ui-test

ui-test is a command for coding agents from xcodethink/open-claude-code-skills. It costs 32 tokens per session (516 once invoked), scanned A, original, MIT.

A UI review command that changes an interface to match a design and then checks the result in a real browser.

In plain words
What is it for?
Use it when implementing or reviewing a design, checking the main user flow, and testing loading, empty, error, offline, mobile, Chrome, and Safari cases.
Why use it?
It catches visual and functional problems that type checks and automated tests may miss, including issues on different browsers, screen sizes, and less common states.

Command

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 commands/xcodethink/open-claude-code-skills/ui-test
Clone the repo
git clone --depth 1 https://github.com/xcodethink/open-claude-code-skills

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 ui-test

README.md
[![agentmods](https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/ui-test.svg)](https://agentmods.dev/commands/xcodethink/open-claude-code-skills/ui-test)
Your own site
<a href="https://agentmods.dev/commands/xcodethink/open-claude-code-skills/ui-test"><img src="https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/ui-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00516
Opus 5 $0.00016 $0.00258
Sonnet 5 $0.00006 $0.00103
Haiku 4.5 $0.00003 $0.00052

Measured 3d ago against content hash 5c91779c7cae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-test 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.

commands/ui-test.md · 32 lines

What it actually says

ui-test — UI 还原 + 浏览器实测

用户输入 /ui-test $ARGUMENTS 触发 代码改 + 浏览器实测(防"改完没真去看"陷阱)。

"真去浏览器看 / 评判 UI"默认用 (自研 AI 浏览器审计器, 已注册为 MCP server + 全局 link; 见全局 CLAUDE.md 顶部铁律)。

  • 优先: MCP 工具 (see/judge/compare) > <ui-audit-tool> explore --url <url> --goal <..> --criteria <..> / <ui-audit-tool> run > 自写 Playwright
  • <ui-audit-tool> doctor 自检; key 在 <该工具仓>/.env; 首次 AUDIT_AUTO_CONSENT=1
  • 下面的 Playwright/手动流程仅作 确实不可用时的兜底, 不要默认走它。

立刻读取并完整加载: ~/.claude/prompts/lib/06-设计/UI还原浏览器实测.md

按其"行为契约"段严格执行:

  1. 按设计稿改代码
  2. 启动 dev server,真去浏览器看(不只是"类型检查通过 = 完成")
  3. 跑通golden path + 边缘 case(空状态 / 错误 / 加载 / 离线)
  4. 多设备 / 多浏览器(至少 Chrome + Safari + 手机宽度)
  5. 监控"是否破坏了其他功能"

无法跑浏览器(headless 环境)→ 明确说不能,不假装完成

参数含修饰符 → 叠加对应文件。

核心契约:类型检查 / 测试套件验代码正确性,不验功能正确性。UI 改动不去浏览器看 = 没做完。

参数: $ARGUMENTS

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. 3d ago First seen · 32 lines · 0 tokens per session scan A 5c91779c7cae

Subscribe to this mod's changes

ui-test is a command published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 28d ago), licensed MIT. It adds 32 tokens to every session and 516 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.