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.
npx skills add willnie9/agent-skills --skill auto-ui-explorergit clone --depth 1 https://github.com/willnie9/agent-skillsWrote 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.
[](https://agentmods.dev/skills/willnie9/agent-skills/auto-ui-explorer)<a href="https://agentmods.dev/skills/willnie9/agent-skills/auto-ui-explorer"><img src="https://agentmods.dev/badge/skills/willnie9/agent-skills/auto-ui-explorer/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.
<a href="https://agentmods.dev/skills/willnie9/agent-skills/auto-ui-explorer"><img src="https://agentmods.dev/badge/skills/willnie9/agent-skills/auto-ui-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00075 | $0.12092 |
| Opus 5 | $0.00037 | $0.06046 |
| Sonnet 5 | $0.00015 | $0.02418 |
| Haiku 4.5 | $0.00007 | $0.01209 |
Grade A, and why
auto-ui-explorer 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 739 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto UI Explorer · 全模块 E2E 测试编排大师
本 skill 依赖
playwright-skill执行浏览器操作。所有浏览器参数从playwright-skill/config/playwright-skill.config.json读取，不写死。 噪音黑名单和表单组件类型从config/auto-ui-explorer.config.json读取，可按项目定制。
目录结构
.claude/skills/auto-ui-explorer/
├── SKILL.md 本文件
│
├── config/ 项目适配层
│ └── auto-ui-explorer.config.json 噪音黑名单 + 点击事件模式 + 表单组件类型
│
├── schemas/ 硬契约
│ ├── ui-dictionary.schema.json Step 1 词典输出的 JSON Schema
│ ├── baseline.schema.json ★ baseline 结构校验
│ └── experience.schema.json ★ experience 结构校验
│
├── scripts/ 脚本工具
│ ├── analyze-module.mjs 全目录递归扫盘器(读 config)
│ ├── validate-dictionary.mjs Step 1 产物校验(校验 schema)
│ ├── validate-flow-plan.mjs Step 2.6 产物校验(SP 引用/覆盖率/空值拦截)
│ └── diff-baseline.mjs ★ Step 0.7 增量判断脚本
│
├── references/ 子文档(详细规范)
│ ├── single-point-spec.md 单点测试用例编写规范
│ ├── failure-tags.md 失败分类标签定义
│ ├── form-data-generation.md 表单测试数据生成规则
│ └── status-markers.md ★ 状态标记体系与责任归属
│
└── output/ ⚠️ gitignore — 运行产物
├── <module>-ui-dictionary.json Step 1 的词典
├── <module>-E2E-FLOW-PLAN.md Step 2 的剧本
├── <module>-API-AUDIT.md Step 0.9 的 API 对接审计报告
├── <module>-E2E-REPORT.md Step 6 的最终测试报告
├── <module>-baseline.json ★ 增量执行基线（断点续跑依据）
└── <module>-experience.json ★ 操作经验库（跨对话复用）
测试模式 (Test Mode) ★★★
用户启动测试时必须选择模式，或从输入关键词自动推断。模式贯穿全流程，影响 Step 0.9 / Step 4 / Step 5 / Step 6 的行为。
模式一：mock — 测试 Mock 拦截层
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- config/auto-ui-explorer.config.json 672 B
- references/execution-templates.md 7.6 KB
- references/failure-tags.md 3.4 KB
- references/form-data-generation.md 2.5 KB
- references/single-point-spec.md 2.0 KB
- references/status-markers.md 12 KB
- schemas/baseline.schema.json 2.2 KB
- schemas/experience.schema.json 4.3 KB
- schemas/ui-dictionary.schema.json 2.9 KB
- scripts/analyze-module.mjs 8.3 KB runs code
- scripts/diff-baseline.mjs 3.5 KB runs code
- scripts/validate-dictionary.mjs 3.2 KB runs code
- scripts/validate-flow-plan.mjs 4.5 KB runs code
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.
- 9d ago First seen · 739 lines · 75 tokens per session scan A 8d4497e3b361
auto-ui-explorer is a skill published in the GitHub repository willnie9/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 12,092 once invoked, about $0.0004 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.
Other skills, from other repositories
vibe-behavioral-test-capture
Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture generation.
browser-proof
Browser-visible verification — route smoke, screenshots, console errors. Receipt required.
dev-browser
CIEL's framework for browser automation with persistent page state. Navigates URLs, fills forms, takes screenshots, scrapes data, and tests web apps via sandboxed JavaScript scripts.
webapp-testing
Verify a local web app in a real browser with page, element, click, form, console and screenshot evidence. Use after a build or UI change; do not implement features or publish deployments with this skill.
e2e-and-visual-verification
CIEL's framework for Playwright E2E testing and intentional frontend design.
vibe-e2e
A browser-based end-to-end check of a running project. It tests pages, buttons, forms, browser output, and API responses as a real user would.