Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fusengine/agentsnpx agentmods add commands/fusengine/agents/audit-designWrote 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/commands/fusengine/agents/audit-design)<a href="https://agentmods.dev/commands/fusengine/agents/audit-design"><img src="https://agentmods.dev/badge/commands/fusengine/agents/audit-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/commands/fusengine/agents/audit-design"><img src="https://agentmods.dev/badge/commands/fusengine/agents/audit-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.00480 |
| Opus 5.5 | $0.00015 | $0.00192 |
| Sonnet 5.5 | $0.00007 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
design-audit 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
/design:audit — Design Quality Audit
Validate an existing design without generating new code.
Complete documentation: skills/design-review/SKILL.md.
Usage
/design:audit ./pages/index.html
/design:audit ./site-1/
/design:audit
When no path is provided, audits all HTML files in the current directory.
Workflow
- Identify target files (path argument, or all
.htmlin the current directory). - Read
design-system.mdif it exists — the reference for token compliance. If missing, audit againstskills/design-system/references/typography-pairs.md(forbidden fonts) andcontrast-ratios.md(contrast) only. - Run
skills/design-review/SKILL.mdPart 1 (deterministic checks): contrast, forbidden fonts, color format, em-dash, token adherence, anti-AI-slop, mechanical pre-flight, WCAG, consistency. - Run Part 2 (bounded visual review): serve, screenshot light+dark, cross-viewport, motion verdict if any animation exists.
- Report with severity levels: CRITICAL (contrast, missing dark mode, broken accessibility), MAJOR (forbidden fonts, non-OKLCH colors, missing states), MINOR (token mismatches), PASS.
Output Format
| Check | Status | Details |
|-----------|----------|----------------------------------------|
| Fonts | FAIL | Found Inter in header.css:12 |
| Colors | WARN | 3 hex values found, convert to oklch() |
| Contrast | PASS | All ratios >= 4.5:1 |
| States | WARN | Missing :focus on .btn-secondary |
| Dark mode | FAIL | No dark mode implementation found |
Forbidden
Generating or modifying code (audit only, unless the user explicitly asks for fixes afterward). Skipping any deterministic check. Reporting PASS without actually verifying. Skipping the light+dark screenshot pass.
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 · 44 lines · 37 tokens per session scan A 7593cec07493
design-audit is a command published in the GitHub repository fusengine/agents (32 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 480 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
shadcn-ui
Install and configure shadcn/ui components.
ccc-multi-frontend
Frontend-focused multi-model workflow (research, ideation, plan, execute, optimize, review) with Gemini as the UI authority. Use for components, responsive layout, UI animation and style work.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.