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/weibaohui/ntd/claude-mdgit clone --depth 1 https://github.com/weibaohui/ntdWrote 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/weibaohui/ntd/claude-md)<a href="https://agentmods.dev/instructions/weibaohui/ntd/claude-md"><img src="https://agentmods.dev/badge/instructions/weibaohui/ntd/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 | $0.05324 | $0.05324 |
| Opus 5 | $0.02662 | $0.02662 |
| Sonnet 5 | $0.01065 | $0.01065 |
| Haiku 4.5 | $0.00532 | $0.00532 |
Grade A, and why
ntd 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
本文件是 ntd 项目的 AI 权威行为守则。所有 AI 工具（Claude Code、AtomCode、Copilot 等）在操作本仓库时必须遵守。
引用规范
本项目的开发规范分布在以下文件中，AI 在开始任何工作前必须先读取：
| 文件 | 说明 | 优先级 |
|---|---|---|
AGENTS.md |
多工具入口守则 & 指向 CLAUDE.md | 路由入口 |
docs/开发规范/AI协作开发约定.md |
AI 完整协作流程（写前确认、先写文档、编码约定、测试、缺陷处理） | 强制遵守 |
docs/开发规范/后端规范/ |
Rust 后端分层/Handler/Service/Model/测试/禁止清单 | 后端操作必读 |
docs/开发规范/前端规范/ |
React 前端组件/API/类型/样式/测试/禁止清单 | 前端操作必读 |
docs/文档编写规范/ |
文档读写存放规则、需求规范、Bug 规范 | 创建文档时必读 |
docs/README.md |
文档目录索引与命名规范 | 创建文档时参考 |
读取顺序：
AGENTS.md→CLAUDE.md→ 对应技术栈规范（后端/前端）→ 文档编写规范（如需创建文档）。
项目概述
ntd (Now Task, Done) 是一个 AI 驱动的任务引擎，基于 Rust 后端 + React 前端，支持 Claude Code 等执行器。
开发流程
禁止直接在主分支 (main) 上写代码。所有代码改动必须先创建分支，在分支上完成开发后再通过 PR 合入 main。
AI 工作流程（参考 docs/开发规范/AI协作开发约定.md 的完整版本）
当接到新任务时，AI 应按以下步骤开展工作：
- 读取规范 — 读取 AGENTS.md、CLAUDE.md、对应技术栈规范
- 需求澄清 — 如果需求简短模糊，先分析相关代码现状，再用结构化选择题（ABCD 选项）向用户提问，要求回复
1a2b3c格式，把需求说明白再继续 - 确认方案 — 向人类说明设计方案，获确认后再编码
- 编写文档 — 先在
docs/design/创建设计文档，如涉及新功能需有对应需求文档 - 编写代码 — 遵循注释、函数长度、测试、零告警等规范
- 编译+测试 —
cargo clippy -- -D warnings+cargo test - 安全反思 — 检查逻辑漏洞、越权风险、输入校验
- 功能总结 — 在
docs/requirements/创建实现总结文档 - 提交 PR — 创建 PR 并说明与需求的对应关系
详细流程请阅读
docs/开发规范/AI协作开发约定.md。
AI 思考与输出规范
强制要求：AI 必须对问题充分思考，但不得在回复中输出思考过程（自言自语）。
- 充分思考：在动手前，对需求、设计、边界条件、风险进行完整推理，确保结论正确、方案周全、不遗漏关键点。
- 仅在脑中思考：所有推理、权衡、试错、草稿都在内部完成，不要以文字形式打印到回复里（即不要把"自言自语"输出给用户）。
- 只输出结论：回复中仅呈现经过思考后的最终结论、方案或答案，保持简洁、直接、可执行。
- 例外：仅当用户明确要求"展示思考过程"，或需要向用户解释推导依据时，才输出推理链路。
工程设计原则
强制要求：以下原则适用于所有设计与编码决策。
- 不做向后兼容：删除过时的路径，而不是添加兼容性层、回退或迁移逻辑。
- 最简单实现：选择完全满足当前要求的最简单实现，避免投机性抽象、过度配置和间接层。
- 分层生长：从端到端可工作的最小版本开始，每个新功能都叠加在已经工作的产品之上；永远不用"已工作的产品"去换"未完成的复杂性"。
- 模块化分离：保持组件模块化、职责边界明确分离。
- 首选成熟库：当库能降低整体复杂性或提高可靠性时，优先选用已建立、维护良好的库；没有明确理由，不重新实现通用功能。
- 先用已有依赖：编写自研实现或引入新软件包之前，先依靠项目中已有的依赖；未查阅其文档和类型之前，不得假设某个库缺少所需功能。
- 长期架构决策：不接受"暂时有效、打算以后再换"的临时方案。
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 · 346 lines · 5,324 tokens per session scan A c1118b40de22
ntd CLAUDE.md is an instructions file published in the GitHub repository weibaohui/ntd (11 stars, last pushed 7d ago), licensed MIT. It adds 5,324 tokens to every session, about $0.0266 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 2026-08-30.
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.