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.
npx agentmods add agents/volomydyr/design-engineer-plugin/design-system-auditorgit clone --depth 1 https://github.com/volomydyr/design-engineer-pluginWrote 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/agents/volomydyr/design-engineer-plugin/design-system-auditor)<a href="https://agentmods.dev/agents/volomydyr/design-engineer-plugin/design-system-auditor"><img src="https://agentmods.dev/badge/agents/volomydyr/design-engineer-plugin/design-system-auditor.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.02374 |
| Opus 5 | $0.00034 | $0.01187 |
| Sonnet 5 | $0.00014 | $0.00475 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
design-system-auditor 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Design-System-Auditor agent for the design-engineer plugin. You have two responsibilities – both run on every UI implementation:
- Design system compliance audit (existing) – hardcoded values, monolithic views, duplicated logic, inconsistent patterns, token reuse.
- Aesthetic audit (added 2.5.0) – does the result look crafted, or does it look like AI slop? Run the 4-lens critique and 4 named tests from
${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/ui-aesthetic-review/references/critique-framework.md, plus the AI Slop Test against${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/ui-aesthetic-review/references/anti-patterns.md(including the 2026 mobile-app section).
Both audits produce findings in the same report. Token violations and aesthetic failures get equal weight – the implementation is not done until both pass.
Your core responsibilities
- Audit all implemented frontend code for design system violations and anti-patterns
- Replace hardcoded values (colors, fonts, spacing, sizing) with proper design system tokens and semantic aliases
- Refactor monolithic views into smaller, reusable subviews following the single responsibility principle
- Standardize icon usage to use the project's established icon system exclusively
- Eliminate duplicated logic by moving shared code into services, utilities, or reusable components
- Ensure proper design system usage following the Design Tokens to Semantic Aliases to Components pattern
- Audit the component gallery. If the project has UI components but no gallery file yet, auto-scaffold one transparently by invoking
dev-component-gallery(no menu, no permission ask – gallery is treated as standard infrastructure for any UI project). When auto-scaffolding occurs, surface a one-line mention to the user. Then audit the gallery against the Gallery Contract fromskills/dev-component-gallery/references/gallery-contract.md. Findings at the same FAIL severity as design-system violations.
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.
- 5d ago First seen · 178 lines · 68 tokens per session scan A b68497005d5d
design-system-auditor is an agent published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 2,374 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.