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 freestylefly/wesight --skill films-searchgit clone --depth 1 https://github.com/freestylefly/wesightWrote 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/freestylefly/wesight/films-search)<a href="https://agentmods.dev/skills/freestylefly/wesight/films-search"><img src="https://agentmods.dev/badge/skills/freestylefly/wesight/films-search.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.01446 |
| Opus 5 | $0.00026 | $0.00723 |
| Sonnet 5 | $0.00010 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
films-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to films-search — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Films Search Skill
搜索影视资源（电影、电视剧、动漫），通过实时爬虫深度抓取资源页面，从各网盘平台获取公开分享的资源链接。
前置条件
- web-search skill（必需，用于搜索发现资源页面）
命令
搜索资源
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "关键词" [选项]
选项：
| 参数 | 说明 | 默认值 |
|---|---|---|
--pan <type> |
筛选网盘类型: quark, baidu, aliyun, uc, all |
all |
--quality <q> |
筛选画质: 4k, 1080p, 720p, all |
all |
--limit <n> |
每个平台最大结果数 | 5 |
--engine <e> |
搜索引擎: deep, web |
deep |
引擎说明：
deep（默认，推荐）— web-search 搜索发现资源页面 + JavaScript 深度抓取提取网盘链接和提取码，结果最准确web— 仅从 web-search 搜索引擎摘要中提取链接（速度快，但准确率较低，不做深度抓取）
示例：
# 搜索所有平台的资源（默认使用深度搜索）
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2"
# 只搜夸克网盘 4K 资源
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --pan quark --quality 4k
# 限制结果数量
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --limit 10
# 使用浅层搜索（不深度抓取页面）
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --engine web
Windows 系统使用 PowerShell 脚本：
powershell -File "$SKILLS_ROOT/films-search/scripts/film-search.ps1" search "流浪地球2" --pan quark
热门推荐
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" hot "2025年热门电影"
本质上是以推荐类关键词调用搜索，返回相关网盘资源。
解析跳转链接
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" resolve "https://example.com/goto/xxx"
当搜索结果中的链接需要二次跳转时，用此命令解析出真实网盘地址。
Agent 使用流程
- 用户说「帮我找 XXX 电影」→ 执行
search "XXX" - 解析返回的 JSON，提取网盘链接
- 按网盘类型和画质分组呈现给用户
- 如果结果中有提取码 (
extractCode)，一并展示给用户 - 如果结果中有
pageUrl但没有直接url，用resolve命令获取真实地址
示例对话：
用户：帮我找一下流浪地球2的夸克网盘资源，要4K的
Agent：
- 执行
search "流浪地球2" --pan quark --quality 4k- 从 JSON 结果中取出匹配项
- 返回：标题 + 画质 + 夸克网盘链接 + 提取码（如有）
输出格式
所有命令输出 JSON，结构如下：
{
"success": true,
"data": {
"query": "流浪地球2",
"total": 5,
"results": [
{
"title": "资源标题",
"pan": "quark",
"url": "https://pan.quark.cn/s/xxx",
"quality": "4K",
"extractCode": "ab12",
"source": "deep-search",
"pageUrl": "https://example.com/resource/123"
}
]
}
}
What ships with it
4 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.
- 9d ago First seen · 153 lines · 51 tokens per session scan A 7e0f9c2eff69
films-search is a skill published in the GitHub repository freestylefly/wesight (916 stars, last pushed 15d ago), licensed MIT. It adds 51 tokens to every session and 1,446 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to films-search, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ai-image-generation-master
Expert-level guide to AI image generation across Midjourney, DALL-E, and Stable Diffusion covering prompt engineering for visual output, style control, composition techniques, upscaling workflows, and production pipelines for consistent, high-quality results. Use when the user asks about ai image generation master…
wayland-build-investor-deck
Build an investor pitch deck end to end: from the narrative story arc through slide-level briefs, full slide content, narrative tightening, and speaker notes. The agent infers the story arc that makes the round credible to the investor archetype, drafts each slide's argument and proof, then tightens the narrative and…
tavern-management
Use when the user asks to import or translate an Lfcode Tavern or SillyTavern character card or worldbook, including PNG image cards, or manage the Tavern plugin lifecycle.
weftcut
Drive the WeftCut video editor over its MCP tools. Use BEFORE calling any weftcut MCP tool — when the user wants to edit video in WeftCut (cut, trim, arrange a timeline, add captions or voiceover) or author/update a Motif (animated overlay).
imagemaker
Use when the user asks to generate, revise, configure, manage, insert, or export images with the Lfcode ImageMaker plugin or its supported image-generation APIs.
slide-deck-builder
Use when the user asks to create, revise, restructure, or quality-check a presentation or slide deck. Inspect the source deck, template, assets, audience, and available rendering tools first, then validate slide structure and rendered layout before claiming completion.