# Project Design System

> Use this package when extending or auditing {{project_name}} UI. It captures the derived tokens, component grammar, architecture, and platform mapping from the shipped code.

- **Type:** Skill
- **Install:** `agentstack add skill-tommylower-cortex-package`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [tommylower](https://agentstack.voostack.com/s/tommylower)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [tommylower](https://github.com/tommylower)
- **Source:** https://github.com/tommylower/cortex/tree/main/design/workflows/asbuilt/assets/templates/package

## Install

```sh
agentstack add skill-tommylower-cortex-package
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# {{project_name}} Design System

Use this package before creating or modifying UI for `{{project_name}}`.

## Read First

1. [references/tokens.md](references/tokens.md)
2. [references/architecture.md](references/architecture.md)
3. [references/components.md](references/components.md)
4. [references/platform-mapping.md](references/platform-mapping.md)

## Thesis

{{design_thesis}}

## Hard Rules

- Code is the source of truth.
- New components enter through the component intake rule in `references/components.md`.
- Use existing semantic tokens before proposing new ones.
- Reuse a behavior floor when one exists.
- Do not copy skin from external references.
- Record unresolved decisions instead of hiding them.

## Anti-Patterns Seen In The Code

- {{anti_pattern}}

## Component Intake

Before adding a new component, classify it:

- `composition`: an arrangement of existing parts
- `headless-floor`: behavior exists in a proven floor; skin it with project tokens
- `novel`: no floor exists; write the full state machine

## Completion Bar

A UI change conforms only when:

- it uses semantic tokens or records a proposed token
- it names the component bucket
- every state is represented
- motion numbers come from this package or the code
- build/lint/test commands listed in `AGENTS.md` pass, or failures are documented

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [tommylower](https://github.com/tommylower)
- **Source:** [tommylower/cortex](https://github.com/tommylower/cortex)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-tommylower-cortex-package
- Seller: https://agentstack.voostack.com/s/tommylower
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.
