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 MayDay-wpf/snow-app --skill snow-app-docsgit clone --depth 1 https://github.com/MayDay-wpf/snow-appWrote 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/mayday-wpf/snow-app/snow-app-docs)<a href="https://agentmods.dev/skills/mayday-wpf/snow-app/snow-app-docs"><img src="https://agentmods.dev/badge/skills/mayday-wpf/snow-app/snow-app-docs/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/mayday-wpf/snow-app/snow-app-docs"><img src="https://agentmods.dev/badge/skills/mayday-wpf/snow-app/snow-app-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 37 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 37 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00527 | $0.05723 |
| Opus 5.5 | $0.00211 | $0.02289 |
| Sonnet 5.5 | $0.00105 | $0.01145 |
| Haiku 4.5 | $0.00053 | $0.00572 |
Grade A, and why
snow-app-docs 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 yesterday.
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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snow App 文档阅读与配置指导（Docs & Configuration Guide）
当用户请求配置 MCP 服务器、安装与管理 Skills、创建与编写 Skills、配置 Hooks 与子代理、配置 API 密钥与模型、配置图像生成、配置代理与网络、管理浏览器密码/数据、处理应用更新、个性化与自定义请求头、用量/日志诊断、 开发/安装/发布插件、项目级设置，或询问 settings.json 字段 / 内置工具 / 安全边界 / 数据位置，或询问 应用怎么用、功能在哪里、如何上手时， 先阅读应用内置文档，再按文档步骤动手配置，而不是凭记忆操作。
1. 先读文档（Read the docs first）
文档随应用安装到 ~/.snowapp/docs/（Windows 为 C:\Users\<用户名>\.snowapp\docs\）。
文件工具（filesystem-read / filesystem-create / filesystem-replace_edit / filesystem-copy
/ grep-search）会展开开头的 ~，直接把 ~/.snowapp/docs/... 当路径传入即可；若仍报
「找不到指定路径」，用 bash-terminal-execute 执行 echo $env:USERPROFILE（Windows）或
echo $HOME（macOS/Linux）取主目录，再拼绝对路径重试。
先执行 config-list scope=language 读取界面语言（支持 en/zh-CN/zh-TW；
旧安装可能存兼容值 zh，等同简体中文；无法读取时默认中文分支），
再选择对应文档分支（无法读取时默认中文分支）：
- 中文界面 → 读
~/.snowapp/docs/zh-CN/ - English UI → read
~/.snowapp/docs/en/
按任务定位文档（路径相对所选语言分支）：
| 任务 | 使用指南（How-to） | 参考手册（Reference） |
|---|---|---|
| 快速开始（安装/首次运行/基础配置） | 1-快速开始.md（en: 1-getting-started.md） |
— |
| 配置 MCP 服务器 | 2-使用指南/1-配置MCP服务器.md（en: 2-guides/1-configure-mcp.md） |
3-参考手册/1-settings.json配置参考.md |
| 安装与管理 Skills | 2-使用指南/2-安装与管理Skills.md（en: 2-guides/2-install-and-manage-skills.md） |
— |
| 创建与编写 Skills | 2-使用指南/21-创建与编写Skills.md（en: 2-guides/21-create-and-author-skills.md） |
— |
| 开发、安装、发布与管理插件（含插件市场与 AI 自动安装；发布流程见 §11） | 2-使用指南/24-插件开发与安装.md（en: 2-guides/24-plugin-development-and-installation.md） |
3-参考手册/6-插件元数据域参考.md（en: 3-reference/6-plugin-metadata-domains.md；37 个元数据域的字段）、3-参考手册/2-内置工具参考.md（config plugins 域）、3-参考手册/4-数据存储位置.md |
| 判断扩展该做成面板插件还是客户端脚本（选型与重叠场景取舍） | 2-使用指南/26-插件体系选择指引.md（en: 2-guides/26-plugin-type-selection-guide.md） |
2-使用指南/24-插件开发与安装.md、2-使用指南/22-油猴脚本.md |
| 配置 API 密钥与模型 | 2-使用指南/3-配置API密钥与模型.md#5（en: 2-guides/3-configure-api-keys.md#5；§5 为 agent 操作速查） |
3-参考手册/1-settings.json配置参考.md |
| 对话请求代理层（用脚本改写模型请求体与 SSE 响应事件） | 2-使用指南/25-对话请求代理层.md（en: 2-guides/25-conversation-request-proxy.md） |
3-参考手册/5-安全与信任边界.md |
| 配置图像生成 | 2-使用指南/9-图像生成.md（en: 2-guides/9-image-generation.md） |
3-参考手册/2-内置工具参考.md（imagegen 章节与 config 的 imagegen scope） |
| 使用聊天与 AI 助手（界面/对话/命令/回滚/压缩） | 2-使用指南/10-使用聊天与AI助手.md（en: 2-guides/10-using-chat-and-ai.md） |
— |
| 终端与 SSH 远程管理 | 2-使用指南/11-终端与SSH远程管理.md（en: 2-guides/11-terminal-and-ssh.md） |
— |
| Git 面板与代码浏览 | 2-使用指南/12-Git面板与代码浏览.md（en: 2-guides/12-git-and-code-browsing.md） |
— |
| 配置代理与网络、站点拦截规则 | 2-使用指南/4-配置代理与网络.md（en: 2-guides/4-configure-proxy.md） |
3-参考手册/2-内置工具参考.md、3-参考手册/3-配置文件字段参考.md |
| 配置 Hooks 与子代理 | 2-使用指南/5-配置Hooks与子代理.md（en: 2-guides/5-configure-hooks-and-subagents.md） |
— |
| 浏览器自动化 | 2-使用指南/6-浏览器自动化.md（en: 2-guides/6-browser-automation.md） |
— |
| 代码库索引与代码诊断 | 2-使用指南/7-代码库索引与代码诊断.md（en: 2-guides/7-codebase-index-and-diagnostics.md） |
— |
| AI 开发协作、经验与前端美化工作流 | 2-使用指南/13-AI开发协作.md、2-使用指南/14-AI开发经验与教训.md、2-使用指南/15-前端设计与美化工作流.md（en: 2-guides/13-ai-development-collaboration.md、2-guides/14-ai-development-lessons.md、2-guides/15-frontend-design-and-beautification-workflow.md） |
4-架构与开发/2-开发者指南.md |
| 安全、隐私与工具授权 | 2-使用指南/16-安全隐私与工具授权.md（en: 2-guides/16-security-privacy-and-tool-authorization.md） |
3-参考手册/5-安全与信任边界.md |
| 浏览器设置、密码保险库与本机导入 | 2-使用指南/17-浏览器设置密码与数据导入.md（en: 2-guides/17-browser-settings-passwords-and-import.md） |
3-参考手册/4-数据存储位置.md |
| 应用更新 | 2-使用指南/18-应用更新.md（en: 2-guides/18-app-updates.md） |
3-参考手册/5-安全与信任边界.md |
| 系统提示词、个性化、请求头、主题与快捷键 | 2-使用指南/19-个性化主题与快捷键.md（en: 2-guides/19-personalization-theme-and-shortcuts.md） |
3-参考手册/3-配置文件字段参考.md |
| 用量统计与系统日志 | 2-使用指南/20-用量统计与系统日志.md（en: 2-guides/20-usage-statistics-and-system-logs.md） |
3-参考手册/4-数据存储位置.md |
| 查询内置工具 / 配置域 / 日志 | — | 3-参考手册/2-内置工具参考.md#config（en: 3-reference/2-builtin-tools-reference.md#config；§app-control 有 21 个设置页表格） |
| 查询配置文件字段 | — | 3-参考手册/3-配置文件字段参考.md（en: 3-reference/3-config-file-field-reference.md） |
| 架构与开发（构建/故障排查/数据流） | 4-架构与开发/1-架构总览.md、2-开发者指南.md、3-打包与安装故障排查.md、4-Agent运行时与工具编排.md、5-存储迁移备份与恢复.md、6-功能模块架构与数据流图集.md（en: 4-architecture-and-development/1-architecture-overview.md 等，按同名编号对应） |
— |
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.
- yesterday Changed 707273d2488f
- 18d ago Changed · +1 lines · +4 tokens per session 24a80a70be6c
- 19d ago Changed · +3 tokens per session ebb6cd030bab
- 20d ago Changed d4338b266fea
- 22d ago Changed · +2 lines 0a9ae274ff3b
- 24d ago Changed · +2 lines · +71 tokens per session 6256c8c24406
- 26d ago Changed · +1 lines · +5 tokens per session 6ee1ae45b8eb
- 27d ago Changed 80d1f7b0532f
- 1mo ago Changed · +8 lines · +24 tokens per session 57d1c6be4ebe
- 1mo ago First seen · 202 lines · 420 tokens per session scan A c2c2d1d7015a
snow-app-docs is a skill published in the GitHub repository MayDay-wpf/snow-app (156 stars, last pushed today), licensed MIT. It adds 527 tokens to every session and 5,723 once invoked, about $0.0021 per session on Opus 5.5. 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.
snow-app-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| snow-app-docsMayDay-wpf/snow-app | Skill | 156 | today | MIT | A | 527 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |