Borrowing it
Nothing to install: this file belongs to zexuanw958-svg/travel-plan-viz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zexuanw958-svg/travel-plan-viz/main/CLAUDE.mdgit clone --depth 1 https://github.com/zexuanw958-svg/travel-plan-vizWrote 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/instructions/zexuanw958-svg/travel-plan-viz/claude-md)<a href="https://agentmods.dev/instructions/zexuanw958-svg/travel-plan-viz/claude-md"><img src="https://agentmods.dev/badge/instructions/zexuanw958-svg/travel-plan-viz/claude-md/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/instructions/zexuanw958-svg/travel-plan-viz/claude-md"><img src="https://agentmods.dev/badge/instructions/zexuanw958-svg/travel-plan-viz/claude-md.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 | $0.02159 | $0.02159 |
| Opus 5 | $0.01079 | $0.01079 |
| Sonnet 5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
travel-plan-viz CLAUDE.md scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **图片必须能加载**：用 `https://commons.wikimedia.org/wiki/Special:FilePath/<URL编码文件名>?width=N`（不要手拼 `upload.wikimedia.org/.../thumb/...` 哈希直链），且每个 URL 要 `curl` 校验返回 200 才用；图片 CSS 用 `object-fit: cover` 防变形。 How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
给在本仓库开发/维护这个 skill 的 AI。终端用户怎么用 skill 见 README.md，skill 运行逻辑见 travel-plan-viz/SKILL.md。
这是什么
travel-plan-viz —— 一个 Claude Code / Codex 通用 Skill（也可适配其他 Agent），把旅行行程生成为单文件、离线可读、手机优先的 HTML（交互地图 + 每日时间轴 + 出发前提醒 + 行前须知 + 待选航班 + 片区价位酒店）。
命名分层（别去"统一"）：README 门面品牌名是 Migo · 旅行领航（Migo = 候鸟领航员吉祥物），但技术 id、SKILL.md
name、触发词、GitHub 仓库名一律保持travel-plan-viz不变——这是有意的分层设计（门面品牌与技术标识各司其职，保持安装路径与触发词稳定）。README 与 SKILL.md 名称"不一致"属正常，请勿为对齐而改动触发词或仓库名。
架构红线
- 混合架构：易错的机械逻辑固化为可复用 JS 引擎，视觉表现每次交给设计步骤重新生成。改动时别把布局/配色写死进引擎，也别把日期/导航逻辑塞给设计步骤临场生成。
- 设计步骤可插拔（无硬依赖）：优先用
frontend-design或huashu-designskill（任一已安装），都没有则走references/design-guidelines.md内置准则。这样 skill 可独立分享，不强制别人先装别的 skill。别把它改回硬依赖某个外部 skill。 - 第三方旅行 skill 可选适配（软依赖，非代言）：用户若同时装了飞猪、高德、腾讯地图、滴滴等官方旅行类 skill / MCP，本 skill 可调用它们拿实时/权威数据（航班、酒店、坐标、路线规划、用车等）来补全调研，并在成品里附「去预订 / 导航 / 叫车」行动链接；没装则走现有静态调研，功能不缺失、不降级。这跟「设计步骤可插拔」同构——永远是软依赖、优雅降级，别改成硬依赖或强制安装。两条底线不能破：①责任边界——这类数据的实时性与真实性由对方官方 skill 负责，本 skill 只做适配与编排，页面须标注数据来源、用中性措辞、不背书不替某一家打广告；②本 skill 引擎/调研永远不自行抓实时票价，实时数据只可能来自用户已装的官方 skill（不违背「不查实时票价」红线）。细则见
references/research-guide.md的「第三方 skill 适配」节（含具名官方入口），字段见assets/page-contract.md。另：map.js自带按境内外分流的高德/Google 免 key URI 点位链接（官方公开 URI 规范、不承载实时数据），不属于 actionLink 的「绝不手拼」禁令，边界见 page-contract「可选适配元素」。2026-07-15 拍板不做：高德 JS API 嵌进成品页、引擎自建 REST 直连（即使用户自备 key）。 - 引擎双端可用：
assets/map.js、assets/reminders.js同时跑在浏览器和 Node，靠文件底部的if (typeof module !== 'undefined' && module.exports)守卫导出。改这两个文件别破坏这个守卫。assets/validate.js是第三个引擎（契约机械校验，Node 侧用，含 CLI），不内联进页面。 - 坐标一律 WGS-84：OSM 瓦片是 WGS-84，高德/腾讯返回 GCJ-02——来自它们的坐标必须经
map.js的gcj02ToWgs84转换再入trip，否则境内点位偏移几百米。别删这个转换，也别默认所有坐标都要转（静态调研的坐标通常已是 WGS-84）。 - 数据与呈现分离：完整
trip以<script id="trip-data" type="application/json">内嵌进成品页面，迭代修改读这块 JSON、不反解析 DOM。别把这个约定改掉。 - 离线能力如实表述：对外说「离线可读」（文字行程离线可读；地图/图片需联网、有 onerror 降级），别写成"完全离线可用"。
escapeHTML在 map.js 与 reminders.js 各有一份，是故意重复——两文件须各自独立，别合并去重。- 内容契约是权威：
assets/page-contract.md定义trip数据结构和必须包含的区块。改了引擎导出的函数名/数据字段，必须同步这份契约和SKILL.md。
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.
- 13d ago First seen · 51 lines · 2,159 tokens per session scan A 710831a243a9
travel-plan-viz CLAUDE.md is an instructions file published in the GitHub repository zexuanw958-svg/travel-plan-viz (373 stars, last pushed yesterday), licensed MIT. It adds 2,159 tokens to every session, about $0.0108 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).