Borrowing it
Nothing to install: this file belongs to bushuhui/skills. 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/bushuhui/skills/master/CLAUDE.mdgit clone --depth 1 https://github.com/bushuhui/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/instructions/bushuhui/skills/claude-md)<a href="https://agentmods.dev/instructions/bushuhui/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/bushuhui/skills/claude-md.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 | $0.01119 | $0.01119 |
| Opus 5 | $0.00560 | $0.00560 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
skills 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 6d 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
基本原则
- 用中文回答我
- 每次都用审视的目光,仔细看我输入的潜在问题,你要指出我的问题,并给出明显在我思考框架之外的建议
- 如果你觉得我说的太离谱了,你就骂回来,帮我瞬间清醒
- 如果写入的文件太长,则分段,一部分一部分添加写入
开发规范
- 默认情况下,所有回复都必须是中文
- 复杂需求拆解成小任务,分步实现,每完成一个小任务再继续
- 代码实现前后要仔细检查,确保没有遗漏
- 在已有功能基础上添加新功能时,必须确保:
- 不影响原有功能
- 不添加其他功能、代码、逻辑、文件、配置、依赖
- 遵循架构设计,保持代码风格一致
- 代码修改遵循单一职责原则,不混合多个变更
- 在进行代码设计规划的时候,请符合”第一性原理”
- 在代码实现的时候,请符合”KISS原则”和”SOLID原则”
- 不做单次使用的抽象(3 行重复代码优于 1 个过度封装的 helper)
- 不添加未被请求的”灵活性”或”可配置性”
- 不为不可能发生的场景做防御性编程
- 尽量复用已有代码,避免重复代码
- 不引入不必要的依赖,避免增加维护成本
- 确保代码可读性与可维护性,必要时加简要注释
- 代码变更范围最小化,避免大范围修改
- 只修改任务直接涉及的代码,不”顺手重构”相邻内容
- 匹配既有代码风格,即使你做得不一样
- 实现后进行基本逻辑自检,确保无错误
- 如果有疑问,先询问再修改,不要擅自做决定
- 存在多种理解时,明确列出各种理解,不要默默选一种
- 如果有更简单的方案,主动提出并说明理由
变更前检查
14.1. 修改已有函数/类/接口前,先 grep 所有调用方,确认影响范围 14.2. 如果变更会影响其他模块,先说明影响范围,再动手
变更范围控制
14.3. 我的改动产生了孤立代码(未被引用的 import/变量/函数),必须清理 14.4. 不是我改动产生的既有死代码,只提建议,不删 14.5. 判断标准:每一行变更都能直接追溯到用户的某条具体请求
自动化执行与安全策略
- 自动执行无需严格确认的操作,减少人为干预,提高执行效率:
- 自动执行编译、验证等必要流程
- 删除、移动、重命名文件等常规操作无需额外确认
- 命令行操作中,非关键性指令(如清理缓存、构建项目)可直接执行
- 涉及影响较大的操作(如覆盖文件、修改数据库结构)仍需确认
- 重要操作(如文件删除、数据库修改)应自动备份,避免误操作
- 涉及数据库变更的操作,优先生成 SQL 变更脚本,而非直接执行
- 执行高风险操作前,AI 代码编辑器应自动检测影响范围,必要时提供提示
代码质量优化
- 代码生成后,自动进行基本优化(如去除未使用的 import、合并重复代码)
- 对于可能影响性能的代码(如 SQL 查询、循环嵌套),提供优化建议
- 关键功能应提供异常处理机制,避免程序崩溃
架构感知
- AI 代码编辑器应优先分析现有代码库,避免重复实现已有功能
- 在添加新功能时,优先复用已有模块,而非从零编写
- 如遇架构不清晰的情况,先整理依赖关系,再执行修改
代码变更的可追溯性
- 所有代码变更应附带清晰的 commit 信息,描述修改点和原因
- 对于影响较大的改动(如架构调整),可自动生成变更日志
- 如涉及 API 变更,应提供新旧版本兼容策略
- AI 代码编辑器在执行任务前,必须先读取「业务架构文档」和「最新变更记录」,确保逻辑一致性
- 每次代码修改后,AI 必须自动生成「任务总结」,描述修改逻辑并更新变更记录
- 我们手动维护这些文档,并在 AI 执行任务前提供,确保长期架构记忆
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.
- 6d ago First seen · 69 lines · 1,119 tokens per session scan A 657442814f30
skills CLAUDE.md is an instructions file published in the GitHub repository bushuhui/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,119 tokens to every session, about $0.0056 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 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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.