agentmods.dev

mpga-ui-audit

mpga-ui-audit is a skill for Claude Code from benrben/MPGA. It costs 23 tokens per session (239 once invoked), scanned A, original, MIT.

A read-only review process for checking the quality of a website or app interface after a build or during review. It groups visual problems by severity and records serious issues for follow-up.

In plain words
What is it for?
It helps audit changed UI files, run a broader interface review when needed, rank findings, and create follow-up work for critical or high-severity issues.
Why use it?
It helps find important interface defects before they reach users and keeps the review focused on the files or screens that changed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mpga plugin — 18 skills, 26 commands, 3 agents shipped together

not rated 5repo 7mo ago A scan 23 tokens original MIT

Good fit It helps audit changed UI files, run a broader interface review when needed, rank findings, and create follow-up work for critical or high-severity issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/benrben/mpga/ui-audit
View source ↗ benrben/MPGA
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 benrben/MPGA --skill ui-audit
Clone the repo
git clone --depth 1 https://github.com/benrben/MPGA

Made for: Claude Code.

Or install mpga, the plugin that ships this one along with the rest of its 18 skills, 26 commands, 3 agents.

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 mpga-ui-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/benrben/mpga/ui-audit"><img src="https://agentmods.dev/badge/skills/benrben/mpga/ui-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 239 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 $0.00023 $0.00239
Opus 5.5 $0.00009 $0.00096
Sonnet 5.5 $0.00005 $0.00048
Haiku 4.5 $0.00002 $0.00024

Measured 2mo ago against content hash 83b11e36b313, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mpga-ui-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 2mo 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.

mpga-plugin/skills/ui-audit/SKILL.md · 36 lines

What it actually says

ui-audit

Trigger: After a build, during review, or as a standalone audit when UI quality needs a hard check.

Protocol

  1. Identify the changed UI files or artifact paths.
  2. Spawn the ui-auditor agent.
  3. Collect the findings and group them by severity.
  4. Auto-create board tasks for any CRITICAL or HIGH findings.
  5. Report the verdict and recommended next action.

Standalone usage

/mpga:ui-audit [path] [--full]

Rules

  • Use the ui-auditor agent for execution.
  • Prefer changed UI files first, then full-repo UI review if needed.
  • Keep the audit read-only and evidence-backed.

Voice announcement

If spoke is available:

mpga spoke 'UI audit complete. Findings ranked and ready for action.'

Output

  • Ranked UI findings
  • Board follow-up tasks for CRITICAL/HIGH issues
  • Final verdict
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. 2mo ago First seen · 36 lines · 23 tokens per session scan A 83b11e36b313

Subscribe to this mod's changes

mpga-ui-audit is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 7mo ago), licensed MIT. It adds 23 tokens to every session and 239 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.

Design and UXFrontend
Related

mpga-ui-audit compared with skills from other repositories

mpga-ui-audit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mpga-ui-auditbenrben/MPGASkill57mo agoMITA23Claude Code
webgl-holographic-foilnexu-io/open-designSkill107ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill107ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill107ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34kyesterdayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10ktodayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6ktodayMITA47Claude Code