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.
git clone --depth 1 https://github.com/KimYx0207/Kim_ServiceWrote 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/commands/kimyx0207/kim_service/kim-form)<a href="https://agentmods.dev/commands/kimyx0207/kim_service/kim-form"><img src="https://agentmods.dev/badge/commands/kimyx0207/kim_service/kim-form/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/commands/kimyx0207/kim_service/kim-form"><img src="https://agentmods.dev/badge/commands/kimyx0207/kim_service/kim-form.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 | $0.00024 | $0.01354 |
| Opus 5.5 | $0.00010 | $0.00542 |
| Sonnet 5.5 | $0.00005 | $0.00271 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
kim-form scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- kim-form — 89% identical, 17 lines differ
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kim Service 执行门(必须先执行)
- 先复述原始用户意图,并列出本次计划调用的 MCP 工具、目标目录和拟新增或修改的文件;不要把本命令扩展成 Router 或自动验收流程。
- 任何项目写入、依赖安装、外部访问或环境变更都必须先获得对应的人类批准。未批准时只分析并展示计划。
- 写入前读取现有目标;目标已存在时不得用重定向、空文件或整文件覆盖。只做受管更新,遇到冲突停止并展示差异。
- 新文件只能在已批准的项目根目录内安全创建;不得写用户级配置。MCP 仅使用本 Tool 的 cli.mjs mcp codex 或 cli.mjs mcp gemini 运行时及其已注册工具。
Kim表单生成命令
输入字段和校验规则,生成完整的表单组件(React/Vue + 校验 + 样式)
你现在要生成表单组件:$ARGUMENTS
模式说明:专门生成前端表单组件,自动处理校验、样式、提交逻辑。
执行流程
阶段1:分析表单需求
解析用户输入,提取:
- 表单名称:如
LoginForm、UserProfile - 字段列表:字段名、类型、校验规则
- 提交地址:API端点
- 框架选择:React/Vue(检测项目)
如果信息不完整,询问用户:
📝 请补充表单信息:
1. 表单名称:用户注册表单
2. 字段列表:
- username: 文本, 必填, 4-20字符, 字母数字下划线
- email: 邮箱, 必填, 邮箱格式
- password_field: 密码, 必填, 8位以上, 含字母数字
- confirm_password_field: 密码, 必填, 与password_field一致
- agreeTerms: 复选框, 必填
3. 提交地址:/api/register
4. 成功后:跳转登录页
请确认或修改:
阶段2:检测前端框架
使用Glob检测项目使用的前端框架:
# 检测React
ls package.json 2>/dev/null | xargs grep -l "react"
# 检测Vue
ls package.json 2>/dev/null | xargs grep -l "vue"
# 检测UI库
grep -E "antd|@mui|element-plus|naive-ui" package.json 2>/dev/null
阶段3:调用Codex生成组件
使用MCP工具调用Codex生成表单组件:
React模板:
生成内容:
1. 表单组件(React Hook Form / Formik)
2. 校验Schema(Zod / Yup)
3. 样式文件(Tailwind / CSS Modules)
4. 类型定义(TypeScript)
Vue模板:
生成内容:
1. 表单组件(Vue 3 Composition API)
2. 校验规则(VeeValidate / Element Plus rules)
3. 样式文件
4. 类型定义
阶段4:输出结果
# 表单生成结果:{表单名称}
## 表单预览
| 字段 | 类型 | 校验规则 |
|------|------|----------|
| username | 文本输入 | 必填, 4-20字符 |
| email | 邮箱输入 | 必填, 邮箱格式 |
| password_field | 密码输入 | 必填, 8位以上 |
| confirm_password_field | 密码输入 | 必填, 密码一致 |
| agreeTerms | 复选框 | 必须勾选 |
## 生成的文件
1. `components/RegisterForm.tsx` - 表单组件
2. `schemas/register.ts` - 校验Schema
3. `types/register.ts` - 类型定义
## 使用方法
```tsx
import RegisterForm from '@/components/RegisterForm';
function RegisterPage() {
return <RegisterForm onSuccess={() => router.push('/login')} />;
}
生成的代码
[代码内容...]
---
## 使用示例
```bash
# 基础用法
/kim-form "登录表单:用户名、密码、记住我"
# 详细描述
/kim-form "用户资料编辑表单:昵称必填、头像上传、性别单选、生日日期选择、个人简介文本域"
# 复杂表单
/kim-form "订单表单:收货人、手机号(11位)、省市区级联、详细地址、发票信息可选"
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 · 169 lines · 24 tokens per session scan A 6081f4126d8f
kim-form is a command published in the GitHub repository KimYx0207/Kim_Service (177 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 1,354 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 2026-09-14.
Other commands, from other repositories
scaffold-desktop
Scaffold a desktop application using Electron or Tauri with proper project structure.
component-gen
Generate React or Vue components with prop types, styling, accessibility, and tests.
dare-frontend-design
Arquitetura frontend DARE para projetos React e Vue. Detecta god components, fetch inline em JSX/template, e gera scaffold DARE-compliant.
prototype-loop
Enter leveraged-prototype focus mode — focus marker plus normal watch/rebuild loop for visual-parity work and batch upstream framework gap-fixes.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.