uxaudit-l4-judge

uxaudit-l4-judge is an agent for Claude Code from gotalab/uxaudit. It costs 111 tokens per session (5,029 once invoked), scanned A, original, Apache-2.0.

A strict reviewer for one captured user journey in the uxaudit pipeline. It examines ordered screenshots, the recorded actions, and the check’s rubric, then writes a pass, fail, or unverifiable verdict.

In plain words
What is it for?
Use it to evaluate a recorded journey across four aspects of the experience and save the result as result.json.
Why use it?
Separating evidence capture from judgment helps keep the review tied to what the user actually saw and did, rather than to assumptions about the source code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the uxaudit plugin — 1 skill, 7 agents, 1 hook shipped together

Good fit Use it to evaluate a recorded journey across four aspects of the experience and save the result as result.json.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gotalab/uxaudit/uxaudit-l4-judge
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.

Clone the repo
git clone --depth 1 https://github.com/gotalab/uxaudit

Made for: Claude Code.

Or install uxaudit, the plugin that ships this one along with the rest of its 1 skill, 7 agents, 1 hook.

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 uxaudit-l4-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-l4-judge/github.svg)](https://agentmods.dev/agents/gotalab/uxaudit/uxaudit-l4-judge)
Your own site
<a href="https://agentmods.dev/agents/gotalab/uxaudit/uxaudit-l4-judge"><img src="https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-l4-judge/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 uxaudit-l4-judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/gotalab/uxaudit/uxaudit-l4-judge"><img src="https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-l4-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00111 $0.05029
Opus 5 $0.00056 $0.02514
Sonnet 5 $0.00022 $0.01006
Haiku 4.5 $0.00011 $0.00503

Measured 11d ago against content hash 0baa1c0bce41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

uxaudit-l4-judge 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 11d 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.

description: "L4-journey Judge for the uxaudit pipeline. Reads the per-journey capture directory (screenshots + steps.json + evaluation brief) and writes a strict pass/fail/unverifiable verdict with four-axis journey_eva
agents/uxaudit-l4-judge.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

uxaudit L4-journey Judge

You are an L4-journey Judge for uxaudit. You evaluate ONE captured journey (a directory of ordered screenshots plus a steps.json action trace) against ONE check's rubric (prompt.md) and one per-journey evaluation brief, then write a strict verdict with a four-axis journey_evaluation block.

You have Read, Write, and Glob onlyGlob so you can enumerate evidence/*.png in capture order, nothing more. No Bash, no WebFetch, no Grep, no Edit. You cannot drive a browser, you cannot curl the running app, you cannot read journey-scripts/*.json, the spec, or any source file. The capture is already done. Your only inputs are the PNG files, steps.json, the check's prompt.md, and the per-journey brief. The tool surface is itself the rationalization gate.

What the dispatch prompt gives you

  • check_id: e.g. core-experience/primary-journey or usability/first-time-user-experience — the canonical slug, must be echoed verbatim into your result.json. L4 journey checks all share core-experience/primary-journey — never invent per-journey slugs; distinguish journeys via the journey_name field or narrative prose.
  • prompt_path: absolute path to the check's prompt.md (the per-axis rubric)
  • evidence_dir: absolute path to <iter-dir>/checks/<check-dir>/evidence/ — a directory of 001.png, 002.png, … screenshots (3-digit zero-padded, sort order matches capture order)
  • steps_json_path: absolute path to <iter-dir>/checks/<check-dir>/evidence/steps.json — the capture trace
  • brief_path: absolute path to <iter-dir>/evaluation-briefs/<journey-id>.json — the compressed UX contract for this journey
  • journey_name: the journey's human name from the contract (e.g. "Create a recipe"), copied into your verdict
  • output_path: absolute path to write result.json to
  • Language: en or ja — controls narrative output language

Three-stage Judge protocol (WebJudge-inspired)

Read the full file on GitHub · 229 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. 11d ago First seen · 229 lines · 111 tokens per session scan A 0baa1c0bce41

Subscribe to this mod's changes

uxaudit-l4-judge is an agent published in the GitHub repository gotalab/uxaudit (54 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 111 tokens to every session and 5,029 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

ui-visual-validator

Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.

wshobson/agents · 54 tokens

product

You are the product quality evaluator for the Kernel AI platform. You think like a user, not an engineer.

isaacsight/kernel · 0 tokens

visual-qa-agent

Visual regression testing and design comparison agent. Renders web app pages via Chrome DevTools and Playwright, captures Figma designs, and produces structured visual diff reports with cross-browser testing.

PMDevSolutions/Aurelius · 42 tokens

visual-reviewer

Drives the visual-review loop for generated UI — boots the app via the ui-harness runner, runs the axe-core a11y gate + anti-slop rubric, reads the screenshots multimodally, scores them against DESIGN.md, and reports triaged findings until the design bar is met.

gosha70/code-copilot-team · 63 tokens

ui-visual-validator

Use this agent to verify whether UI modifications have achieved their intended goals through rigorous screenshot analysis. Essential for validating visual changes, fixes, and improvements after implementation.

NOMARJ/sigil · 36 tokens

clone-team-tester

The most important quality gate on the clone-team. An expert in testing methodology AND UX who runs a full regression of every delivery against the original site and returns a strict OK/NG verdict with specific, reproducible issues. Loads ui-pack and verifies through agent-browser. Spawned by the clone-team Manager /…

Varalix-Digitech-Solutions/clone-team · 70 tokens