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 mrsunjc/TravelPilot-agent-skills --skill travel-plannergit clone --depth 1 https://github.com/mrsunjc/TravelPilot-agent-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/mrsunjc/travelpilot-agent-skills/travel-planner)<a href="https://agentmods.dev/skills/mrsunjc/travelpilot-agent-skills/travel-planner"><img src="https://agentmods.dev/badge/skills/mrsunjc/travelpilot-agent-skills/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/mrsunjc/travelpilot-agent-skills/travel-planner"><img src="https://agentmods.dev/badge/skills/mrsunjc/travelpilot-agent-skills/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 | $0.00195 | $0.02882 |
| Opus 5 | $0.00097 | $0.01441 |
| Sonnet 5 | $0.00039 | $0.00576 |
| Haiku 4.5 | $0.00019 | $0.00288 |
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 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能旅行规划助手
把调研结果转成真正能执行的日程,而不是简单罗列热门景点。第一优先级是路线合理:先建立位置与交通关系,再决定每天去哪以及先后顺序。
平台兼容
- 核心规范只依赖本文件、
references/、schemas/和 Python 3 标准库脚本;不要假定存在某个厂商专属工具。 - 使用当前 Agent 可用的搜索、浏览器、地图、天气和文件工具。某类工具不可用时,继续完成方案并明确降级项。
- 确定性 SVG 信息图不依赖图片模型;AI 封面只调用宿主已经提供的生图工具或用户明确配置的图片 API,不复制任何厂商私有系统 Skill。
agents/openai.yaml只是 OpenAI/Codex 的可选界面元数据,其他 Agent 可以忽略。- 不把 API key、令牌、证件号或预订凭据写入 Skill、计划文件、命令、日志或回复。地图服务密钥只能由宿主通过环境变量或安全凭据存储提供。
最小输入规则
用户只说“洛阳,3天”也要直接生成,不得把补充问题设为前置条件。缺失信息采用以下默认值并在结果开头列出:
- 普通成年游客、正常强度、中等预算;公共交通为主,明显节时处建议打车。
- 未给日期:不生成伪精确天气;开放时间、票价和预约规则仍尽量查询最新信息,并注明核验日期。
- 未给抵离时间:按三个完整游玩日规划;最后一天保持可裁剪,并提醒补充车次/航班后可二次优化。
- 未给出发城市:只规划抵达当地交通枢纽后的路线。
- 地名有歧义时,选择最常见含义,清楚写出假设并允许用户一句话纠正。
只有在错误假设会造成高风险或目的地无法识别时才必须追问。其余问题可以在交付完整初版后作为可选优化项询问。
工作流
1. 解析需求
提取目的地、天数/日期、出发城市、抵离枢纽与时间、同行人、强度、预算、住宿偏好、必去和排除景点。读取 references/planning-rules.md 确定默认值、强度上限和特殊人群约束。
2. 实时调研
先建立候选景点池,再核验票价、开放时间、闭馆日、预约、临时关闭、季节限制和适合时段。提供具体日期时查天气,并只在可靠预报期内给出逐日天气。
必须读取并遵守 references/research-policy.md。优先官方来源;关键动态事实注明来源与核验日期。无法联网时不得编造精确数字,要标为“待核验”或范围估计。
宿主没有同类工具而需要标准化 API 数据时,读取 references/api-providers.md 并使用 scripts/provider_client.py。当前支持:
- 高德:国内地理编码、景点搜索、步行/公交/驾车路线;密钥只能来自
AMAP_API_KEY。 - Open-Meteo:最多 16 天的逐日天气规范化。
- Nominatim:仅在用户/开发者明确接受官方使用政策、提供缓存目录时进行单次地理编码;禁止自动补全和批量抓取。
API 输出只是研究证据,不等于景点官方票务或开放公告。票价、预约、闭馆和紧急信息仍需优先核验一手来源。
3. 景点分级
按城市代表性、独特性、用户兴趣、口碑稳定性、游览成本和路线代价分成:
- 必去:第一次到访时最能代表目的地,且与用户约束相容。
- 推荐:值得去,但可因距离、天气或兴趣替换。
- 可选:填充空档或适合特定偏好,行程紧时优先删除。
用户指定的必去项不能静默删除;用户明确不想去的项不能出现在主方案中。
4. 建立空间与交通模型
这是排程前置条件,不得先写 Day 1 再补交通:
- 为景点、候选住宿区、车站/机场建立坐标或地图位置。
- 获取相关时段的点到点距离、预计时间、换乘次数与大致费用;地图路径优先于直线距离。
- 按自然片区聚类,如城北、老城、城南或相邻街区;不要只根据行政区名。
- 比较步行、公共交通、打车/网约车;结合人数与节省时间选择,而非固定偏爱某一种方式。
- 每天以一个主片区为核心,通常只允许一次有方向的跨区移动;避免上午城北、下午城南、晚上又回城北。
数据较多时,把研究结果整理成 JSON,并运行:
python scripts/validate_schema.py trip_input.json --schema schemas/route-input.schema.json
python scripts/route_optimizer.py trip_input.json --output optimized_route.json
脚本使用已提供的真实交通矩阵;没有矩阵时退化为坐标/片区估算并在输出中标记,不能把估算冒充地图实测。
What ships with it
32 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.
- agents/openai.yaml 321 B
- references/api-providers.md 3.0 KB
- references/data-contracts.md 2.7 KB
- references/output-contract.md 4.2 KB
- references/persistence.md 1.5 KB
- references/planning-rules.md 5.9 KB
- references/quality-gates.md 2.7 KB
- references/research-policy.md 4.1 KB
- references/visual-output.md 3.0 KB
- schemas/final-plan.schema.json 12 KB
- schemas/handoff.schema.json 1.6 KB
- schemas/quality-policy.json 1.8 KB
- schemas/route-input.schema.json 2.4 KB
- scripts/plan_store.py 8.1 KB runs code
- scripts/provider_client.py 16 KB runs code
- scripts/route_optimizer.py 24 KB runs code
- scripts/travel_quality/__init__.py 99 B runs code
- scripts/travel_quality/common.py 3.5 KB runs code
- scripts/travel_quality/evidence_checks.py 8.3 KB runs code
- scripts/travel_quality/handoff_checks.py 4.2 KB runs code
- scripts/travel_quality/plan_checks.py 22 KB runs code
- scripts/travel_quality/quality_gate.py 3.2 KB runs code
- scripts/travel_quality/schema_validator.py 5.6 KB runs code
- scripts/travel_visualizer.py 15 KB runs code
- scripts/validate_handoff.py 1.5 KB runs code
- scripts/validate_plan.py 1.5 KB runs code
- scripts/validate_schema.py 1.1 KB runs code
- tests/__init__.py 51 B runs code
- tests/fixtures/luoyang-three-days.json 2.5 KB
- tests/test_plan_store.py 2.7 KB runs code
- tests/test_route_optimizer.py 4.6 KB runs code
- tests/test_visualizer.py 3.6 KB runs code
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 · 163 lines · 195 tokens per session scan A b461aeb3742c
travel-planner is a skill published in the GitHub repository mrsunjc/TravelPilot-agent-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 195 tokens to every session and 2,882 once invoked, about $0.0010 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
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…
jobs-to-be-done
Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also…
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…