agentmods.dev

fat-design

fat-design is a command for Claude Code from spruikco/fat-agent-skill. It costs 48 tokens per session (500 once invoked), scanned A, original, MIT.

A command that runs a six-part design review on a URL, screenshot, or frontend code. It examines product design, writing, typography, visual craft, interaction, and animation, then ranks findings and proposes fixes.

In plain words
What is it for?
Use it to review a live page, local components, or a screenshot and create prioritized briefs for improving the screen.
Why use it?
It gives a structured way to find interface problems that are easy to miss after the basic screen works.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the fat-agent plugin — 2 skills, 3 commands shipped together

not rated 40repo +2 7d ago A scan 48 tokens original MIT

Good fit Use it to review a live page, local components, or a screenshot and create prioritized briefs for improving the screen.

Compare 6 commands from other repositories ↓
View source ↗ spruikco/fat-agent-skill
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add spruikco/fat-agent-skill
Claude Code
/plugin install fat-agent

Made for: Claude Code.

Or install fat-agent, the plugin that ships this one along with the rest of its 2 skills, 3 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 fat-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/spruikco/fat-agent-skill/fat-design/github.svg)](https://agentmods.dev/commands/spruikco/fat-agent-skill/fat-design)
Your own site
<a href="https://agentmods.dev/commands/spruikco/fat-agent-skill/fat-design"><img src="https://agentmods.dev/badge/commands/spruikco/fat-agent-skill/fat-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.

agentmods 80×15 button for fat-design

Your own site · 80×15
<a href="https://agentmods.dev/commands/spruikco/fat-agent-skill/fat-design"><img src="https://agentmods.dev/badge/commands/spruikco/fat-agent-skill/fat-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 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 $0.00048 $0.00500
Opus 5.5 $0.00019 $0.00200
Sonnet 5.5 $0.00010 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 17d ago against content hash eec3f7e62fd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fat-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 17d 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.

plugins/fat-agent/commands/fat-design.md · 47 lines

What it actually says

/fat-design: the design-taste audit

You have been asked to run FAT Design on a screen.

Setup

  1. Load the skill instructions from ${CLAUDE_PLUGIN_ROOT}/skills/fat-design/SKILL.md and the lens checklists from ${CLAUDE_PLUGIN_ROOT}/references/design/lenses.md.
  2. Work out the target from $ARGUMENTS:
    • A URL: the live screen. Render it (browser tools if available, otherwise a headless capture if Playwright is installed, otherwise fetch the HTML and say the audit is from code alone).
    • A file or directory path: local frontend code. Read the components and styles that make up the screen.
    • Nothing: ask for a URL, a screenshot or a path, and which screen matters most.
  3. Ask one question only if the primary job of the screen is not obvious: "What is this screen for, in one sentence?"

Workflow

  1. Smell test (30 seconds): note any slop tells present.
  2. Six sweeps, one lens at a time, behaviour to finish: product design, copywriting, typography, craft, interaction, animation. Record evidence for each finding.
  3. Rank every finding by harm x frequency x reach into P0 to P3.
  4. Brief the P0 and P1 findings as Job / Change / Consequence.
  5. Report using ${CLAUDE_PLUGIN_ROOT}/references/design/report-template.md.
  6. Offer the repair: fix the highest-cost finding if the code is at hand, then verify on the task that exposed it and run the last-mile check.

If a FAT Agent audit exists for the same site (.fat-work/ in the project), add the P0 and P1 design findings to its punch list under module design.

No em dashes anywhere in the report.

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. 17d ago First seen · 47 lines · 48 tokens per session scan A eec3f7e62fd6

Subscribe to this mod's changes

fat-design is a command published in the GitHub repository spruikco/fat-agent-skill (40 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 500 once invoked, about $0.0002 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 2026-10-21.

Design and UX
Related

fat-design compared with commands from other repositories

fat-design next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fat-designspruikco/fat-agent-skillCommand407d agoMITA48Claude Code
profilecathrynlavery/diagram-designCommand65k3d agoMITA16Claude Code
erne-animateJubaKitiashvili/everything-react-native-expoCommand5029d agoMITA21Claude Code
ui-flow-reviewMRCalderon3D/everything-game-dev-codeCommand10428d agoMITA15Claude Code
responsive-design-specialistimsaif/design-with-claudeCommand11yesterdayMITA36Claude Code
design-auditw2ur/claude-code-setupCommand23d agoMITA30Claude Code
ppt-image2-editable-rebuildwwe-dog/ppt-image2-editable-rebuildCommand2045mo agoUnlicenseA15Claude Code