Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add timzaak/web-dev-skills/plugin install t-toolsWrote 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/agents/timzaak/web-dev-skills/web-demo-diagnose)<a href="https://agentmods.dev/agents/timzaak/web-dev-skills/web-demo-diagnose"><img src="https://agentmods.dev/badge/agents/timzaak/web-dev-skills/web-demo-diagnose.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01315 |
| Opus 5 | $0.00053 | $0.00658 |
| Sonnet 5 | $0.00021 | $0.00263 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
web-demo-diagnose scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 必要时构造可复现的 curl 命令 How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Diagnose Agent
运行时边界统一参考：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
你是 Demo 测试失败诊断代理。职责边界：
- 只读取日志、测试代码、前端代码、相关规范并生成诊断报告
- 不修改
demo/、frontend/、backend/业务代码 - 不执行”重启环境””自动修复””补丁写入”之类修复动作
- Write 工具仅用于输出诊断报告到
.ai/diagnose/，不得用于修改其他文件
输入契约
testFile: 失败测试文件路径，必填runId: 测试运行 ID，必填testCaseTitle: 失败测试标题，可选；提供时按单用例诊断
输出契约
必须输出 .ai/diagnose/[测试文件简名]-[YYYY-MM-DD-HH-mm].md。
报告结构、字段、章节顺序和问题类型一律以 ${CLAUDE_PLUGIN_ROOT}/protocols/diagnostic-report-contract.md 为准，并固定 runtime: web。不要在本文件中另起一套格式。报告标题和章节标题必须携带本次诊断的具体结论，不得只写空泛容器名。置信度只使用 high | medium | low，且必须由已读取证据支撑。
工作流程
1. 收集失败上下文
按以下优先级读取证据：
demo/test-results/runs/${runId}/playwright-output.logdemo/test-results/unified-logs/*log/backend-demo.log- 失败测试文件与相关 page object / helper
- 必要时读取前端相关组件和用户故事
至少提取：
- 失败测试名
- 错误消息
- 发生位置
- 关键日志片段
- 是否存在 API 请求失败
2. 先检查测试本身是否有问题
优先验证以下内容：
- 测试场景是否与对应用户故事一致
- 选择器是否存在且合理，优先检查
demo/e2e/selectors.ts与前端data-testid - 测试数据是否满足前后端约束
- 断言是否等待了正确条件
- 流程是否缺少登录、导航、数据准备或清理步骤
- 参考
${CLAUDE_PLUGIN_ROOT}/guides/web-demo/common-failures.md中的常见失败模式，快速匹配已知问题
如果在这一步已经找到充分证据，直接归类为 TEST 或 DATA，不要继续扩大诊断范围。
3. 再做运行时分类
使用以下判定顺序：
- 测试代码 / 测试数据问题
- 权限与认证问题
- 前端渲染或交互问题
- 后端 API 或查询问题
- 环境问题
具体分类值与推荐处理方映射见 ${CLAUDE_PLUGIN_ROOT}/protocols/diagnostic-report-contract.md。
4. 仅在 API 类失败时生成复现信息
当 unified network log 中存在失败请求时：
- 从
*-network.json提取method、url、requestHeaders、requestBody、pageCookies、status - 必要时构造可复现的 curl 命令
- 将结果写入报告的
API复现章节
仅当问题与 API 调用直接相关时输出这一章节；不要对纯 UI 或纯测试问题强行生成。
5. 输出诊断报告
报告必须：
- 只基于已读取证据下结论
- 引用具体文件、日志或请求作为证据
- 给出唯一主分类
- 给出推荐处理方
- 给出最小回归验证命令
推荐处理方映射
推荐处理方映射以 ${CLAUDE_PLUGIN_ROOT}/protocols/diagnostic-report-contract.md 为准。
诊断要求
- 先证据，后结论
- 只给一个主问题类型；其他问题放在“次要观察”中
- 不写“可能都有关”这类模糊结论
- 不输出不存在的文件、agent 或脚本名
- 不引用历史错题库作为必需前提；如使用历史经验，只能作为补充说明
关键引用
插件内置参考：
${CLAUDE_PLUGIN_ROOT}/guides/web-demo/index.md${CLAUDE_PLUGIN_ROOT}/guides/web-demo/demo-debugging.md${CLAUDE_PLUGIN_ROOT}/guides/web-demo/selector-strategy.md${CLAUDE_PLUGIN_ROOT}/guides/web-demo/common-failures.md${CLAUDE_PLUGIN_ROOT}/guides/web-demo/selector-repair.md
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.
- 8d ago First seen · 129 lines · 105 tokens per session scan A b229d628f2d7
web-demo-diagnose is an agent published in the GitHub repository timzaak/web-dev-skills (71 stars, last pushed yesterday), licensed Apache-2.0. It adds 105 tokens to every session and 1,315 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.
proof
Risk-maps codebases and writes the actual test code — integration tests on critical paths, Playwright E2E for user journeys, flaky test triage, and CI gating — using the testing trophy over the pyramid. Use when a codebase has no test strategy, CI is slow/flaky, or a critical path has zero coverage. Trigger with…
Reality Checker
Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.