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 saudademjj/luopan --skill travel-plannergit clone --depth 1 https://github.com/saudademjj/luopanWrote 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/saudademjj/luopan/travel-planner)<a href="https://agentmods.dev/skills/saudademjj/luopan/travel-planner"><img src="https://agentmods.dev/badge/skills/saudademjj/luopan/travel-planner/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/saudademjj/luopan/travel-planner"><img src="https://agentmods.dev/badge/skills/saudademjj/luopan/travel-planner.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 | $0.00091 | $0.05719 |
| Opus 5 | $0.00046 | $0.02860 |
| Sonnet 5 | $0.00018 | $0.01144 |
| Haiku 4.5 | $0.00009 | $0.00572 |
Grade A, and why
travel-planner 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 10d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
旅行规划 (Travel Planner)
When to Use
- 用户提出任何旅行、出游、行程规划相关需求时使用;用户未明说"规划"但请求涉及目的地、天数、路线或行程安排的,同样适用
- 覆盖自由行、家庭游、亲子游、商务出差、自驾等所有类型
为用户的旅行需求生成一份完整、可执行、节奏合理的规划。输出一律用中文。 以下四个步骤按顺序执行,不得跳步、不得提前输出。
第一步:收集需求(必问预算)
在开始任何联网查询或规划前,先收集齐以下信息。用户请求里没明确给出的,用一次提问问清(不要逐条追问,按顺序打包成 4-7 个问题):
- 出发地:用户所在城市/出发城市(影响大交通与预算口径;用户未提时默认按用户所在地推断,并在输出页眉注明推断假设)
- 目的地:城市/地区,必要时细分到区域
- 日期与天数:起止日期或"X天"+ 大致出发时间
- 同行人与人数:个人 / 情侣 / 带老人 / 带孩子 / 团队——老人小孩直接影响节奏
- 预算——必须问:人均或总预算、口径(含不含机票/购物)。用户没提预算就必须问,不能跳过、不能自己默认。若用户说"没想好",给出档位让他选:经济(青旅/公共交通)、舒适(中档酒店/地铁为主)、奢华(高星酒店/包车)。**预算未确认前,只输出问题清单,不输出任何行程内容——包括草稿、框架、示例,都不要给。**若用户明确拒绝提供预算,默认按舒适档规划,并在输出页眉注明"按默认舒适档估算"。用户回答预算后,才进入第二步。
- 偏好:节奏(松弛/紧凑/无所谓)、兴趣(美食/人文/自然/购物/夜生活/小众)、避雷内容
- 限制:签证/证件、身体条件、天气敏感度、是否需要 WiFi/翻译/无障碍
目的地范围红线:行程范围严格等于用户指定的目的地(指定城市名即其行政市域,指定地区即该地区域)。不得擅自加入其他城市/区域——包括"顺路""高铁 1 小时内"的周边一日游,哪怕你认为单城天数偏长。若天数确实偏多:(1)优先放慢节奏、加深单城玩法——冷门点位、博物馆、街区深度游、留半天休息日;(2)周边一日游只能作为问题清单里的一道选择题先问用户("X天单城可能偏长,是否考虑加 1-2 天周边一日游?"),用户明确同意后才纳入主行程;未获同意则主行程保持单城。若用户明确要求"环线/深度游"等跨区域形态,当行程必须覆盖跨出指定区域的部分时,在输出开头向用户明确解释每个跨区点的原因,并给出严格限定在指定区域内的替代方案,让用户拍板,不得擅自决定。
第二步:联网调研(实时信息)
用 WebSearch/WebFetch 联网核实以下内容,输出中标注信息来源与查询日期:
- 目的地当前状况:最佳季节、当月天气气温、节庆或大型活动(影响人流与价格)
- 大交通:出发地→目的地航班/高铁/大巴的价格区间与耗时、机场/车站→市区方式
- 住宿:按预算档位推荐区域,各区域特点与大致价位
- 景点:必去景点开放时间、门票、预约要求、排队预期;小众景点
- 签证/入境(国际旅行必查):要求、材料、办理时间
- 当地实用信息:时差、货币、语言、安全、电源插头
调研纪律:
- 搜索时带年份/月份关键词,优先取最新信息;区分"攻略观点"与"事实性信息"(开放时间、票价、签证政策以官方为准)
- 来源分级:事实性数据(票价/开放时间/政策)优先官方渠道(景区官网、政府公告、12306、航司、场馆官方公众号),权威媒体次之;自媒体与"野榜"(小红书、自媒体榜单、平台号攻略)只作线索不作依据——仅出自自媒体的信息须标注"来源为自媒体,需官方确认",不得当确定事实写;美食/口碑类推荐须多个本地来源交叉验证,单一榜单不作推荐理由
- 可追溯:每个事实性数据(票价、开放时间、闭馆日、签证要求、班次时刻)都要能追溯到来源——查询所得项标注来源与查询日期(如"某航司官网 2026-08""官方公告 2026-02"),未查到的一律明确写"未查到,需自行确认"
- 绝不编造:查不到或不确定的,明确写"需以官网/预订平台为准"
- 若联网工具不可用,在输出开头声明:"以下为知识库信息,票价/开放时间/航班等实时信息可能过期,请以官方渠道为准"
第三步:构建行程框架
先定优先级,再排天,然后逐条校验以下规则(R1-R13 全部必须满足,编号用于对照,不是可选项):
R1 优先级分级:用调研结果与目的地公认热度,把候选景点分为必去级(城市顶级地标——5A/国家级场馆/当地共识必打卡)、值得去级(有特色但可取舍)、可选级(锦上添花,如次级景点、小众点位)。必去级必须进主行程,绝不放备选;可选级只作补充,不能当行程主卖点。排序依据是热度数据与官方评级,不是模型自己的偏好。若必去级总量超出天数可承载(按 R3 体量、R4 独占一天计算排不下),不得静默删减:按热度与官方评级降序,把取舍选项一次写入问题清单让用户拍板(如"3 天排不下全部必去景点,以下二选一:…)",用户同意后才可移出主行程,并在自检表备注注明原因与依据。
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.
- 10d ago First seen · 231 lines · 91 tokens per session scan A daa56598e727
travel-planner is a skill published in the GitHub repository saudademjj/luopan (1 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 5,719 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 2026-08-31.
Other skills, from other repositories
patent-disclosure-skill
A Chinese patent-work assistant for finding invention ideas, writing patent disclosures, explaining patents in plain language, tracking policy changes, and preparing responses to examiner notices.
patent-search
A search tool for published Chinese patent records, using fields such as inventor, applicant, classification number, and title.
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
patent-application
A patent-application document workflow that turns supplied invention materials into claims, a description, an abstract, and black-and-white drawings. It can also produce Markdown and Word files.
patent-disclosure
A guided workflow for finding patentable ideas, doing a limited prior-art search, and drafting a Chinese patent disclosure document. A disclosure document describes an invention for later patent drafting.
patent-oa
An assistant for preparing replies to patent office examination opinions in China. It can use stored past cases and practice manuals to help shape a draft, which must be reviewed before filing.