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.svg" alt="Measured on agentmods" 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 | $0.00351 | $0.04024 |
| Opus 5 | $0.00176 | $0.02012 |
| Sonnet 5 | $0.00070 | $0.00805 |
| Haiku 4.5 | $0.00035 | $0.00402 |
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 8d 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 — 165 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、导入第三方配置 与插件、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、 项目级设置，或询问 settings.json 字段 / 内置工具 / 安全边界 / 数据位置时， 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 ~/.snow/docs/（Windows 为 C:\Users\<用户名>\.snow\docs\）。
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
~/.snow/docs/zh-CN/ - English UI → read
~/.snow/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） |
— |
| 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 |
| 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） |
— |
| 第三方配置导入与插件 runtime | 2-使用指南/8-第三方配置导入.md（en: 2-guides/8-third-party-configuration-import.md） |
3-参考手册/5-安全与信任边界.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.
- 8d ago First seen · 165 lines · 351 tokens per session scan A 99214a51fefc
snow-app-docs is a skill published in the GitHub repository MayDay-wpf/snow-app (65 stars, last pushed today), licensed MIT. It adds 351 tokens to every session and 4,024 once invoked, about $0.0018 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…