawning implementers
3. **File ownership is critical** — Never assign the same file to multiple implementers; use interface contracts at boundaries
4. **Monitor with `/team-status`** — Check progress regularly and use `/team-delegate --rebalance` if work is uneven
5. **Graceful shutdown** — Always use `/team-shutdown` rather than killing processes manually
6. **Keep teams small** — 2-4 teammates is optimal; larger teams increase coordination overhead
7. **Use Shift+Tab** — Claude Code's built-in delegate mode (Shift+Tab) complements these commands for ad-hoc delegation

© Seth Hobson · MIT · wshobson/agents

Similar plugins

All plugins for Agent setup: memory, context, orchestration →

From the same set342

The whole set →
signed-audit-trails Learn how to sign records of Claude Code tool calls and detect tampering. Useful for evaluating the approach before adding runtime infrastructure. CX Codex ★ 41,729repo stars protect-mcp Gates every tool call through a Cedar policy and issues an Ed25519-signed receipt. Useful when an agent needs limits on files and shell commands. CX Codex ★ 41,729repo stars plugin-eval Lint plugin and skill structure without model calls, then optionally run experimental model-based scoring. Use it to inspect or compare skills. CX Codex ★ 41,729repo stars brand-landingpage Runs a brand discovery interview, builds landing pages through Stitch, and hands back a deployment-ready HTML bundle. Useful when the product exists but the palette and page structure don't. CX Codex ★ 41,729repo stars conductor Turns Claude into a project management tool: context and spec first, code after. Useful when features should follow a plan instead of being improvised. CX Codex ★ 41,729repo stars dgx-spark-ops A plugin for setting up and debugging ML workloads on NVIDIA DGX Spark (GB10): CUDA-13 checks, OOM ladders, thermal monitoring. CX Codex ★ 41,729repo stars developer-essentials A bundle of developer skills for everyday work: Git, SQL, code review, E2E tests, debugging and monorepos. CX Codex ★ 41,729repo stars arm-cortex-microcontrollers Supports ARM Cortex-M firmware work with peripheral drivers and memory safety patterns for Teensy, STM32, nRF52, and SAMD. CX Codex ★ 41,729repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor