Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/vindm/dotclaudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/vindm/dotclaude/design)<a href="https://agentmods.dev/plugins/vindm/dotclaude/design"><img src="https://agentmods.dev/badge/plugins/vindm/dotclaude/design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/vindm/dotclaude/design"><img src="https://agentmods.dev/badge/plugins/vindm/dotclaude/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dotclaude-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "dotclaude-design",
"description": "A design/UX audit layer for Claude Code. /dotclaude:design elicits your design north-star; ux, flow, pages, a11y, interaction, and design-token audits grade every screen against it, plus a product-designer IA/flow spec.",
"version": "3.0.0",
"author": { "name": "Dima Vinokurov" },
"homepage": "https://github.com/vindm/dotclaude",
"repository": "https://github.com/vindm/dotclaude",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 5 skills, 7 agents travel with it, and installing the plugin installs all of them — 1,008 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill design A 67 tokens
- Skill iterative-polish-autoloop A 92 tokens
- Skill element-reuse A 87 tokens
- Skill journey-mapping A 70 tokens
- Skill persona-testing A 74 tokens
- Agent product-designer A 97 tokens
- Agent a11y-audit A 85 tokens
- Agent interaction-audit A 96 tokens
- Agent pages-audit A 0 tokens
- Agent ux-audit A 86 tokens
- Agent flow-audit B 157 tokens
- Agent design-token-audit C 97 tokens
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 10 lines scan A 88f970ccbdce
dotclaude-design is a plugin published in the GitHub repository vindm/dotclaude (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
ux-ui-agent-skills
Turn Claude into a senior design architect: DTCG design tokens, 52 components, WCAG 2.2 AA to AAA accessibility, 138 brand-grade design systems, any-framework code generation, and 52 objective quality gates that fail the build instead of claiming success.
humane
21 design-method skills for people and agents: evidence, prototypes, tokens, typography, semantic interactions, scroll stories, optional sound, reviews, and framework adaptation.
frontend
Frontend development specialists for React, Vue, Next.js, CSS, HTML, and UI/UX design. Comprehensive coverage of modern frontend technologies.
feinschliff
Office / decks (PowerPoint) for Claude Code — brand-pluggable design system via the feinschliff CLI. Ships the feinschliff brand pack with 8 themes (default, claude, catppuccin-latte, catppuccin-macchiato, feinschliff-dark, gruvbox-dark, nord, solarized-dark). Image/2D, video, and audio live in the sibling feinbild.
webability-accessibility
Scan pages and HTML for WCAG 2.2 / ADA / Section 508 issues, get framework-aware fixes, and verify them. Free hosted MCP from WebAbility.
bleu
Claude Code plugin for living blueprints. Turn an idea into a deeply structured, lint-passing, file-backed system plan before writing any code.