Tianshu Harness is a TypeScript runtime for coding agents, with terminal and desktop interfaces that share an agent core for managing goals, state, evidence, permissions, and completion checks. Developers use it to have language models carry out software tasks while the runtime verifies progress through tests, diffs, or other commands. The catalogue entries are skills and instructions for the agent's coding workflow.
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 huiliyi37/Tianshu-harness --skill design-prototypegit clone --depth 1 https://github.com/huiliyi37/Tianshu-harnessWrote 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/huiliyi37/tianshu-harness/design-prototype)<a href="https://agentmods.dev/skills/huiliyi37/tianshu-harness/design-prototype"><img src="https://agentmods.dev/badge/skills/huiliyi37/tianshu-harness/design-prototype/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/huiliyi37/tianshu-harness/design-prototype"><img src="https://agentmods.dev/badge/skills/huiliyi37/tianshu-harness/design-prototype.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00775 |
| Opus 5.5 | $0.00011 | $0.00310 |
| Sonnet 5.5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
design-prototype 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 1mo 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.
What it actually says
Design Prototype（前端设计原型）
对标 Codex Product Design 插件的方法论，适配天枢交付纪律。
工作流
1. 意图澄清（单问约束）
开始动手前，若以下任一项不明，只问一个最关键的问题：
- 目标用户与核心动作（注册？购买？浏览？）
- 品牌调性（极简 / 企业 / playful / 暗色）
- 有无参考（竞品截图、Figma 链接描述、色板）
不要一次抛多个选择题。
2. 探索 2–3 个视觉方向
每个方向输出单文件 HTML 原型：
- 内联 CSS（无构建步骤，即开即预览）
- 语义化 HTML + 基础可访问性（label、alt、focus 可见）
- 真实文案占位（不用 lorem 堆砌——用场景化假数据）
- 移动端优先，desktop 用 media query 扩展
文件命名：prototype-{direction}.html（如 prototype-minimal.html）
3. 多视口自检（必做）
每个方向完成后：
ui_preview— mobile / tablet / desktop 三视口截图ui_responsive_audit— 抓横向溢出、过小点击区、过小字号
有问题先修 HTML，再进入下一步。不要带着 overflow 交付。
4. 参考对齐（有 mockup 时）
用户提供参考图或竞品截图时：
ui_palette— 从参考图提取色板，写入 CSS variables- 实现后
ui_diff— 与参考/mockup 像素对比，目标 mismatch < 5% - mismatch > 5% 必须迭代，不能口头说「差不多」
5. 交付纪律（复现即证明）
交付设计任务时必须附带：
- 至少一组三视口
ui_preview截图路径 ui_responsive_audit结果（零 high 级 issue，或明确列出已知遗留）- 若有参考：最新
ui_diffmismatch 百分比
口头描述「已经 responsive 了」不算交付。
工具速查
| 工具 | 何时用 |
|---|---|
ui_preview |
HTML/URL → 多视口 PNG |
ui_diff |
实现 vs 参考 mockup |
ui_palette |
参考图 → CSS/Tailwind tokens |
ui_responsive_audit |
布局问题清单 + 截图 |
反模式
- 不要跳过 preview 直接改 CSS 猜效果
- 不要用
<table>做整页布局（2020 年代前的 hack） - 不要在未装
tianshu-design插件时会话里调用上述工具——先/plugin install或让用户安装 - Chrome 未安装时工具会返回明确错误；提示用户安装 Chrome 或设置
CHROME_PATH
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.
- 1mo ago First seen · 76 lines · 28 tokens per session scan A 39894b6a1db6
design-prototype is a skill published in the GitHub repository huiliyi37/Tianshu-harness (1,158 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 775 once invoked, about $0.0001 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.
Other skills, from other repositories
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
frontend-design
A design and coding guide for building distinctive web interfaces, including pages, dashboards, landing pages, and reusable components.
prototype-workflow
Generate and lifecycle-manage HTML prototypes for UI exploration and OpenSpec changes. Use when creating, validating, completing, or archiving a UI prototype.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.