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 uvwt/agentdock-skills --skill douban-marksgit clone --depth 1 https://github.com/uvwt/agentdock-skillsWrote 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/uvwt/agentdock-skills/douban-marks)<a href="https://agentmods.dev/skills/uvwt/agentdock-skills/douban-marks"><img src="https://agentmods.dev/badge/skills/uvwt/agentdock-skills/douban-marks/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/uvwt/agentdock-skills/douban-marks"><img src="https://agentmods.dev/badge/skills/uvwt/agentdock-skills/douban-marks.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 | $0.00085 | $0.01025 |
| Opus 5 | $0.00043 | $0.00513 |
| Sonnet 5 | $0.00017 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
douban-marks 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
豆瓣标记
用于只读查询豆瓣标记数据。
能力边界
- 读取操作只读；写入操作必须显式要求并默认
dry_run=true。 - 不接收明文 cookie 参数；如需登录态，使用
DOUBAN_COOKIE环境变量或本地.env。 - 默认读取公开主页；如果列表私密，必须是用户自己的登录态。
- 不用于批量采集、绕反爬、抓取非授权账号或高频同步。
- 写入只允许操作用户自己的账号；真实提交必须提供
DOUBAN_COOKIE、dry_run=false和confirm=true。
常用操作
movie-suggest: 搜索电影候选。movie-watched: 读取电影已看。movie-wish: 读取电影想看。movie-doing: 读取电影在看。marks: 通用读取，category为movie、book、music，status为collect、wish、do。status: 检查网页接口可达性，以及是否配置了DOUBAN_USER_ID、DOUBAN_COOKIE。movie-interest-status: 用登录态检查电影条目标记弹窗。movie-mark-wish: 标记想看。movie-mark-doing: 标记在看。movie-mark-watched: 标记看过，可附带 1-5 星评分。movie-rate: 提交看过并评分。
配置
可在 AgentDock 环境或本地 .env 设置：
DOUBAN_USER_ID=你的豆瓣用户 ID
DOUBAN_COOKIE=bid=...; dbcl2=...; ck=...
DOUBAN_COOKIE 只用于请求头，不会出现在输出里。
辅助脚本执行
Skill 本体是本说明文档。确需调用包内辅助脚本时，在 Skill 包根目录使用相对路径执行；运行宿主负责切换到包根目录并把所需变量注入当前子进程。
printf '%s' '{"skill_action":"<动作>"}' | python3 run.py
输入必须是 JSON 对象。写操作仍按本文档中的确认规则执行。
| 动作 | 用途 |
|---|---|
status |
检查豆瓣网页接口可达性，以及本地是否配置了 DOUBAN_USER_ID 和 DOUBAN_COOKIE。 |
movie-suggest |
查询豆瓣电影联想候选，返回标题、年份、豆瓣 ID、类型、海报和 URL。 |
marks |
读取豆瓣用户标记列表。category 支持 movie/book/music；status 支持 collect/wish/do。默认从 DOUBAN_USER_ID 取用户 ID。 |
movie-watched |
读取电影已看列表，等价于 marks(category=movie,status=collect)。 |
movie-wish |
读取电影想看列表，等价于 marks(category=movie,status=wish)。 |
movie-doing |
读取电影在看列表，等价于 marks(category=movie,status=do)。 |
movie-interest-status |
用登录态读取电影条目标记弹窗，检查是否能提取当前兴趣状态。需要 DOUBAN_COOKIE。 |
movie-mark-wish |
将电影标记为想看。默认 dry_run=true；真实写入必须 dry_run=false 且 confirm=true，并需要 DOUBAN_COOKIE。 |
movie-mark-doing |
将电影标记为在看。默认 dry_run=true；真实写入必须 dry_run=false 且 confirm=true，并需要 DOUBAN_COOKIE。 |
movie-mark-watched |
将电影标记为看过，可附带 1-5 星评分。默认 dry_run=true；真实写入必须 dry_run=false 且 confirm=true，并需要 DOUBAN_COOKIE。 |
movie-rate |
给电影评分；本质上提交看过 collect + rating。默认 dry_run=true；真实写入必须 dry_run=false 且 confirm=true，并需要 DOUBAN_COOKIE。 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 67 lines · 85 tokens per session scan A a857fbf4fead
douban-marks is a skill published in the GitHub repository uvwt/agentdock-skills (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,025 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
muapi-workflow
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
muapi-media-editing
Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.
muapi-media-generation
Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5.
wechat-article-writer
A Chinese-language content-creation workflow for public-account and social-media writing. It supports article drafting, cover images, illustrations, process diagrams, style analysis, and adapting writing to selected styles.
muapi-storyboard-to-cooking-video
Turn a single photo of a person into a 15-second cinematic pasta-making (or other cuisine) tutorial video. First builds a composite reference sheet (character + kitchen + 9-step action board), then animates the full cooking sequence with audio in a single continuous shot.