kim-api

kim-api is a command for Claude Code from KimYx0207/Claudecode-Codex-Gemini. It costs 24 tokens per session (1,018 once invoked), scanned A, original, MIT.

A command that generates one API endpoint from a written description, including its route, input checks, response structure, error handling, and API documentation comments. An API endpoint is a specific URL and method that software uses to exchange data.

In plain words
What is it for?
Use it for custom GET, POST, PUT, or DELETE endpoints such as sending verification codes or resetting passwords.
Why use it?
It turns an incomplete endpoint idea into the connected pieces needed for implementation and documentation. It also checks the existing project structure before generating code.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Install

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.

agentmods
npx agentmods add commands/kimyx0207/claudecode-codex-gemini/kim-api
Clone the repo
git clone --depth 1 https://github.com/KimYx0207/Claudecode-Codex-Gemini

Made for: Claude Code.

Wrote 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.

agentmods badge for kim-api

README.md
[![agentmods](https://agentmods.dev/badge/commands/kimyx0207/claudecode-codex-gemini/kim-api.svg)](https://agentmods.dev/commands/kimyx0207/claudecode-codex-gemini/kim-api)
Your own site
<a href="https://agentmods.dev/commands/kimyx0207/claudecode-codex-gemini/kim-api"><img src="https://agentmods.dev/badge/commands/kimyx0207/claudecode-codex-gemini/kim-api.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,018 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01018
Opus 5 $0.00012 $0.00509
Sonnet 5 $0.00005 $0.00204
Haiku 4.5 $0.00002 $0.00102

Measured 6d ago against content hash d5f005084c9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kim-api 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 6d 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.

.claude/commands/kim-api.md · 165 lines

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.

Kim API生成命令

输入接口需求,生成完整API端点:路由、参数校验、错误处理、文档注释

你现在要生成API端点:$ARGUMENTS

模式说明:专门生成单个API端点,比CRUD更灵活,适合非标准接口。

执行流程

阶段1:分析接口需求

解析用户输入,提取:

  • 接口名称:如 sendVerificationCoderesetPassword
  • HTTP方法:GET/POST/PUT/DELETE
  • 请求参数:Query/Body/Path参数
  • 响应格式:返回数据结构
  • 业务逻辑:核心处理逻辑

如果信息不完整,询问用户:

📝 请补充接口信息:

1. 接口名称:发送验证码
2. HTTP方法:POST(推荐)
3. 请求参数:
   - email: string, 必填, 邮箱格式
   - type: string, 可选, 验证码类型(register/reset)
4. 响应格式:
   - success: boolean
   - message: string
   - expire_in: number (秒)

请确认或修改:

阶段2:检测项目结构

使用Glob检测项目现有的API结构:

# 查找现有路由文件
ls src/routers/ src/routes/ src/api/ routes/ 2>/dev/null

# 查找现有的Schema/Validator
ls src/schemas/ src/validators/ 2>/dev/null

遵循现有项目结构和命名规范

阶段3:调用Codex生成代码

使用MCP工具调用Codex生成完整API:

生成内容:
1. 路由定义(含路径、方法、描述)
2. 请求参数Schema(含校验规则)
3. 响应模型Schema
4. Service层业务逻辑
5. 错误处理
6. API文档注释(OpenAPI格式)

阶段4:输出结果

# API生成结果:{接口名称}

## 接口信息

| 属性 | 值 |
|------|-----|
| 路径 | POST /api/verification/send |
| 描述 | 发送验证码到指定邮箱 |
| 认证 | 不需要 |
| 限流 | 60秒/次 |

## 请求参数

```json
{
  "email": "[email protected]",  // 必填,邮箱格式
  "type": "register"            // 可选,默认register
}

响应格式

成功 (200)

{
  "data": {
    "success": true,
    "message": "验证码已发送",
    "expire_in": 300
  },
  "error": null
}

失败 (400/429)

{
  "data": null,
  "error": {
    "code": "RATE_LIMITED",
    "message": "请求过于频繁,请60秒后重试"
  }
}

生成的代码文件

[代码内容...]


---

## 使用示例

```bash
# 基础用法
/kim-api "发送验证码接口,参数email和type"

# 详细描述
/kim-api "用户头像上传接口,POST方法,接收multipart/form-data,限制5MB,返回图片URL"

# 复杂逻辑
/kim-api "订单支付回调接口,验证签名,更新订单状态,发送通知"

支持的接口类型

类型 示例 特点
查询接口 搜索、筛选、统计 GET + Query参数
操作接口 发送、提交、触发 POST + Body参数
上传接口 文件上传 multipart/form-data
回调接口 支付、Webhook 签名验证
聚合接口 仪表盘数据 多数据源整合

适用场景

适合使用 /kim-api

  • 非标准的业务接口
  • 需要复杂参数校验
  • 第三方集成接口
  • 单个功能端点

不适合

  • 标准CRUD → /kim-crud
  • 大量相关接口 → /kim-code
  • 复杂系统 → /kim-team

Read the full file on GitHub · 165 lines

Changes

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.

  1. 6d ago First seen · 165 lines · 24 tokens per session scan A d5f005084c9b

Subscribe to this mod's changes

kim-api is a command published in the GitHub repository KimYx0207/Claudecode-Codex-Gemini (119 stars, last pushed 24d ago), licensed MIT. It adds 24 tokens to every session and 1,018 once invoked, about $0.0001 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.