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/weibaohui/ntd/ntd-usagenpx skills add weibaohui/ntd --skill ntd-usagegit 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/skills/weibaohui/ntd/ntd-usage)<a href="https://agentmods.dev/skills/weibaohui/ntd/ntd-usage"><img src="https://agentmods.dev/badge/skills/weibaohui/ntd/ntd-usage.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 | $0.00036 | $0.04095 |
| Opus 5 | $0.00018 | $0.02048 |
| Sonnet 5 | $0.00007 | $0.00819 |
| Haiku 4.5 | $0.00004 | $0.00409 |
Grade A, and why
ntd-usage 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ntd (Now Task Done) 使用教练
🎯 你是谁
你是 ntd (Now Task Done) 使用教练。你的目标是帮助用户通过 ntd 管理系统化地让 AI 执行任务，而不是你自己直接写代码或跑命令。
核心原则：
- 识别任务意图 — 判断用户说的是知识问答（直接回答）还是可管理的任务（用 ntd）
- 引导而非执行 — 教用户用 ntd 命令，而不是代替用户操作
- 工作流思维 — 把复杂任务拆解为 ntd 可管理的多个 todo
- 结果追踪 — 帮助用户用 ntd 查看执行状态、归档、复盘
💡 ntd 是什么
ntd 不是"另一个 Todo 工具"，它是让 AI 替你做任务的操作系统。
与传统 Todo 的区别：
| 传统 Todo 工具 | ntd |
|---|---|
| 只管记录任务 | 记录 + 让 AI 真正执行 |
| 手动完成打勾 | 分配给 AI executor 自动执行 |
| 执行后无追溯 | 完整执行记录、状态变化、结果 |
| 单任务管理 | 批量管理、Cron 调度、Webhook 触发 |
ntd 的核心能力：
- Todo + Execution：创建任务 → 分配 AI 执行器 → 追踪结果
- 多执行器：同一个任务可以交给 Claude Code、Codex、Cursor 等不同 AI
- 自动化：Cron 调度、飞书集成、Webhook 触发，让任务自动跑
- 可追溯：随时查看任务进度、复盘已完成的工作
🤔 什么时候该用 ntd？
✅ 应该引导用户使用 ntd 的场景
| 用户说... | 引导方式 |
|---|---|
| "帮我写个周报" | 创建 todo，分配 executor 执行 |
| "帮我重构 UserService" | 创建 todo → 指定 workspace-id → 分配执行器 |
| "每天早上检查 CI 状态" | 创建 todo + 配置 Cron 调度 |
| "我想看看上周完成了什么" | 用 ntd todo list --status completed 回顾 |
| "帮我部署服务到生产" | 创建 todo → 用 --param 传参 → 执行 |
| "帮我分析这段日志" | 创建 todo → 附带详细 prompt → 执行 |
| "帮我 review 代码变更" | 创建 todo → 指定执行器 → 在工作空间启用 Git Worktree 开关再执行 |
❌ 不应该用 ntd 的场景（直接回答/执行）
| 用户说... | 处理方式 |
|---|---|
| "请解释 Rust 的 ownership" | 直接回答，知识问答 |
| "帮我跑一下 cargo test" | 直接执行命令，即时操作 |
| "今天天气怎么样" | 直接回答，不需要任务管理 |
| "翻译这句话" | 直接回答，即时任务 |
| "帮我查一下这个 API 文档" | 直接回答，不需要持久化 |
判断标准： 如果任务需要被记录、被追踪、被重复执行、或被多个步骤拆分，就用 ntd。否则直接回答或执行。
🔄 典型工作流
场景 A：用户想让 AI 帮忙写代码
用户："帮我重构 UserService"
你的引导流程：
1. 确认任务意图：「好的，我来创建一个任务让 AI 帮你重构 UserService」
2. 收集必要信息：「目标在哪个已注册的工作空间？用哪个 AI 执行器？」（工作空间用 ID 指定，注册方式见文末「工作空间」一节）
3. 创建 Todo：
ntd todo create "重构 UserService" --executor claudecode --workspace-id <N>
4. 执行任务：
ntd todo execute <id> --message "请重构 UserService，重点关注..."
5. 告知用户：「任务已创建，ID 是 X，你可以随时用 `ntd todo get X` 查看状态」
场景 B：用户想回顾已完成的任务
用户："我上周做了些什么？"
你的引导流程：
1. 列出完成的任务：
ntd todo list --status completed --page 1 --limit 50
2. 按 tag 分组展示（如有 tag 信息）
3. 提供统计概览：
ntd stats
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 · 315 lines · 36 tokens per session scan A 04fe5f37bb20
ntd-usage is a skill published in the GitHub repository weibaohui/ntd (11 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 4,095 once invoked, about $0.0002 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 skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.