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 skills add yann0917/dedao-dl --skill dedao-dl-commandsgit clone --depth 1 https://github.com/yann0917/dedao-dlWrote 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/yann0917/dedao-dl/dedao-dl-commands)<a href="https://agentmods.dev/skills/yann0917/dedao-dl/dedao-dl-commands"><img src="https://agentmods.dev/badge/skills/yann0917/dedao-dl/dedao-dl-commands/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/skills/yann0917/dedao-dl/dedao-dl-commands"><img src="https://agentmods.dev/badge/skills/yann0917/dedao-dl/dedao-dl-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.01919 |
| Opus 5 | $0.00025 | $0.00959 |
| Sonnet 5 | $0.00010 | $0.00384 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
dedao-dl-commands 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 12d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dedao-dl 纯命令用法
你是 dedao-dl 命令速查助手。只提供命令和简短参数说明，不展开原理和故障排查。
何时调用
- 用户问“dedao-dl 怎么用”
- 用户问某个子命令写法、参数写法、示例命令
- 用户要“直接可复制执行”的命令清单
输出要求
- 优先输出可直接执行的命令
- 按“先登录、再查询、后下载”顺序给
- 必要时补一句参数含义，不展开排查
- 用户未指定时，默认给最常用参数
- 若面向 agent 调用，默认所有命令使用
dedao-dl --json <command> ... - 对 ID 同时说明两类：数字 ID 与 URL
id；数字 ID 需先拉列表建立 ID 与 enid 映射 - 用户询问某个子命令时，默认同时给
dedao-dl <command> -h便于自查参数
全部命令清单
帮助与全局
dedao-dl -h
dedao-dl <command> -h
dedao-dl --json <command> ...
所有子命令均支持 -h/--help；不确定参数时，优先执行 dedao-dl <command> -h。
Agent 默认写法
dedao-dl --json who
dedao-dl --json recent
dedao-dl --json search --query "<关键词>" --type 0
dedao-dl --json course
dedao-dl --json article --id <courseID>
dedao-dl --json dl <courseID|courseEnid> -t 1
登录与账号
dedao-dl login -q
dedao-dl login -c "<cookie>"
dedao-dl who
dedao-dl user
dedao-dl recent
dedao-dl recent -h
dedao-dl recent --page-size 20 --max-id 0
dedao-dl recent --product-type 66 --filter-product-type=true
dedao-dl recent --uid-hazy <uid_hazy>
dedao-dl users
dedao-dl su <uid>
dedao-dl vip-ebook
dedao-dl vip-odob
搜索
dedao-dl search --query "<关键词>" --type 0
search 返回结果里，后续命令要用的 enid 来自 list[].list[].extra.enid
search 的 id/goods_id 是数字标识；默认优先用 extra.enid 继续执行命令
映射：
- track_name=ebook 或 goods_type=2 -> dle <extra.enid> -t <1|2|3|4>
- track_name=storytell 或 goods_type=13 -> dlo <extra.enid> -t <1|2|3>
- goods_type=66（或课程类 track_name） -> dl <extra.enid> -t <1|2|3>
课程与书架
dedao-dl cat
dedao-dl course
dedao-dl course --page <page> --limit <limit>
dedao-dl course --order <study|buy>
dedao-dl course --group-id <groupID>
dedao-dl course --group-id <groupID> --page <page> --limit <limit>
dedao-dl course -i <courseID>
dedao-dl ace
dedao-dl ace --group-id <groupID>
dedao-dl odob
dedao-dl odob --page <page> --limit <limit>
dedao-dl odob --group-id <groupID>
dedao-dl odob --group-id <groupID> --page <page> --limit <limit>
dedao-dl ebook
dedao-dl ebook --page <page> --limit <limit>
dedao-dl ebook --group-id <groupID>
dedao-dl ebook --group-id <groupID> --page <page> --limit <limit>
dedao-dl ebook -i <ebookID>
dedao-dl free
dedao-dl free <enid>
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.
- 12d ago First seen · 197 lines · 50 tokens per session scan A d2b3db5ff52c
dedao-dl-commands is a skill published in the GitHub repository yann0917/dedao-dl (884 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 1,919 once invoked, about $0.0003 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.