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-donghuagit 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-donghua)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-donghua"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-donghua/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-donghua"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-donghua.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 | $0.00053 | $0.02087 |
| Opus 5 | $0.00026 | $0.01043 |
| Sonnet 5 | $0.00011 | $0.00417 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
laohan-donghua 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
真人口播动画生产
2026-07-16 起，本 skill 仅保留 METHOD_LAB/历史兼容。新 episode 默认由
codex-direct-production直接编写 Remotion、渲染完整 candidate、完整观看并最多修三轮；不经过 proposal/extension/seal 或双 renderer。
本 skill 执行已经做出的导演决策，不重新决定哪些话要动画。动画不是固定 B-roll 覆盖率，也不是一个 HTML 模板。
必要输入
读取当前 episode：
- 07-剪辑/clean.mp4 与 subtitles.srt；
- 09-导演/edl.json、animation-brief.json、animation-ast.json、source-manifest.json、renderer-brief.md、styleframes 与 animatic-manifest.json；NATIVE 还包括 renderer-route.json 与 caption-style.json；
- 10-素材/素材清单.json（仅当 EDL 有 BROLL_STOCK）；
- episode-config.json。
缺输入时报告文件名并停止。只有 素材清单.json 标为 visually_verified 的资产可以使用。
🛑 STOP：EDL、animation brief/AST、source manifest、renderer brief、animatic 或 required 素材缺失时，不创建 renderer 项目。先运行 node animation-method/scripts/compile-animation-ast.mjs episodes/<slug>/09-导演 --check；漂移时回⑨，不在⑪手修 AST。
工作流
1. 建立 renderer 任务
先在 workflow 根运行 node scripts/prepare-renderer-handoff.mjs episodes/<slug> <remotion|hyperframes>。两个 renderer 只能消费各自 11-动画/renderer-handoffs/<renderer>/input-manifest.json，先验证全部 SHA-256；禁止从 视频动画 的旧 pilot 或历史 project 猜输入。
渲染前运行 node scripts/verify-renderer-handoff.mjs episodes/<slug>/11-动画/renderer-handoffs/<renderer>/input-manifest.json。任何 hash 变化都回⑨或⑩重新生成 handoff，不能沿用旧 candidate。
读取 handoff 后，先为每个 renderer 写 11-动画/renderer-proposals/<renderer>.json：必须绑定当前 brief SHA，完整映射 AST state，能力只能来自 AST allow-list，proof 只能绑定⑩的 asset ID/SHA。再生成并验证 11-动画/renderer-extensions/<renderer>.json，同时绑定 AST/proposal SHA 和全部 state/transition/fact boundary；缺 extension 不得开始实现。
NATIVE 的确定性顺序固定为：
node scripts/prepare-renderer-extension.mjs episodes/<slug> <renderer>，再以--check验证；node scripts/create-renderer-workspace.mjs episodes/<slug> <renderer>创建未 seal scaffold；- 只在本期 workspace 实现批准 extension，移除
NATIVE_IMPLEMENTATION_REQUIRED； node scripts/seal-renderer-workspace.mjs episodes/<slug> <renderer>，再运行node scripts/verify-renderer-workspace.mjs episodes/<slug> <renderer>；node scripts/render-episode-<renderer>.mjs episodes/<slug>只生成candidates/base/<renderer>.mp4；node scripts/apply-review-captions.mjs episodes/<slug> <renderer>使用同一 SRT/caption style 生成candidates/<renderer>.mp4和 caption evidence。
What ships with it
11 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.
- references/broll-architecture.md 9.1 KB
- references/broll-design-reference.md 5.1 KB
- references/broll-techniques.md 43 KB
- references/example-a-data.html 4.8 KB
- references/example-b-list.html 4.3 KB
- references/example-c-concept.html 3.9 KB
- references/example-d-negate.html 3.5 KB
- references/example-e-affirm.html 3.5 KB
- references/example-f-punch.html 2.5 KB
- references/example-g-cta.html 4.1 KB
- references/example-h-stamp.html 3.8 KB
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 · 104 lines · 53 tokens per session scan A f111a806e20a
laohan-donghua is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 2,087 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
officecli-pitch-deck
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
morph-ppt-3d
3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.
bilibili-upload
A workflow for using the sau command-line tool to log in to Bilibili, a Chinese video-sharing platform, check an account, and upload videos.
video-director
A general workflow for AI video requests, covering video creation, planning, editing, storyboards, keyframes, reference images, and talking-head characters.
cosyvoice-ssml
An internal skill for the CosyVoice text-to-speech step in approved digital-person and character voice-video workflows. It is not intended for ordinary chat, audio, short-video, product-video, or advertising requests.