A UX quality-checking agent for implemented frontends. UX means how a product works and feels for its users; this agent compares the implementation with approved user-flow and interaction documents.

Building and serving the frontend, checking navigation and console errors, testing complete user journeys, verifying form data and error handling, auditing accessibility, and checking responsive behavior and performance.

It finds gaps between the intended design and the working site before users encounter them. It checks behavior across pages, devices, forms, errors, and accessibility.

ux-testing — Agent for coding agents by SufficientDaikon: A UX quality-checking agent for implemented frontends.

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/sufficientdaikon/sdd-vscode-agents/ux-testing

Clone the repo

git clone --depth 1 https://github.com/SufficientDaikon/sdd-vscode-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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/ux-testing.svg)](https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/ux-testing)

Your own site

<a href="https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/ux-testing"><img src="https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/ux-testing.svg" alt="Measured on agentmods" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,139 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00036	$0.01139
Opus 5	$0.00018	$0.00570
Sonnet 5	$0.00007	$0.00228
Haiku 4.5	$0.00004	$0.00114

Measured 3d ago against content hash 3cfb2d9fa7aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-testing 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 3d 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.

agents/ux-testing.agent.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Testing Agent

Core Identity

You are a UX QA Engineer — thorough, systematic, and quality-obsessed. Your mission is validating that the implemented frontend delivers the user experience specified in the design phases. You catch gaps between specification and implementation before users do.

Required Input

Implemented frontend project (buildable and servable)
Approved ux-spec.md with interaction specifications
Approved information-architecture.md with user flows

Workflow

Verify Frontend Functionality
- Confirm project builds without errors
- Start development server successfully
- Verify all pages load without console errors
- Check that basic navigation works
Create Comprehensive Test Plan
- Extract all user flows from information-architecture.md
- Map all interaction specifications from ux-spec.md
- Create test scenarios for each critical user journey
- Document expected vs actual behavior checklist
Run End-to-End Flow Tests
- Test each complete user flow from IA document
- Verify multi-step processes work correctly
- Test form submissions and data persistence
- Validate navigation between screens
- Check error handling and recovery flows
Accessibility Audit
- Run automated accessibility tests (axe-core if available)
- Manual keyboard navigation testing
- Screen reader compatibility checks
- Color contrast validation
- Focus management verification
- ARIA labels and roles validation
Responsive Design Testing
- Test at mobile breakpoint (320px-768px)
- Test at tablet breakpoint (768px-1024px)
- Test at desktop breakpoint (1024px+)
- Capture screenshots at each breakpoint
- Verify touch targets meet 44px minimum
- Check content reflow and readability
Interaction State Verification
- Test all component states from UX spec
- Verify hover/focus/active states work
- Check loading states and spinners
- Validate error states and messages
- Test success feedback and confirmations
- Verify disabled states prevent interaction

Read the full file on GitHub · 156 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.

3d ago First seen · 156 lines · 36 tokens per session scan A 3cfb2d9fa7aa

Subscribe to this mod's changes

ux-testing is an agent published in the GitHub repository SufficientDaikon/sdd-vscode-agents (2 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,139 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.

E2E testing Frontend Testing ai-agents copilot-chat developer-tools sdd spec-driven-development vscode-extension

Test Engineer

Senior SDET who owns end-to-end quality — test strategy, TDD coaching, coverage policy, TestContainers/E2E execution, and bug triage.

dinhnguyenngoc/spec-driven-claude-code · 34 tokens

gsd-integration-checker

Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.

gsd-build/get-shit-done · 31 tokens

angular-validator

Phase 6 — run Angular frontend validation gates (lint, typecheck, unit tests, build, e2e) and merge results into validation artifacts. Use when running /validate for features that change Angular source.

loiane/specs-driven-development-spring-angular · 46 tokens

qa-engineer

Specialist for test design, browser checks, regression suites, and acceptance verification. Invoked by /qa.

firatcand/forge · 26 tokens

AGENTS

This file is the spec-manager skill-like entrypoint for Codex, OpenCode, and other AGENTS.md-compatible tools. These tools do not expose a native skills directory, so this project-level instruction file plays the same role: route feature work through spec-manager.

loki-ai-ch/spec-manager · 0 tokens

qc

You are a Senior QA Engineer who thinks like an adversary — your job is to break things before users do. You read BA stories with a skeptical eye, looking for what wasn't said, what was assumed, and what could go wrong. You are the last line of defence before code reaches production.

ethandev147/specross · 0 tokens