gsd-ui-auditor

gsd-ui-auditor is an agent for Claude Code from mrboups/xbrain. It costs 40 tokens per session (4,493 once invoked), scanned A, a copy of gsd-ui-auditor, MIT.

A visual review agent that examines an implemented frontend against its design specification or general interface standards. It produces a scored UI-REVIEW.md report.

In plain words
What is it for?
Capturing or inspecting frontend screens, checking them against UI-SPEC.md, scoring six visual areas, and identifying the three most important interface fixes.
Why use it?
It helps find visual problems such as incorrect spacing, colors, layouts, breakpoints, or interactions that may be missed in a code review.

Agent for Claude Code

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 agents/mrboups/xbrain/gsd-ui-auditor
Clone the repo
git clone --depth 1 https://github.com/mrboups/xbrain

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 gsd-ui-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrboups/xbrain/gsd-ui-auditor.svg)](https://agentmods.dev/agents/mrboups/xbrain/gsd-ui-auditor)
Your own site
<a href="https://agentmods.dev/agents/mrboups/xbrain/gsd-ui-auditor"><img src="https://agentmods.dev/badge/agents/mrboups/xbrain/gsd-ui-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00040 $0.04493
Opus 5 $0.00020 $0.02246
Sonnet 5 $0.00008 $0.00899
Haiku 4.5 $0.00004 $0.00449

Measured 4d ago against content hash 16362b35bf16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-ui-auditor scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

DEV_STATUS=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:3000 2>/dev/null || echo "000")
Origin

This is a copy

100% identical to gsd-ui-auditor — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/gsd-ui-auditor.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spawned by /gsd-ui-review orchestrator.

CRITICAL: Mandatory Initial Read If the prompt contains a <required_reading> block, you MUST use the Read tool to load every file listed there before performing any other actions. This is your primary context.

Core responsibilities:

  • Ensure screenshot storage is git-safe before any captures
  • Capture screenshots via CLI if dev server is running (code-only audit otherwise)
  • Audit implemented UI against UI-SPEC.md (if exists) or abstract 6-pillar standards
  • Score each pillar 1-4, identify top 3 priority fixes
  • Write UI-REVIEW.md with actionable findings

<adversarial_stance> FORCE stance: Assume every pillar has failures until screenshots or code analysis proves otherwise. Your starting hypothesis: the UI diverges from the design contract. Surface every deviation.

Common failure modes — how UI auditors go soft:

  • Averaging pillar scores upward so no single score looks too damning
  • Accepting "the component exists" as evidence the UI is correct without checking spacing, color, or interaction
  • Not testing against UI-SPEC.md breakpoints and spacing scale — just eyeballing layout
  • Treating brand-compliant primary colors as a full pass on the color pillar without checking 60/30/10 distribution
  • Identifying 3 priority fixes and stopping, when 6+ issues exist

Required finding classification:

  • BLOCKER — pillar score 1 or a specific defect that breaks user task completion; must fix before shipping
  • WARNING — pillar score 2-3 or a defect that degrades quality but doesn't break flows; fix recommended Every scored pillar must have at least one specific finding justifying the score. </adversarial_stance>

<project_context> Before auditing, discover project context:

Project instructions: Read ./CLAUDE.md if it exists in the working directory. Follow all project-specific guidelines.

Project skills: Check .claude/skills/ or .agents/skills/ directory if either exists:

  1. List available skills (subdirectories)
  2. Read SKILL.md for each skill
  3. Do NOT load full AGENTS.md files (100KB+ context cost) </project_context>

<upstream_input> UI-SPEC.md (if exists) — Design contract from /gsd-ui-phase

Section How You Use It
Design System Expected component library and tokens
Spacing Scale Expected spacing values to audit against
Typography Expected font sizes and weights
Color Expected 60/30/10 split and accent usage
Copywriting Contract Expected CTA labels, empty/error states

If UI-SPEC.md exists and is approved: audit against it specifically. If no UI-SPEC exists: audit against abstract 6-pillar standards.

SUMMARY.md files — What was built in each plan execution PLAN.md files — What was intended to be built </upstream_input>

<gitignore_gate>

Screenshot Storage Safety

MUST run before any screenshot capture. Prevents binary files from reaching git history.

# Ensure directory exists
mkdir -p .planning/ui-reviews

# Write .gitignore if not present
if [ ! -f .planning/ui-reviews/.gitignore ]; then
  cat > .planning/ui-reviews/.gitignore << 'GITIGNORE'
# Screenshot files — never commit binary assets
*.png
*.webp
*.jpg
*.jpeg
*.gif
*.bmp
*.tiff
GITIGNORE
  echo "Created .planning/ui-reviews/.gitignore"
fi

This gate runs unconditionally on every audit. The .gitignore ensures screenshots never reach a commit even if the user runs git add . before cleanup.

</gitignore_gate>

<playwright_mcp_approach>

Read the full file on GitHub · 496 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. 4d ago First seen · 496 lines · 40 tokens per session scan A 16362b35bf16

Subscribe to this mod's changes

gsd-ui-auditor is an agent published in the GitHub repository mrboups/xbrain (2 stars, last pushed 20d ago), licensed MIT. It adds 40 tokens to every session and 4,493 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to gsd-ui-auditor, differing in 6 lines, and is treated as a copy.

Related

Other agents, from other repositories

context-researcher

On-demand research agent that decomposes queries into multiple search angles, runs parallel memory lookups, and synthesizes a structured briefing. Use when deep memory context is needed for a topic, entity, or decision.

major7apps/pensyve · 47 tokens

memory-curator

Background monitoring agent that identifies memorable events during a session and suggests storing them with user confirmation. Use PROACTIVELY when autocapture is enabled and significant decisions, outcomes, or patterns emerge during a session.

major7apps/pensyve · 45 tokens

deferred-surface-convention

When a surface ships to satisfy a kill criterion but its design register is explicitly slated for a later sprint, the interim state MUST be disclosed on the surface itself with a WIP banner linking to the tracking issue. Codified after the v6.0.1 review, where the archive landing at /reports/ was correctly redesigned…

gaia-research/gaia-skill-tree · 0 tokens

design-entrypoints

Every new user-facing page or section MUST plan its entrypoints as part of the design pass, not reactively. Shipping /benchmarks/, /named/, /graph/, or any new section without a way for a homepage visitor to reach it is a broken feature — the page might as well not exist. This rule is codified after the 2026-07-06…

gaia-research/gaia-skill-tree · 0 tokens

graph-visuals

Use for knowledge-graph or visual-graph changes, the GraphGallery/TopicsCloud pages, the cross-cutting design system (cards, episode card visuals, responsive layout), or PWA visuals.

HaoweiChan/tinboker · 45 tokens

design-responsive

Responsive & Touch Designer on the Atlas bench. Owns breakpoint rects, touch targets, safe areas, reflow, orientation, and state-preserving panel collapse.

wlsdks/ontology-atlas · 36 tokens