---
name: "Metis"
tagline: "Cost-aware swarm orchestration for Claude Code."
description: "An open-source Claude Code plugin marketplace for cost-aware AI coding. Run a budget-bound swarm of agents that plan before they build, and drive visual iOS QA from the same project. MIT licensed."
platforms: ["cli"]
status: "released"
githubUrl: "https://github.com/chensagi/metis"
canonical: "https://blog.chensagi.com/apps/metis"
---

Metis is a marketplace of [Claude Code](https://claude.com/claude-code) plugins
built around one idea: an AI coding session should be cheap, disciplined, and
able to run more than one thing at a time.

## Add it

```text
/plugin marketplace add chensagi/metis
/plugin install metis@metis
/install
```

The optional iOS QA companion installs the same way:

```text
/plugin install ios-qa@metis
```

## What's inside

- **Swarm orchestration.** Parallel task execution with dependency tracking, per-task verification, and a budget ceiling.
- **iOS QA.** Spec-driven visual QA that drives the iOS Simulator and bundles its simulator driver, so there is no separate setup step.
- **Capability packs.** Reusable instruction bundles for TypeScript, React Native, Expo, Python, Go, and more, handed to an agent per task instead of all at once.
- **Cost tracking.** An optional metrics server that reports token spend while the swarm runs.

## How it works

Every task runs the same loop: ask the clarifying questions first, explore the
code, research the approach, plan it, then execute and verify. Cheap models do
the cheap steps. The expensive model is saved for judgment. The payoff is fewer
wrong turns and a token bill you can predict.

Metis is open source under the MIT license. The skills, capabilities, and
plugins are all readable, and the project is built to be extended.