Borrowing it
Nothing to install: this file belongs to 569270901/claude-web-test-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/569270901/claude-web-test-harness/main/CLAUDE.mdgit clone --depth 1 https://github.com/569270901/claude-web-test-harnessWrote 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/instructions/569270901/claude-web-test-harness/claude-md)<a href="https://agentmods.dev/instructions/569270901/claude-web-test-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/569270901/claude-web-test-harness/claude-md/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/instructions/569270901/claude-web-test-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/569270901/claude-web-test-harness/claude-md.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 | $0.00722 | $0.00722 |
| Opus 5 | $0.00361 | $0.00361 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
claude-web-test-harness CLAUDE.md 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 10d 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.
What it actually says
项目指南（接入方在此声明自己的约定）
这是多 agent UI 测试 harness 的项目约定文件。agent 读它来自适应你的项目， 没有硬编码业务路径。接入你自己的项目时，改下面「项目约定」一节即可。 demo 默认值面向 TesterHome（只读流程）。
必读文件
每次写代码 / 写测试 / 补页面地图前，先读：
rule.md— 编码规则与技术避坑（selector 写法、等待时机、组件行为）artifacts/README.md— 多 agent 编排总览（artifact schema、gate、红线、progress.log）- 相关的
page_map/*.yaml— 当前页面元素地图
发现新知识主动回写：技术坑 → rule.md；页面元素变化 → 对应 page_map/*.yaml。
项目约定（← 接入时改这里）
| 约定 | 本项目取值 |
|---|---|
| 站点基础 URL | https://testerhome.com（见 pytest.ini 的 --base-url） |
| 页面地图目录 | page_map/（按 page_map/<模块>/<页面>.yaml 组织） |
| 测试数据目录 | data/（YAML） |
| 测试代码目录 | tests/（不嵌套模块子目录） |
| 测试运行命令 | python -m pytest tests/ -v |
| 登录逻辑 | demo 全部只读，无需登录；接入时在 conftest.py 加登录 fixture |
| 失败 DOM 落盘目录 | data/debug/（调试用，已 gitignore） |
开发原则
- 所有字段都填（包括非必填）、都断言
- 绝不删断言来让测试通过——失败就是 bug
expected避免用"0"，用有语义的值- 注释用中文
- selector 优先 ID / role / 稳定属性，禁用 hash class /
:nth-child/ xpath 位置索引（详见rule.md）
测试命令
# 全部测试
python -m pytest tests/ -v
# 单个文件 / 单个用例
python -m pytest tests/test_home.py -v
python -m pytest tests/test_home.py::test_home_title -v
# 看得见浏览器（调试）
python -m pytest tests/ -v --headed
demo 任务（验证 harness 跑通）
在本目录打开 Claude Code，对主对话说：
「为 TesterHome 首页 + 搜索设计一套只读测试并写出来」
主对话（orchestrator）会按需派发：
page-map-sync → test-case-design(阶段1解构→decomp.md，你审 GATE 0) → test-case-design(阶段2生成→cases.md+flow.md，你审 GATE 1) → test-writing → review。
只做只读流程（浏览话题列表、打开帖子详情、搜索关键词、断言渲染），不要自动化注册/登录/发帖。
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.
- 10d ago First seen · 68 lines · 722 tokens per session scan A 1857960967d6
claude-web-test-harness CLAUDE.md is an instructions file published in the GitHub repository 569270901/claude-web-test-harness (38 stars, last pushed 22d ago), licensed MIT. It adds 722 tokens to every session, about $0.0036 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.