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 hanzhcn/laohan-skills --skill laohan-douyinsousuogit clone --depth 1 https://github.com/hanzhcn/laohan-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/hanzhcn/laohan-skills/laohan-douyinsousuo)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-douyinsousuo"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-douyinsousuo/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/hanzhcn/laohan-skills/laohan-douyinsousuo"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-douyinsousuo.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 | $0.00109 | $0.01506 |
| Opus 5 | $0.00055 | $0.00753 |
| Sonnet 5 | $0.00022 | $0.00301 |
| Haiku 4.5 | $0.00011 | $0.00151 |
Grade A, and why
laohan-douyinsousuo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
抖音搜索
这是工作流里的抖音搜索编排接口。只使用宿主已安装且已登录的 OpenCLI,不自带爬虫、浏览器、cookie 复制、独立 profile 或 Python runtime。
输入
query:必填,搜索关键词。limit:可选,1—30,默认 10。episode:可选,本期episodes/<slug>路径;只允许写00-抖音搜索证据.json与.md,不得写 candidates、source-health 或00-选题.*。
执行
1. 预检
opencli doctor
opencli douyin whoami -f json
Browser Bridge 可连接且 logged_in=true 时执行搜索。任一预检失败时,episode 模式仍写出 UNAVAILABLE 证据与原始错误供①继续判断;独立搜索请求则如实报告当前不可用。不要抽取或复制 Chrome cookie,也不要安装新工具。
2. 搜索
Episode 模式用确定性包装器一次执行 1—3 个短名单查询并原子写 JSON/Markdown:
node ~/Documents/laohan-skills/laohan-douyinsousuo/scripts/search-evidence.mjs \
--episode episodes/<slug> \
--query "关键词一" \
--query "关键词二" \
--limit 10
独立单查询可直接执行:
opencli douyin search "$QUERY" --limit "$LIMIT" -f json
结果必须是 JSON 数组,并逐条保留 OpenCLI 返回的 rank、desc、author、url、aweme_id、发布时间及可用互动字段。稳定 id 优先使用 aweme_id 或 URL 中的 /video/<id>;两者都没有时才用 sha256(url + desc)[:12]。排名不得参与稳定 id;不要按缺失字段重排,也不要把 OpenCLI 的结果顺序描述成“按点赞排行”。
3. 失败降级
按顺序执行,成功即停:
- 同一命令加
--trace retain-on-failure,使用 OpenCLI autofix 修复现有 adapter;总尝试最多 3 次。 - 若
opencli doctor仍正常但 adapter 持续失败,使用opencli browser douyin-search bind绑定用户当前已登录的抖音标签页,仅做读取和取证。执行浏览器降级前说明会操作当前标签页。 - 仍失败则记录失败层级和原始错误。episode 模式标记平台数据
UNAVAILABLE并返回证据文件,不把它升级为①的卡点;独立搜索请求报告本次未取得结果。不得临时安装 DrissionPage、Playwright、浏览器或自制爬虫。
输出与判断
先展示搜索健康状态和实际返回条数,再展示结果表:
| # | 作者 | 点赞 | 标题 | 链接 |
|---|---|---|---|---|
| 1 | author | likes/不可用 | desc | url |
- 互动字段缺失写
null并在field_availability标记false;实际返回数字0则保留 0 并标记true,不得混为一谈。 - 返回空数组时写
EMPTY_OR_FIELD_UNAVAILABLE;不能据此断言抖音上没有相关内容。 - 当前已安装 OpenCLI 1.8.6 的
douyin search只提供搜索结果样本,卡片通常只有点赞字段;douyin hashtag hot可提供全站热点,已由 laohan-redian 的 discovery route 使用。douyin hashtag search当前接口实测失败,hashtag hot --keyword也不能可靠按关键词过滤。因此搜索量、供给总量、增长速度和官方内容缺口默认均为UNAVAILABLE;以后只有 OpenCLI 实际返回这些字段时才使用,不从结果条数或点赞反推。 - 事实性结论必须回到原视频或权威来源核验;搜索结果只能作为发现证据。
- 用户单独要求搜索分析时,可总结结果中可见的内容类型和重复角度;不得决定工作流最终选题,不得补造搜索结果未提供的事实。
- 指定
episode时必须使用 runtime-locked 包装器,先写机器真源00-抖音搜索证据.json,再从它生成.md;Markdown 不得新增 JSON 没有的结论。
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.
- 11d ago First seen · 102 lines · 109 tokens per session scan A 9ab09c10e744
laohan-douyinsousuo is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,506 once invoked, about $0.0005 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
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
douyin-upload
A workflow for using the sau command-line tool to log in to Douyin, the Chinese short-video platform, check account cookies, and publish videos or image-and-text posts.
kuaishou-upload
A workflow for using the sau command-line tool to log in to Kuaishou, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
xiaohongshu-upload
A workflow for using the sau command-line tool to log in to Xiaohongshu, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.