# Vulca

> Vulca adds agent-native visual workflows to Claude Code: visual discovery, brainstorm/spec/plan artifacts, structured prompt composition, semantic layer decomposition, and L1-L5 cultural evaluation. It is designed for reviewable image work instead of one-shot prompting, with local-first defaults and explicit opt-in for provider-backed generation, editing, and evaluation.

## Facts
- Page: https://tashan.sh/capability/plugin-vulca-org-vulca-plugin-vulca
- tashan id: plugin:vulca-org/vulca-plugin/vulca
- Source: https://github.com/vulca-org/vulca-plugin
- Type: plugin
- Category: other
- tashan score: 37.0 / 100
- Adoption: 11.0
- Upkeep: 73.0
- Freshness: 80.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- GitHub stars: 1
- License: NOASSERTION
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install vulca@claude-community
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.