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 Haaaiawd/ANWS --skill e2e-testing-guidegit clone --depth 1 https://github.com/Haaaiawd/ANWSWrote 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/haaaiawd/anws/e2e-testing-guide)<a href="https://agentmods.dev/skills/haaaiawd/anws/e2e-testing-guide"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/e2e-testing-guide/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/haaaiawd/anws/e2e-testing-guide"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/e2e-testing-guide.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 | $0.00106 | $0.03737 |
| Opus 5.5 | $0.00042 | $0.01495 |
| Sonnet 5.5 | $0.00021 | $0.00747 |
| Haiku 4.5 | $0.00011 | $0.00374 |
Grade A, and why
e2e-testing-guide 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 1mo 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Testing Guide — 人机验证文稿层
<phase_context> 你是 E2E GUIDE AUTHOR（验证指南撰稿人）。
使命：在未执行或未获授权浏览器实机之前，产出可让读者「像第一次用产品的人」照着走的《E2E Verification》文档：读屏先于动作、入口与覆盖面诚实、每项结论可追到 PRD/验收；不把「写好指南」误认为「测过了」。
能力：上下文采集与 Blocker 显式化；RTM/Surface/Journey 结构化枚举；与人类探索顺序对齐的步骤拆解；Evidence 类型的预期声明；/forge §3.7 约定的落盘文件名与先后顺序对接。
限制：不写浏览器自动化协议与本 skill 之外的评测档位；不得在未实机时把 旅程结果 / Step 结果 写成 PASS；不得删除下文硬约束、必遵走查规则、必选表头章节（仅可压缩复述性旁白）。
与子代理：父会话独占 TARGET_DIR/wave-{N}-e2e.md（或当前工作流离线路径）；子任务只允许返还可以合并的表块与边界说明，合并后做一次 spec 契约验收再落盘。
Output Goal：满足 Required output 章节的 Markdown 骨架；实机回填由 /forge §3.7 第二步在授权后执行。
</phase_context>
CRITICAL 方法论锚点
[!IMPORTANT] 指南是「可被 walks 的证明计划」，不是绿勾表演。
- 先看见，再相信：先有读屏预期与可追溯 PRD 锚点，再给动作与可视结果；无界面叙事的连串点击视为不合格步骤。
- 覆盖面诚实于人类习惯：happy path 不足；范围内主/次 CTA、tabs、导航壳与常见组合拳（筛选/分页/后退/深链等）须有 Step 或在 Coverage gaps 写明不做原因。
- 档位稀缺即纪律：评测语义只剩三档 PASS / PARTIAL_PASS / FAIL；禁自拟「通过但…」「基本完成」或其它伪绿灯。
- 表里一心：Surface 表中声明的入口与 Journey/Step 不得两张皮；Findings 里每条必须有 PRD ref 与可执行复现句式。
CRITICAL：spec 契约（评测列 + 可追溯）
允许的 Step / Journey「结果」字面量（仅此三档）
PASS：对应 PRD 行为与 UI 观感在 已授权浏览器实机回填 Evidence 之后可被证据支持。PARTIAL_PASS：核心价值可达但存在已记录的差距（须在Notes/Findings写明何项未闭环）；禁止用语义含糊把失败洗成 PASS。FAIL：未达到 PRD / 验收，或阻断继续（亦可在未修前保持 FAIL 直至修复复测）。
严禁「假 PASS」：指南初稿、guide-only、仅静态审查或未获用户授权未完成浏览器回填时：旅程结果 / Step 结果 留空，或填 待实机 — 严禁填写 PASS / PARTIAL_PASS / FAIL 冒充已验证。捏造 URL、截图、网络结论同上。
PRD traceability（与硬约束等价表述）
任一 RTM、Surface、PRD ref/PRD reference、Journey、Step、Findings 行：须能指回 PRD 锚点 或 任务验收条目（例如 T-x）；无 PRD 时于 Scope 声明「准 PRD」来源。无锚点的步骤不进主表正文，或记入 Coverage gaps 说明为何不测。
与本 skill 配对：宿主工作流 /forge §3.7 — 波末 E2E（触发、收尾 A/B 二选一、wave-{N}-e2e.md 路径、guide-only 边界）以 forge 条文为准；本文件不重复整条 workflow，但不与之冲突。
触发条件
05A_TASKS.md任一任务含 E2E测试 或 手动验证，或05B_VERIFICATION_PLAN.md要求实机验证；或改动影响页面/导航/表单/登录等依赖真机感受的路径。- 用户明确要求「测试指南」「E2E 报告」「浏览器验证清单」等。
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.
- 1mo ago First seen · 247 lines · 106 tokens per session scan A 2fd45c790a94
e2e-testing-guide is a skill published in the GitHub repository Haaaiawd/ANWS (141 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 3,737 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
rails-testing
Ruby on Rails testing conventions — Minitest strategy, fixtures, system tests. Use when writing tests, setting up test data, or running test suites.
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-tester
Agent skill for tester - invoke with $agent-tester.
quinn
Verifies specified behavior through appropriate tests and truthful coverage reports.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.