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-sucaigit 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-sucai)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-sucai"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-sucai/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-sucai"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-sucai.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 | $0.00092 | $0.01403 |
| Opus 5 | $0.00046 | $0.00701 |
| Sonnet 5 | $0.00018 | $0.00281 |
| Haiku 4.5 | $0.00009 | $0.00140 |
Grade A, and why
laohan-sucai 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B-roll 素材供应器
只为已经判定为 BROLL_STOCK 的现实场景找素材。它不决定动画、不把库存素材伪装成事实、不合成视频。V5默认采用“永久本地素材Top-K＋网络高权重多样性”策略：本地catalog负责快速复用，Pexels/Pixabay/Coverr仍并行提供新候选；只下载最终选择项。
输入与停止条件
正式入口是 09-导演/source-manifest.json 的 broll_requests，以及已批准的 PROOF_PUBLIC/PROOF_USER source_entries。每项 BROLL 必须有 beat_id、source_mode=BROLL_STOCK、visual_need 和 must_not_imply；PROOF 必须有 evidence.id。
🛑 STOP：没有 broll_requests 或请求不是 BROLL_STOCK 时，不搜索、不下载。是否生成请求由⑨素材策略决定；只要真实B-roll能增加具体性或画面变化，默认生成请求，只有明确SKIP_WITH_REASON才跳过网络。没有 provider key 时记录provider_errors并继续永久本地素材召回。
命令
# 搜索候选：默认读取项目本地catalog，同时并行检索Pexels/Pixabay/Coverr
node scripts/sucai.mjs search --source 09-导演/source-manifest.json --out 10-素材/network
# 非项目cwd时可显式指定本地库；local候选会复制到本episode后再抽帧
node scripts/sucai.mjs search --source 09-导演/source-manifest.json --out 10-素材/network --local-library "/绝对路径/你的素材库"
# accepted final使用过的网络素材才晋升永久素材库
node scripts/material-library.mjs promote-episode episodes/<slug>
# 下载一个候选，并生成缩略图供实际视觉检查
node scripts/sucai.mjs download --manifest 10-素材/network/素材清单.json --beat B01 --candidate pexels:123
# 先实际查看缩略图或 contact sheet，再记录判定
node scripts/sucai.mjs verify --manifest 10-素材/network/素材清单.json --beat B01 --candidate pexels:123 --verdict pass --reason "主体、构图和事实边界均匹配"
# 查看当前清单
node scripts/sucai.mjs report --manifest 10-素材/network/素材清单.json
# PROOF 只物化已批准证据；显式视觉确认后复制到本期并登记
node scripts/register-proof-asset.mjs episodes/<slug> B03 <proof-file> <thumb-file> --visually-verified
环境变量和官方申请入口见 references/providers.md。不要把 key 写入 SKILL.md、JSON、episode 或 Git。
工作流
- 读取 broll_requests 的 query_terms；缺 query_terms 时只用 visual_need，记录搜索理由。
- 默认读取项目
本地素材库/catalog.json，只返回相关度最高的本地视频候选；catalog不存在时才回退到文件名扫描。不得把整个素材库塞进导演上下文。 - 无论本地是否命中，Pexels、Pixabay、Coverr默认仍并行提供网络候选，以增加画面多样性。只有本期明确
--providers local时才只查本地；Mixkit不做自动抓取。 - 记录每个provider的status、candidate_count、elapsed_ms、rate_limits，并分别记录本地/网络候选数；单个provider的无key、限流或失败不阻断其他provider。
- 写入
10-素材/network/素材清单.json、素材清单.md、_credits.md；清单绑定当前source manifest，候选初始状态都是candidate_unverified。material-library.mjs promote-episode仍兼容历史episode的10-素材/素材清单.json，新episode只使用network分区。 - 只下载选择的candidate并使用FFmpeg抽帧；local候选先复制到本episode。
- 实际检查人物、动作、画幅、水印、错误文字、字幕安全区和must_not_imply。
- 只有verify pass才标为visually_verified；selected candidate必须位于本期
10-素材/network/broll-assets/并绑定文件/缩略图SHA，⑪只读取这种资产。 - Jeffrey接受final后，只把实际使用且已核验的网络素材通过
material-library.mjs promote-episode晋升永久库；未采用的网络候选不入库。 - PROOF不进入库存B-roll搜索池。只把⑨已批准且绑定⑤
SUPPORTED claim_id的同源evidence复制到10-素材/network/proof-assets/，不重做事实判断。
What ships with it
3 files 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.
- 12d ago First seen · 76 lines · 92 tokens per session scan A 1601d9409149
laohan-sucai is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,403 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.