Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsnpx agentmods add skills/xcodethink/open-claude-code-skills/13Wrote 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/xcodethink/open-claude-code-skills/13)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/13"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/13/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/xcodethink/open-claude-code-skills/13"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/13.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 | $0.00269 | $0.04126 |
| Opus 5.5 | $0.00108 | $0.01650 |
| Sonnet 5.5 | $0.00054 | $0.00825 |
| Haiku 4.5 | $0.00027 | $0.00413 |
Grade A, and why
13-系统体检和审计 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **2** | 每项必须贴证据 | 没有命令输出/curl/SQL/文件:行号证据的 PASS 视为未执行 | How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
系统体检和审计
核心目标：确保系统在真实用户手中能完整、流畅、安全地完成所有核心操作，产生真实收入。
功能开发一大堆但用户无法正常使用 = 零价值。这个技能专治"功能堆砌但不闭环"。
审计心法（对抗式 — 防"过早闭环"，最高优先）
实战教训：AI 反复宣布"做完了 / 没问题 / 可以收尾了"，但人换一个角度一问，又能挖出真 bug、 真质量提升（退款级 AI bug、catalog 级数据重复、性能 2x、监控盲点…）。根因 = 过早闭环： 覆盖了显而易见的维度（功能对不对、有没有报错）就宣布完成，没系统轮换到正交维度。
1. "完成"是待证伪的假设，不是结论。 听到/想说"OK 了 / 没问题了"→ 立刻反问"我从哪个维度还没看过？"。默认立场是"我还没找到问题"， 不是"没有问题"。这是本 skill 一切原则之上的元立场。
2. 换镜头穷举，不靠灵感。 6 大模块 + 下列正交镜头逐个过；一个镜头干净 ≠ 全部干净。常被"过早闭环"漏掉的镜头： 性能（测真延迟 + 比可选方案，别假设当前最优）/ 运维盲点（X 挂了谁告警？定时任务真在跑？）/ 资源增长（什么表/队列会无限膨胀，有保留期吗）/ 跨引用影响面（删改某资源谁按 id 引用它）/ 配置漂移（主/兄弟/各环境是否一致）/ 成本滥用（贵端点能被刷爆账单吗）。
3. 双向怀疑 — 连"审计输出本身"都要核验。（多 agent 时代关键，易被忽略） 既证伪"它坏了"（驳回 agent/Vision/自己的疑虑假阳性——无可复现真实证据不上报）， 也证伪"它没事"（驳回过早全清）。派出去的审计 agent 的发现，也必须用难伪造通道逐条复核， 不能盲信去改——否则就是"为非问题瞎改"（实战：审计 agent 把有可见文字的按钮误报成"缺 aria-label"，盲信会平白加一堆无用属性）。
4. loop-until-dry。 持续轮换镜头，直到连续 2 个镜头无新发现才可说"这一轮到头了"——且只能说"这些镜头我过完了、 当前干净"，禁止说"无任何可打磨/绝对没问题"（永远还有真人才能验的音质/手感、真实用户反馈、 未穷举的边缘 case）。
落地工具：agents/adversarial-auditor.md —— 只读对抗式审计员，
丢个目标（板块/系统/PR）自动按镜头轮换 + 难伪造核验 + loop-until-dry，产出"逐镜头结论 + 真问题 +
假阳性驳回 + 诚实边界"。subagent_type: adversarial-auditor 调用。
与下方"防跳过铁律 / 体检原则"的关系：那些是执行手段（贴证据、不自欺、Not In Scope…）， 本节是元心法（防过早闭环 + 双向怀疑）——心法管"何时敢说完成"，手段管"每一步怎么做扎实"。
触发场景
| 场景 | 执行范围 | 预计耗时 |
|---|---|---|
| 版本发布前 | 全量体检 (6 模块全跑) | 2-4 小时 |
| 功能更新后 | 更新后回归验证 + 相关闭环 | 30-60 分钟 |
| 定期巡检 (月度) | 全量体检 | 2-4 小时 |
| 用户报 bug | 真人路径测试 (定向) | 15-30 分钟 |
| 安全事件后 | 安全深度审计 | 1-2 小时 |
| 上线收费功能前 | 商业闭环审计 | 1-2 小时 |
六大模块
按需读取对应文档，不要一次全读：
| # | 模块 | 解决什么问题 | 文档 |
|---|---|---|---|
| 1 | 全链路体检清单 | 工程基线是否健康：typecheck、test、build、API 合约、数据一致性、部署完整性 | 全链路体检清单.md |
| 2 | 真人路径测试 | 真实用户能不能完成核心操作：注册、扫描、查看报告、付费、使用付费功能 | 真人路径测试.md |
| 3 | 商业闭环审计 | 收入链路是否通畅：注册→激活→付费→权益生效→续费→退款，每一步都不能断 | 商业闭环审计.md |
| 4 | 安全深度审计 | 是否有可被利用的漏洞：认证绕过、权限越界、注入、数据泄露、业务逻辑漏洞 | 安全深度审计.md |
| 5 | 更新后回归验证 | 新改动是否破坏了已有功能：变更影响分析 + 核心路径回归 + 性能基线对比 | 更新后回归验证.md |
| 6 | 体检报告模板 | 标准化输出，可追踪、可对比、可归档 | 体检报告模板.md |
| 7 | 问题修复标准流程 | 审计发现问题后的 11 步工程化修复流程：记录→调研→设计→审查→计划→确认→开发→验证→回归→部署→文档 | ~/.claude/skills/14-问题修复标准流程/（独立技能） |
What ships with it
10 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.
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 · 231 lines · 269 tokens per session scan A 568e3ef2442c
13-系统体检和审计 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 269 tokens to every session and 4,126 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
browser-automation
Playwright browser automation via MCP. Covers E2E testing, UI review, web scraping, screenshot capture, and general browser interaction. MCP-first — CLI is fallback only.
mobile-testing
Mobile E2E testing patterns — Flutter integrationtest, Patrol, Maestro, golden testing, device matrix, and test data management. Use when writing E2E tests for mobile applications.
test-e2e
Plans, authors, and executes end-to-end tests for mobile and web platforms. User-invoked entry point via /test-e2e; not for autonomous or subagent use.
test-integration
Audits I/O adapters, sets up test infrastructure, and systematically improves integration test coverage. User-invoked entry point via /test-integration; not for autonomous or subagent use.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.