Skip to main content
plugin

agent-teams · phuryn — Claude Code plugin: features and installation

The agent-teams Claude Code plugin guides task delegation and lets coding agents act as peers, builders, or independent reviewers. Use it to brief a delegate or work with Codex CLI, Grok CLI, or headless Claude Code.

MIT ★ 741 updated 2026-11-14

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add phuryn/product-engineering
/plugin install agent-teams@product-engineering
Open on GitHub

What agent-teams does

agent-teams helps create delegate briefs that explain the goal, rationale, constraints, and how to check the result. Its skills cover Codex CLI, Grok CLI, and headless Claude Code, where another agent can use them to discuss a decision, handle a work stage, or review changes.

The Codex and Claude Code guidance includes wrappers that preserve session continuity. Grok guidance covers named sessions and device-code sign-in. Gemini runs through the Antigravity CLI only after the user agrees. Google does not support this access on consumer plans, and a terms violation can lead to suspension; API-key and Cloud routes are documented. The independent review cycle lives in independent-review from the ai-shipping pack.

What it helps with

  • write a delegate brief with a goal and constraints
  • hand a work stage to Codex CLI
  • run Grok CLI as a separate reviewer
  • drive Claude Code headlessly from another agent
  • start Gemini through Antigravity with user approval

Example prompts for the agent

  • Draft a delegate brief with the goal, rationale, constraints, and a way to verify the result.
  • Show how to use Codex CLI as the builder for one stage.
  • Explain how to run Grok CLI as an independent reviewer.

How to install agent-teams

Plugin marketplace

/plugin marketplace add phuryn/product-engineering
/plugin install agent-teams@product-engineering

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 Code?

Run these commands in order: /plugin marketplace add phuryn/product-engineering, then /plugin install agent-teams@product-engineering.

What does agent-teams do?

It provides skills for delegation and for working with Codex CLI, Grok CLI, Claude Code, and Gemini through Antigravity. Agents can serve as peers, builders, or reviewers.

What does agent-teams require for Gemini?

Gemini through Antigravity requires user approval. Google does not support this access on consumer plans; API-key and Cloud routes are documented.

Source text

agent-teams · MIT
# agent-teams — work with other agents as partners

A delegate is a partner, not a tool: it gets the why, not just the what. These skills are how to brief any delegate, and how to drive each kind — the Codex CLI, the Grok CLI and Claude Code, each run headless by another agent as a peer, builder or reviewer. Gemini through Google's Antigravity CLI is an option the user agrees to first. The review loop itself, round after round, is `independent-review`, in the `ai-shipping` pack.

## Install

```bash
claude plugin marketplace add phuryn/product-engineering
claude plugin install agent-teams@product-engineering
```

Codex, Cursor and other agents: see the collection's root `README.md`.

## Skills (5)

- **delegation** — The shared doctrine: what never delegates, when a change is too small to hand off, the brief (goal and why, binding constraints and traps, how to prove it), choosing the delegate and its model, parallel work without lost writes, and verifying what comes back.
- **codex-agents** — The OpenAI Codex CLI as a peer you argue decisions with, a builder you hand stages to, or a fresh reviewer, through a wrapper that keeps sessions per directory, resumes by id and re-sends the model on every resume, and a tested command for a read-only review session.
- **grok-agents** — The Grok CLI driven headless from another agent as a peer, a builder or a fresh reviewer: the flags for each, sessions you name and resume, the isolation a review needs, signing in by device code, and what an out-of-credit answer looks like.
- **claude-agents** — How Codex, Grok, Cursor or another Claude session drives Claude Code headless as a peer, builder or reviewer, through a wrapper with session continuity and safe permission modes.
- **gemini-agents** — Gemini through Google's Antigravity CLI as a peer, builder or second reviewer, through a wrapper that checks what actually ran. Unsupported by Google on consumer plans (FAQ read 2026-11-13): third-party access through an Antigravity sign-in breaks the terms and can lead to suspension. API-key or Cloud routes are documented. The user agrees first, per run or as an explicit standing preference; Gemini is never a default.

Which of them reviews a release, and how a review round runs, is `independent-review`, in the `ai-shipping` pack.

## Author

Paweł Huryn — [The Product Compass](https://www.productcompass.pm)

© Paweł Huryn · MIT · phuryn/product-engineering

Similar plugins

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

agent-teams by other authors comes first.

From the same set51

The whole set →
app-lifecycle The app-lifecycle skill for Claude Code and Codex maps a SaaS product’s path from idea to production into stages with completion criteria. It activates for questions about the current stage, next steps, or whether a stage is done. CX Codex +1 ★ 741repo stars codex-agents The codex-agents Claude Code skill brings Codex CLI in as a second agent for implementation and independent review. It responds to requests to consult Codex and to decisions with competing options. CX Codex +1 ★ 741repo stars independent-review The independent-review Claude Code skill runs an independent code review before a release and after fixes. The reviewer must start in a session that did not build the change. CX Codex +1 ★ 741repo stars work-humanizer work-humanizer is a Claude Code plugin that revises work writing with an AI-like tone while preserving its meaning. It can also interview the writer and shape a piece from their answers. ★ 741repo stars app-stack The app-stack Claude Code plugin guides SaaS development from idea to production with Next.js, Supabase, Clerk, and Netlify. Its skills cover product stages, authorization, UI, analytics, and more. ★ 741repo stars agent-harness The agent-harness Claude Code plugin organizes agent instructions, hooks, and persistent work status. Its skills handle session handovers and turn session friction into setup changes. ★ 741repo stars ai-shipping The ai-shipping Claude Code plugin documents AI-built apps and checks changes before release. Its ship-check command brings documentation, reviews, and test coverage into one workflow. ★ 741repo stars product This Claude Code plugin helps decide what to build before development starts. It turns idea research, hypotheses and key screens into a draft for the product owner to review. ★ 741repo stars

Project sponsors

Companies that keep this analytics open