visual-audit

visual-audit is a skill for Claude Code from clearsmog/claude-skills. It costs 40 tokens per session (381 once invoked), scanned A, original, MIT.

A visual review of supported documents and slides, including LaTeX, Quarto, and Typst files. It checks the rendered pages for layout and presentation problems.

In plain words
What is it for?
Use it to inspect every page or slide for overflow, typography consistency, repeated colored callouts, alignment, margins, transitions, and framing text.
Why use it?
It helps catch content that runs outside page boundaries, inconsistent fonts, crowded components, poor spacing, and weak page structure before the document is shared.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to inspect every page or slide for overflow, typography consistency, repeated colored callouts, alignment, margins, transitions, and framing text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/clearsmog/claude-skills/visual-audit
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.

Any agent
npx skills add clearsmog/claude-skills --skill visual-audit
Clone the repo
git clone --depth 1 https://github.com/clearsmog/claude-skills

Made for: Claude Code.

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 visual-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/clearsmog/claude-skills/visual-audit/github.svg)](https://agentmods.dev/skills/clearsmog/claude-skills/visual-audit)
Your own site
<a href="https://agentmods.dev/skills/clearsmog/claude-skills/visual-audit"><img src="https://agentmods.dev/badge/skills/clearsmog/claude-skills/visual-audit/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.

agentmods 80×15 button for visual-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/clearsmog/claude-skills/visual-audit"><img src="https://agentmods.dev/badge/skills/clearsmog/claude-skills/visual-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00040 $0.00381
Opus 5 $0.00020 $0.00191
Sonnet 5 $0.00008 $0.00076
Haiku 4.5 $0.00004 $0.00038

Measured 10d ago against content hash 30e63fb8c070, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

visual-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 10d 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.

visual-audit/SKILL.md · 43 lines

What it actually says

Visual Audit

Perform a thorough visual layout audit of any supported document. Routes to the document-auditor agent.

Steps

  1. Read the file specified in $ARGUMENTS

  2. For Quarto (.qmd) files:

    • Render with quarto render Quarto/$ARGUMENTS
    • Open in browser to inspect each slide
  3. For Beamer (.tex) files:

    • Compile and check for overfull hbox warnings
  4. For Typst (.typ) files:

    • Compile with typst compile FILENAME.typ
    • Check for content overflow, component fatigue, typography consistency
  5. Audit every slide/page for:

    OVERFLOW: Content exceeding boundaries FONT CONSISTENCY: Inline font-size overrides, inconsistent sizes COMPONENT FATIGUE: 2+ colored boxes/callouts on one slide/page, wrong types SPACING: Missing margins, missing alignment LAYOUT: Missing transitions, missing framing sentences, semantic colors

  6. Produce a report organized by slide/page with severity and recommendations

  7. Follow the spacing-first principle:

    1. Reduce vertical spacing with negative margins
    2. Consolidate lists
    3. Move displayed equations inline
    4. Reduce image/SVG size
    5. Last resort: font size reduction (never below 0.85em)
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. 10d ago First seen · 43 lines · 40 tokens per session scan A 30e63fb8c070

Subscribe to this mod's changes

visual-audit is a skill published in the GitHub repository clearsmog/claude-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 40 tokens to every session and 381 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

solidworks-engineering-drawing

A SolidWorks skill for creating and reviewing engineering drawings, which are manufacturing documents showing views, measurements, holes, parts lists, and title-block information.

wzyn20051216/solidworks-automation-skill · 58 tokens

release-sync

Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.

yonatangross/orchestkit · 62 tokens

slides

Create, edit, review, and export native PowerPoint presentations through Kun's governed presentation workflow.

KunAgent/Kun · 21 tokens

diagram

Gerar diagramas tecnicos: flowcharts, sequence, ER, architecture, class diagrams. Mermaid (preferido), PlantUML, D2. Trigger quando usuario quer diagrama, fluxo, arquitetura visual, ou ER diagram.

andregusman-raiz/a-gusman-claude · 49 tokens

canvas-design

Use when design visual art and graphics using HTML5 Canvas, p5.js, or SVG. Create generative art, data visualizations, diagrams, and interactive graphics. Use when designing visual art and graphics using html5 canvas, p5.js, or.

oyi77/1ai-skills · 55 tokens

theme-factory

Use when generating and applying professional color themes, typography systems, and design tokens for applications. Create consistent visual identities across platforms.

oyi77/1ai-skills · 29 tokens