audit

audit is a command for Claude Code from Muminur/frontend-design-craft-skill. It costs 13 tokens per session (636 once invoked), scanned A, original, MIT.

A read-only review of a page, interface component, or codebase’s visual design. It examines polish, motion, and overall design judgment.

In plain words
What is it for?
Auditing typography, spacing, color contrast, layout behavior, animation, visual consistency, and the overall design style.
Why use it?
It identifies design problems without changing the code, so the team can decide what should be improved afterward.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the craft plugin — 4 skills, 13 commands shipped together

Install

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.

agentmods
npx agentmods add commands/muminur/frontend-design-craft-skill/audit
Clone the repo
git clone --depth 1 https://github.com/Muminur/frontend-design-craft-skill

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 4 skills, 13 commands.

Wrote 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.

agentmods badge for audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/audit.svg)](https://agentmods.dev/commands/muminur/frontend-design-craft-skill/audit)
Your own site
<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/audit"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 636 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.00636
Opus 5 $0.00006 $0.00318
Sonnet 5 $0.00003 $0.00127
Haiku 4.5 $0.00001 $0.00064

Measured 5d ago against content hash 5fa2473d553c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 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.

commands/audit.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit

Run a structured design audit across motion, polish, and taste. Report only — do not fix anything in this pass.

Target

$ARGUMENTS

If no target is given, audit the most recently discussed file or, if there is none, ask the user what to audit.

Procedure

  1. Determine mode. Look at the target. Is it a marketing/brand page or a product/app UI? State which.
  2. Determine archetype. If the design has a clear archetype already (editorial, soft-premium, brutalist, expressive, technical), name it. If it does not, note that as a finding.
  3. Run each lens. For each of the three lenses below, list findings with severity (CRITICAL / HIGH / MEDIUM / LOW).

Lens 1 — Polish (typography, spacing, layout, color)

Check every item in the polish checklist (see skills/polish/SKILL.md):

  • Spacing values on a consistent scale
  • Type scale defined and applied
  • Line-height calibrated per size
  • No pure black/white in content
  • WCAG AA contrast
  • Border radius / shadow consistency
  • Layouts change vs. resize at breakpoints

Lens 2 — Taste (anti-slop)

Check the ban list:

  • Purple-blue / pink-orange gradients
  • Glassmorphism / frosted glass cards
  • Gradient text
  • Inter as default sans
  • Centered hero with stacked CTA + image below
  • Three equal-column feature grid
  • shadcn/ui defaults unmodified
  • John Doe, Lorem ipsum, fake stats
  • Stock photos / generic Unsplash imagery
  • Bento grids without visual variation

Lens 3 — Motion

  • Animations communicate state vs. decorate
  • Easing curves consistent across related elements
  • Timing matches weight of change
  • prefers-reduced-motion respected
  • Only transform / opacity animated
  • No transition: all

Output format

## Audit: [target]

**Mode:** [brand | product]
**Archetype:** [name, or "undefined — pick one"]
**Dials (inferred):** VARIANCE: x, MOTION: y, DENSITY: z

### CRITICAL (must fix before ship)
1. [issue] — [location] — [why it matters]
2. ...

### HIGH (visible quality drag)
...

### MEDIUM
...

### LOW (nice to have)
...

## Recommended next steps
1. Run `/typeset` to address typography findings
2. Run `/arrange` to address spacing findings
3. Run `/anti-slop` to address generic patterns

Read the full file on GitHub · 85 lines

Changes

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.

  1. 5d ago First seen · 85 lines · 13 tokens per session scan A 5fa2473d553c

Subscribe to this mod's changes

audit is a command published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 636 once invoked, about $0.0001 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 2026-08-31.