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 413162826/kevinsu-skills --skill kevin-xhs-minitool-publishergit clone --depth 1 https://github.com/413162826/kevinsu-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/413162826/kevinsu-skills/kevin-xhs-minitool-publisher)<a href="https://agentmods.dev/skills/413162826/kevinsu-skills/kevin-xhs-minitool-publisher"><img src="https://agentmods.dev/badge/skills/413162826/kevinsu-skills/kevin-xhs-minitool-publisher/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/413162826/kevinsu-skills/kevin-xhs-minitool-publisher"><img src="https://agentmods.dev/badge/skills/413162826/kevinsu-skills/kevin-xhs-minitool-publisher.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 | $0.00117 | $0.01368 |
| Opus 5 | $0.00059 | $0.00684 |
| Sonnet 5 | $0.00023 | $0.00274 |
| Haiku 4.5 | $0.00012 | $0.00137 |
Grade A, and why
kevin-xhs-minitool-publisher 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书小工具构建与发布
触发本 Skill 表示用户要把当前项目创建或改造成小红书小工具。默认目标是完成到 Builder Hub 审核状态，但本地成品、上传成功、审核中和已发布必须分别报告。
每次都先读
开始前完整读取 references/platform-contract.md。平台是纯离线沙箱，普通网页里合理的网络、外链和浏览器能力可能直接导致退审。
创建或改造项目时再读 references/build-workflow.md。进入 Builder Hub 前再读 references/publishing.md。不要一次加载与当前阶段无关的细节。
用户确认最终预览后、上传 ZIP 前，必须读取并执行 references/official-skill-gate.md。这个门禁负责从当次 Builder Hub 上传页取得最新版官方 Skill；不能用本 Skill 的本地规则代替，也不能沿用上次缓存的官方版本。
首轮只问真正改变结果的问题
先读项目、现有页面、数据和构建方式，已经能确认的事不要再问。把剩余问题一次问完，最多五个，推荐项放前面：
- 小工具只完成哪一个核心任务。
- 登录、支付、联网 AI、实时数据、外链、统计、联机等能力哪些可以删除或改成构建时快照。
- 数据能否随版本静态打包，多久更新一次。
- 是否需要相册、摄像头或麦克风权限；默认不需要权限。
- 新建还是更新已有小工具，以及名称、简介、图标、封面和发布账号是否沿用现有品牌。
若用户已经明确回答，直接开始，不为流程完整重复提问。发现核心需求必须联网、必须打开站外链接或必须使用禁用能力时，先指出不兼容，再让用户决定砍掉、改成离线版本或停止。
权限边界
- 首次触发授权本地只读检查、创建独立小工具目录、构建、测试和生成上传包。
- 用户确认预览满意后，视为授权填写 Builder Hub 和上传本轮已确认的文件。
- 用户本人完成登录、验证码和服务协议确认。不要代填验证码，不要替用户接受法律协议。
- 提交审核前再给一次简短摘要；用户已明确说“发布”“上线”且已确认预览时，可以在其完成协议确认后提交。
- 发布小工具不等于发布或挂载小红书笔记。挂载、发笔记、下架、撤回、删除或覆盖其他工具需要单独授权。
不可妥协的门禁
- 小工具运行包必须完全离线自包含。
- ZIP 内不得出现网络请求、站外跳转、
target="_blank"、外部资源 URL、iframe、Worker、WebSocket、WebRTC、WASM、剪贴板、全屏、下载、动态执行代码等禁用能力。 - 项目旧文档若要求保留外链、实时接口或其他禁用能力，平台当前规则优先。不要静默删除，先把冲突和合规替代方案告诉用户。
- 不允许用“模拟器能显示”替代合规判断；Builder Hub 模拟器可能渲染最终会被审核拒绝的外链。
- 不做兜底或假数据。联网功能要明确删除或改成真实静态快照。
- 默认在原项目增加独立
xhs-minitool/，不破坏主站。共享数据应在构建时读取唯一真相源，不复制第二份长期维护的数据。 - 最终包先执行当次 Builder Hub 提供的官方 Skill 及其审计脚本，再运行
scripts/validate_package.py。两边任何 error 都不能上传。 - 官方 Skill 只允许检查和修改独立小工具目录或其暂存副本，不得为了小工具合规改写主站。官方检查造成可见功能、内容或布局变化时，必须重新给用户预览确认。
- 二维码若编码站外网址、微信或其他平台入口，技术校验可能通过，但内容审核仍可能视为导流；解码确认后必须在提交摘要里单列风险。
预览与确认
至少验证 390×844 与 320×568，覆盖首屏、核心操作、空结果和详情。检查横向溢出、44px 触控目标、真实长文、中文字体、二维码识别和浏览器控制台。把关键截图直接给用户看，说明为小工具删了什么、保留了什么。
用户要求调整就继续迭代。只有用户明确表示满意或同意发布，才进入 Builder Hub。官方 Skill 门禁若修改了可见成品，应重新截图并取得确认；不得拿修改前的满意结论覆盖修改后的版本。
发布收口
上传前重新构建，记录官方 Skill 版本、官方审计结果、ZIP 大小与 SHA-256。发布后必须回到列表回读名称、版本和状态：
- 仅出现模拟器：已上传预览。
- 列表显示“审核中”并有“撤回”：已提交审核。
- 列表显示“已发布”：已经上线。
- 审核通过后仍未挂载笔记：小工具已上线，但尚未随笔记分发。
What ships with it
7 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.
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.
- 7d ago First seen · 66 lines · 117 tokens per session scan A e5aa6ac93dc6
kevin-xhs-minitool-publisher is a skill published in the GitHub repository 413162826/kevinsu-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 117 tokens to every session and 1,368 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
agent-device
Automates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, collecting evidence, or planning agent-device CLI commands.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
phone-harness
Control the user's phone — iPhone through the Mac's iPhone Mirroring window, or an Android over adb: open apps, tap, type, swipe, read the screen.