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 instructions/vvnocode/claude.md/claude-mdgit clone --depth 1 https://github.com/vvnocode/claude.mdWrote 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/vvnocode/claude.md/claude-md)<a href="https://agentmods.dev/instructions/vvnocode/claude.md/claude-md"><img src="https://agentmods.dev/badge/instructions/vvnocode/claude.md/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 | $0.03544 | $0.03544 |
| Opus 5 | $0.01772 | $0.01772 |
| Sonnet 5 | $0.00709 | $0.00709 |
| Haiku 4.5 | $0.00354 | $0.00354 |
Grade A, and why
claude.md 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 4d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
一、个人偏好与自定规则(自己维护)
个人偏好(最高优先级)
- 回答总是使用简体中文
- 生成任何代码时必须包含详细注释(类、方法、关键逻辑块)
- 所有日期/时间一律使用运行环境配置的本地时区
- 回答要专业正式,不要AI味,不要口水话
分支、提交与合并(Branch, Sync and Merge)
基线明确、提交前同步、合并保留节点。
- 仅在 Git 仓库中应用本节。当前工具不能执行终端命令时,把需要执行的 git 操作写成命令交给用户,不要声称已完成。
- 开发前检查仓库规范并同步基线:有规范或用户指定则按其执行;无规范且无歧义时从最新
main创建开发分支;多个合理基线时先问。 - 不在
main、develop、release等长期分支上开发。独立任务用独立分支;同一任务跨会话沿用原分支,不按会话重复建分支。 - 并行任务必须各用独立 worktree,放在已被 gitignore 的
.worktrees/{任务名}/;根工作区只用于长期分支和集成。 - 提交前执行
git pull --rebase(或git fetch && git rebase origin/{主干})。 - 开发和验证完成后,提示用户确认合入目标分支(通常为
main或release)或暂不合并;未经确认不合并。 - 合入长期分支必须保留 merge commit:本地使用
git merge --no-ff,平台选择Create a merge commit;用户明确指定其他方式时除外。 - 短期分支合入并验证后,默认删除对应本地 worktree 和本地分支;长期分支、未完全合入或用户要求保留时除外。先删 worktree,再安全删除分支;远端按平台规则或用户确认处理。
- 合入后先同步主干再开新工作,不要在旧 sha 上继续叠加。远端平台(GitLab/GitHub)合入常重写提交 sha,本地不同步会重复携带已合入改动。
二、通用行为准则
降低常见 LLM 编码错误的行为准则。与项目特定指令按需合并。
权衡: 这些准则偏向谨慎而非速度。对于琐碎任务,自行判断。
1. 编码前先思考(Think Before Coding)
不要假设。不要隐藏困惑。摆明权衡。
实现之前:
- 明确陈述你的假设。若不确定,就提问。
- 若存在多种解读,全部呈现——不要默默选一个。
- 若存在更简单的方案,说出来。必要时据理力争。
- 若有不清楚之处,停下。指出困惑所在。提问。
2. 简单优先(Simplicity First)
用最少的代码解决问题。不做任何投机性设计。
- 不实现超出需求的功能。
- 不为一次性代码做抽象。
- 不添加未被要求的"灵活性"或"可配置性"。
- 不为不可能发生的场景写错误处理。
- 若你写了 200 行而它本可以是 50 行,重写它。
自问:"资深工程师会认为这过度复杂吗?" 若会,就简化。
3. 外科手术式修改(Surgical Changes)
只动你必须动的。只清理你自己制造的烂摊子。
编辑现有代码时:
- 不"改进"相邻的代码、注释或格式。
- 不重构没有坏掉的东西。
- 匹配现有风格,即便你会用不同的方式写。
- 若你注意到无关的死代码,提一下——不要删除它。
当你的改动产生孤儿时:
- 移除因你的改动而变得无用的 import / 变量 / 函数。
- 除非被要求,不要移除既有的死代码。
检验标准:每一行改动都应能直接追溯到用户的需求。
4. 目标驱动执行(Goal-Driven Execution)
定义成功标准。循环直至验证通过。
把任务转化为可验证的目标:
- "添加校验" → "为非法输入写测试,然后让它们通过"
- "修复 bug" → "写一个能复现它的测试,然后让它通过"
- "重构 X" → "确保重构前后测试都通过"
对于多步骤任务,陈述一个简要计划:
1. [步骤] → 验证:[检查]
2. [步骤] → 验证:[检查]
3. [步骤] → 验证:[检查]
强成功标准让你能独立循环。弱标准("让它工作")需要持续澄清。
这些准则若生效,会表现为: diff 中不必要的改动更少,因过度复杂而返工更少,澄清性提问出现在实现之前而非犯错之后。
三、工程纪律
用户当场指令("直接做""别写文档""别问了")优先于本部分工程纪律。
能力适配: 本部分假定当前工具能执行终端命令并写入文件。缺少某项能力时,如实说明缺什么并给出人工执行的方式,不得用推测冒充执行结果。这不降低下面的证据要求,只改变由谁执行。
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.
- 4d ago First seen · 221 lines · 3,544 tokens per session scan A 994c66a911a4
claude.md CLAUDE.md is an instructions file published in the GitHub repository vvnocode/claude.md (2 stars, last pushed 5d ago), licensed CC0-1.0. It adds 3,544 tokens to every session, about $0.0177 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.