multi-agents

# multi-agents

Shared multi-agent pipeline setup for Cursor. Provides standard agents, rules, and pipeline tooling that teams copy into their projects. Claude Code support is documented alongside Cursor conventions.

## Prerequisites

- **Cursor** with models enabled for the agents in the pipeline. Some models (e.g. `gpt-5.1-codex-max`) are hidden by default and must be toggled on in `Cursor Settings > Models`. See [Models | Cursor Docs](https://cursor.com/docs/models) for the full list and visibility defaults.
- **Python** 3.10+, **Node.js** 20+, and **git** for tutorials and the sandbox project. See [TESTING.md](TESTING.md) for details.

## Getting started

**Can you explain what agents, rules, and pipelines are?** If not, start with [Foundation](docs/foundation/index.md).

**Can you set up a pipeline and build a feature end-to-end?** If not, go to [Practitioner](docs/practitioner/index.md).

**Ready to design multi-agent systems and lead others?** See [Expert](docs/expert/index.md).

The `.cursor-foundation/`, `.cursor-practitioner/`, and `.cursor-expert/` directories are the canonical source bundles in this repo. Use them for training and for copying into your project.

## Tier directory layout

Each `.cursor-<tier>/` directory follows this structure (not all tiers include every subdirectory):

| Path | Purpose |
|------|---------|
| `agents/*.md` | One file per agent defining its model, role, inputs, outputs, and behavioral instructions. Cursor discovers these as `subagent_type` targets. |
| `rules/*.mdc` | Always-on or file-triggered behavioral guardrails injected into agent context automatically. YAML frontmatter sets `description`, `alwaysApply`, and optional `globs`. |
| `skills/*/SKILL.md` | On-demand capabilities agents pull in when relevant (unlike rules, not auto-injected). Each skill is a subdirectory with a `SKILL.md`. Foundation has none. |
| `pipeline/` | Runtime tooling: `schema.py` (validates artifact JSON), `check.py` (stage-gate invariants), `R