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 agentmods add skills/xcodethink/open-claude-code-skills/01npx skills add xcodethink/open-claude-code-skills --skill 01git clone --depth 1 https://github.com/xcodethink/open-claude-code-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/xcodethink/open-claude-code-skills/01)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/01"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/01.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 | $0.00242 | $0.02976 |
| Opus 5 | $0.00121 | $0.01488 |
| Sonnet 5 | $0.00048 | $0.00595 |
| Haiku 4.5 | $0.00024 | $0.00298 |
Grade A, and why
01-通用要求 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 3d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
通用开发要求
不要读取本目录所有文件。 先读本文件的内联规则,仅在需要深入了解时才按需读取对应的独立文件。
核心铁律(必须内化,不需要读文件)
代码完整性铁律(最高优先级)
详细版 →「代码完整性铁律.md」
- 文件系统是唯一真相 — 修改前必须读取文件,禁止凭记忆改代码
- 只做增量修改 — 不重写整个文件,只改需要改的行
- diff 确认 — 修改后
git diff确认范围正确 - 任务边界锁定 — 没让你改的代码不要碰,不要"顺便优化"
- 修改前三问 — 用户让我改了吗?是必需的吗?其他功能不变吗?
- 审查结论不等于修改指令 — 代码审查/优化建议必须逐条判断是否合理,不能看到"问题列表"就机械全改。特别是:
- 理解原设计意图:改之前先问"原作者为什么这么写",如果有合理理由就不改
- 确定性输出永久缓存:纯函数结果(TTS、编译产物等)不设 TTL,过期只浪费重算成本
- 改变现有行为必须说明理由:对已上线运行正常的逻辑,修改前必须向用户说明为什么改、改了有什么影响,等确认后再改
- 区分真问题和误判:自动化审查工具/AI 分析报告的每条建议都可能是错的,必须独立思考
一次做到位
详细版 →「一次做到位规范.md」
- 永远做最完整方案,不做最小版本等用户追问
- 宁可多做让用户删,不要少做让用户追
- 页面必须处理 loading / success / empty / error 四种状态
- Bug 修复要全链路分析,不要修一个推一个
产品思维
详细版 →「产品思维和深度分析规范.md」
- 新项目/新功能模块:先做产品分析(竞品→旅程→逐页规格),确认后再写代码
- 每个页面规划到具体模块级别,不是"Dashboard 页面"而是"4 个统计卡 + 趋势图 + 最近活动"
借鉴子文档(mattpocock/skills,MIT,按需读)
详细版 →「深模块设计.md」— 深模块(小接口藏大量行为)/ seam / 删除测试 / 为可测性设计 / Design-It-Twice(设计模块接口、决定 seam 放哪时读) 详细版 →「一次性原型-prototype.md」— 用扔掉的代码答一个设计问题:LOGIC(终端驱动状态机)/ UI(
?variant=多变体);起 dev server 须守 CLAUDE.md 本地进程纪律
开发流程规则(按需读取详细文件)
| # | 规则 | 一句话摘要 | 详细文件 |
|---|---|---|---|
| 1 | 垂直切片开发 | 每个功能 API+前端+交互同时完成,用户立即可体验 | 「垂直切片开发规范.md」 |
| 2 | 开发自验证 | 代码写完 ≠ 完成,必须自测通过 | 「开发自验证规范.md」 |
| 3 | API 健壮性 | 超时 5s、重试 3 次、四种前端状态 | 「API健壮性开发规范.md」 |
| 4 | 技术选型 | 按商业级标准选型,不默认选免费 | 「技术选型规范.md」 |
| 5 | 版本管理 | 语义化版本、CHANGELOG、发布流程 | 「版本和变更管理.md」 |
| 6 | 错误处理 | 用户友好、开发可追踪、系统可恢复 | 「错误处理和日志规范.md」 |
| 7 | AI 质量控制 | prompt 管理、输出校验、幻觉防护 | 「AI输出质量控制.md」 |
| 7b | AI 模型选型 | 按任务选模型、Tier 分级、Fallback 链、成本估算 | 「AI模型选型规范.md」 |
| 8 | 依赖管理 | lock 必提交、禁止重复依赖、安全审计 | 「依赖管理规范.md」 |
| 9 | 回滚应急 | 部署回滚、数据库回滚、事故响应 | 「回滚和应急规范.md」 |
| 10 | 系统监控告警 | 健康检查、Lark 告警、结构化日志、性能埋点、AI 监控 | 「系统监控和告警规范.md」 |
| 11 | 问题修复标准流程 | 11 步工程化修复:记录→调研→设计→审查→计划→确认→开发→验证→回归→部署→文档。禁止跳过分析直接改代码 | ~/.claude/skills/14-问题修复标准流程/(独立技能) |
编码和工程规范(按需读取详细文件)
| # | 规则 | 一句话摘要 | 详细文件 |
|---|---|---|---|
| 10 | 代码规范 | 命名规范、编码规则、API 响应格式 | 「代码规范.md」 |
| 11 | 数据库规范 | cuid 主键、必须时间戳、软删除、缓存策略、禁止内存存储 | 「数据库规范.md」 |
| 12 | 安全规范 | 密钥 .env 管理、API 安全、数据加密 | 「安全规范.md」 |
| 13 | 国际化 | 零硬编码、所有文本走 i18n key | 「国际化规范.md」 |
| 14 | 技术栈白名单 | 公司允许使用的技术栈、框架、基础设施、禁止列表 | 「技术栈白名单.md」 |
| 15 | 生产环境规范 | OAuth 登录、前端 UX、部署验证、历史踩坑 | 「生产环境规范.md」 |
| 16 | 信用点收费系统 | AI 项目积分制收费架构、定价公式、毛利控制、管理后台配置 | 「信用点收费系统规范.md」 |
What ships with it
43 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.
- agents/openai.yaml 882 B
- AI模型选型规范.md 10 KB
- AI输出质量控制.md 6.0 KB
- API健壮性开发规范.md 9.6 KB
- Hooks开发规范.md 9.3 KB
- Plan Mode工作流.md 6.7 KB
- SKILL.en.md 12 KB
- task-template.md 1.3 KB
- 一次做到位规范.md 7.1 KB
- 一次性原型-prototype.md 3.7 KB
- 上下文管理.md 5.5 KB
- 产品思维和深度分析规范.md 12 KB
- 代码完整性铁律.md 4.9 KB
- 代码规范.md 8.6 KB
- 代码迁移和重写规范.md 10 KB
- 依赖管理规范.md 3.8 KB
- 信用点收费系统规范.md 8.3 KB
- 商业级项目自检规范.md 7.0 KB
- 回滚和应急规范.md 4.9 KB
- 国际化规范.md 2.4 KB
- 垂直切片开发规范.md 3.9 KB
- 安全规范.md 3.3 KB
- 开发自验证规范.md 7.7 KB
- 技术栈白名单.md 3.1 KB
- 技术选型规范.md 4.9 KB
- 数据库规范.md 9.1 KB
- 架构模式.md 6.1 KB
- 深模块设计.md 5.0 KB
- 版本和变更管理.md 4.5 KB
- 生产环境规范.md 2.8 KB
- 系统监控和告警规范.md 12 KB
- 经验积累规范.md 4.8 KB
- 踩坑记录/browser-compat.md 4.5 KB
- 踩坑记录/css-layout.md 2.9 KB
- 踩坑记录/database-migration.md 4.5 KB
- 踩坑记录/dev-workflow.md 11 KB
- 踩坑记录/docker-monorepo-deployment.md 4.6 KB
- 踩坑记录/framework.md 4.2 KB
- 踩坑记录/performance.md 2.4 KB
- 部署纪律铁律.md 3.2 KB
- 错误处理和日志规范.md 7.9 KB
- 项目专属文档规范.md 8.9 KB
- 项目合规审查.md 5.6 KB
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.
- 3d ago First seen · 181 lines · 242 tokens per session scan A 7764e448d661
01-通用要求 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 28d ago), licensed MIT. It adds 242 tokens to every session and 2,976 once invoked, about $0.0012 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
android-finance-spec
Use when generating, reviewing, or refactoring Android Kotlin code for financial apps that require BigDecimal/String precision, RTL/i18n safety, Kotlin style discipline, and "do not reinvent existing project patterns" constraints.
elite-engineer
The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
JavaScript Tooling
Development tools, linting, and testing for JavaScript projects.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。.
alipay-webhooks
Receive and verify Alipay (Antom / Alipay+) webhook notifications. Use when setting up Alipay webhook handlers, debugging RSA256 Signature header verification, or handling payment events like notifyPayment, notifyCapture, notifyRefund, notifyAuthorization, and notifyDispute.