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 serejaris/kimi-skills --skill interface-design-labgit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/interface-design-lab)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/interface-design-lab"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/interface-design-lab/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/serejaris/kimi-skills/interface-design-lab"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/interface-design-lab.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 | $0.00093 | $0.00973 |
| Opus 5 | $0.00046 | $0.00487 |
| Sonnet 5 | $0.00019 | $0.00195 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
interface-design-lab 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 9d 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
接口形态探索
基于《软件设计哲学》中的"设计两次"原则：你的第一个方案不太可能是最好的。先生成多种截然不同的设计，再加以比较。
工作流程
1. 收集需求
在开始设计之前，先了解以下信息：
- 这个模块要解决什么问题？
- 谁会调用它？（其他模块、外部用户、测试代码）
- 核心操作有哪些？
- 有什么约束条件？（性能、兼容性、现有模式）
- 哪些内容应该封装在内部，哪些需要暴露？
关键问题："这个模块需要做什么？谁会用到它？"
2. 生成设计方案（并行子代理）
同时启动 3 个以上的子代理（使用 Task 工具），每个子代理必须产出一种截然不同的设计方案。
每个子代理的提示词模板：
为以下模块设计接口：[模块描述]
需求：[已收集的需求]
本设计的约束条件：[为每个代理分配不同的约束]
- 代理 1："方法数量最少——目标 1-3 个方法"
- 代理 2："灵活性最大——支持尽可能多的使用场景"
- 代理 3："为最常见场景优化"
- 代理 4："借鉴 [特定范式/库] 的思路"
输出格式：
1. 接口签名（类型/方法）
2. 使用示例（调用方如何使用）
3. 该设计在内部隐藏了什么
4. 该方案的优劣权衡
3. 展示设计方案
每个方案需展示：
- 接口签名 - 类型、方法、参数
- 使用示例 - 调用方在实际场景中如何使用
- 封装内容 - 内部隐藏了哪些复杂性
逐个展示方案，让用户充分理解每种思路后再进行对比。
4. 对比方案
展示完所有方案后，从以下维度进行对比：
- 接口简洁性：方法越少、参数越简单，越容易学习和正确使用
- 通用性 vs 专用性：灵活度与专注度的取舍
- 实现效率：接口形态是否有利于高效实现？还是会导致内部结构别扭？
- 深度：小接口封装大量复杂性 = 深模块（好）；大接口背后实现单薄 = 浅模块（应避免）
- 易用性 vs 误用风险
用文字讨论权衡取舍，而非表格。重点指出各方案分歧最大的地方。
5. 综合提炼
最佳方案往往融合了多种设计的优点。可以问用户：
- "哪个方案最贴合你的主要使用场景？"
- "其他方案中有没有值得借鉴的元素？"
评价标准
出自《软件设计哲学》：
接口简洁性：方法越少、参数越简单 = 越容易学习、越不容易用错。
通用性：能够应对未来的使用场景而无需修改。但要警惕过度泛化。
实现效率：接口形态是否有利于高效实现？还是会迫使内部结构变得别扭？
深度：小接口封装大量复杂性 = 深模块（好）。大接口背后实现单薄 = 浅模块（应避免）。
反模式
- 不要让子代理产出相似的方案——必须确保方案之间有本质差异
- 不要跳过对比环节——价值就在于方案之间的碰撞
- 不要动手实现——这一步只关注接口形态
- 不要以实现难度作为评价标准
What ships with it
1 file 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.
- 9d ago First seen · 95 lines · 93 tokens per session scan A fc4b24dea7b2
interface-design-lab is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 973 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
offensive-api-abuse
Advanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that bypass traditional security controls. Covers business logic bypass through API call chaining and workflow manipulation. Addresses GraphQL-specific attacks including batching for credential brute-force, query…
offensive-graphql
Offensive methodology for attacking GraphQL APIs during penetration tests and bug bounty engagements. Covers the full attack lifecycle: endpoint discovery, introspection abuse and blind schema reconstruction when introspection is disabled, authentication and authorization bypass through Relay node IDs and nested…
agent-ready-auth-md
Sub-skill: Implement Auth.md for agent registration discovery. Serve /auth.md with OAuth metadata at /.well-known/oauth-protected-resource and authorization server endpoints.
agent-ready-dns-aid
Sub-skill: Implement DNS-AID records so agents discover endpoints through DNS. Use SVCB/HTTPS records under agents namespace with alpn and connection parameters.
agent-ready-link-headers
Sub-skill de agent-ready-cloudflare: Implement Link Response Headers.
agent-ready-markdown-negotiation
Sub-skill de agent-ready-cloudflare: Implement Markdown Content Negotiation.