Borrowing it
Nothing to install: this file belongs to Hehejie1/NoteMeld. 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/Hehejie1/NoteMeld/main/CLAUDE.mdgit clone --depth 1 https://github.com/Hehejie1/NoteMeldWrote 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/hehejie1/notemeld/claude-md)<a href="https://agentmods.dev/instructions/hehejie1/notemeld/claude-md"><img src="https://agentmods.dev/badge/instructions/hehejie1/notemeld/claude-md/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/instructions/hehejie1/notemeld/claude-md"><img src="https://agentmods.dev/badge/instructions/hehejie1/notemeld/claude-md.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 | $0.00910 | $0.00910 |
| Opus 5.5 | $0.00364 | $0.00364 |
| Sonnet 5.5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
NoteMeld 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 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.
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
CLAUDE.md
LLM 行为准则，减少常见编码错误。
0. 产品范式
NoteMeld 的核心范式是：AI 编译知识，人验证和消费。对外定位是"你的 AI 研究助手"——后台运行，标记驱动，随时提供参考和来源。对内架构隐喻是"知识编译器"——Wiki-First Retrieval，管线思维，增量重建。所有代码改动应服务这个范式：AI 负责下载、转写、理解、抽取、构建图谱；人负责标记来源、验证结果、消费知识。详细战略调研见 docs/research/knowledge-compiler-paradigm.md。
1. 先思考再编码
不假设。不隐藏困惑。暴露权衡。
实现前：
- 明确陈述假设。不确定就问。
- 如有多种解读，都列出来——不要默默选一个。
- 如有更简单的方法，说出来。必要时拒绝需求。
- 如果不清楚，停下来。指出困惑点。问。
- 开始任何改动前，先读
docs/system/下的系统文档和AGENTS.md。
2. 简洁优先
解决问题的代码越少越好。不想象未来需求。
- 不写未明确要求的功能。
- 不抽象单次使用的代码。
- 不写未被要求的"灵活性"或"可配置性"。
- 不处理不可能发生的错误场景。
- 如果写了 200 行但 50 行就够了，重写。
- 遵循最小改动原则，优先复用现有模块和 helper。
自问："有经验的工程师会觉得这过度设计吗？" 如果是，简化。
3. 手术式修改
只改必须改的。只清理自己造成的。
编辑已有代码时：
- 不"改进"相邻代码、注释或格式。
- 不重构没坏的东西。
- 匹配现有风格，即使你更喜欢另一种做法。
- 如果注意到无关的死代码，提出来——但不删除。
- 不能破坏源码启动、CLI、桌面、MCP、迁移、Wiki、上传、打包发布任一既有入口。
当你的改动造成孤立代码时：
- 删除被你改动后不再使用的导入、变量、函数。
- 不删除原本就存在的死代码，除非被明确要求。
测试：每一行改动的代码都应该能追溯到用户的需求。
4. 目标驱动执行
定义成功标准。循环直到验证通过。
把任务转化为可验证目标：
- "加校验" → "为无效输入写测试，让测试通过"
- "修 Bug" → "先写复现测试，再修复并验证"
- "重构 X" → "确保测试在重构前后都通过"
多步骤任务，先给出简要计划：
1. <步骤> → 验证：<检查点>
2. <步骤> → 验证：<检查点>
3. <步骤> → 验证：<检查点>
好的成功标准能独立循环验证。差的标准（"让它能用"）需要不断追问。
5. 文档同步
改动以下内容时必须同步更新 docs/system/：
- 系统架构、运行入口、部署方式
- 产品硬规则或 UX 行为
- SQLite 表、字段、文件结构、状态流转
- API 路径、请求参数、返回结构
- MCP 工具
- Wiki rebuild、任务状态、桌面 sidecar、迁移等核心链路
- 新发现的坑点和回归防线
这些准则有效衡量标准： diff 中无关改动减少，不会因过度设计而重写，澄清问题出现在实现之前而不是错误之后。
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 Changed · +4 lines · +144 tokens per session 608dc26ab0d6
- 2mo ago First seen · 78 lines · 766 tokens per session scan A c33b0589a34e
NoteMeld CLAUDE.md is an instructions file published in the GitHub repository Hehejie1/NoteMeld (8 stars, last pushed 27d ago), licensed MIT. It adds 910 tokens to every session, about $0.0036 per session on Opus 5.5. 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.
NoteMeld CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| NoteMeld CLAUDE.mdHehejie1/NoteMeld | Instructions file | 8 | 27d ago | MIT | A | 910 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |