prep

A customized interview-preparation guide based on a company, its job description, and optionally a specific interview type.

In plain words
What is it for?
Use it to prepare for coding, system-design, behavioral, or HR interviews with company-specific technical, cultural, and practice guidance.
Why use it?
It turns company requirements into prioritized study topics, practice questions, preparation tasks, and a time plan instead of leaving you to organize everything yourself.

Command for Claude Code

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/huifer/claude-code-interview/prep
Clone the repo
git clone --depth 1 https://github.com/huifer/claude-code-interview

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,093 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 $0.00007 $0.01093
Opus 5 $0.00003 $0.00547
Sonnet 5 $0.00001 $0.00219
Haiku 4.5 $0.00001 $0.00109

Measured 2d ago against content hash 699b06de6798, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prep 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 2d 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/interview/prep.md · 178 lines

What it actually says

面试准备指南

$1 生成定制化面试准备指南。

参数说明

  • company-name: 必需,目标公司名称
  • interview-type: 可选,面试类型
    • technical - 技术面试
    • system-design - 系统设计
    • behavioral - 行为面试
    • hr - HR面试
    • 省略则生成全面准备指南

工作流程

步骤 1: 分析公司和JD

读取 data/companies/$1.json

  • 提取关键技能
  • 识别技术栈
  • 了解面试流程
  • 分析公司文化

步骤 2: 识别准备重点

基于JD和公司特点:

  • 技术主题清单
  • 优先级排序
  • 时间估算

步骤 3: 推荐练习题

使用 question-generator Skill:

  • 生成相关技术题
  • 推荐系统设计题
  • 准备行为面试题

步骤 4: 生成准备指南

创建 exports/interview-guides/$1_prep_guide.md

准备指南结构

# $1 面试准备指南

生成时间: {当前时间}
目标职位: {职位名称}

## 面试流程概览
{面试各阶段}

## 技术准备清单

### 高优先级 (必须掌握)
- [ ] {主题1} - 预计{X}小时
- [ ] {主题2} - 预计{X}小时

### 中优先级 (建议掌握)
- [ ] {主题3} - 预计{X}小时

### 低优先级 (加分项)
- [ ] {主题4} - 预计{X}小时

## 推荐练习题

### 算法和数据结构
1. {题目1} - {难度} - {频率}
2. {题目2} - {难度} - {频率}

### 系统设计
1. {题目1} - {公司常见}
2. {题目2} - {相关度}

### 行为面试 (STAR)
1. {问题1} - {能力}
2. {问题2} - {能力}

## 公司特定准备

### 技术重点
- {该公司重视的技术}
- {面试风格}

### 文化匹配
- {公司价值观}
- {行为特质}

### 已知问题
- {历年高频题}
- {该公司特色题}

## 时间规划

### 距离面试还有{X}天
**每日任务**:
- Day 1-3: {任务}
- Day 4-7: {任务}

### 每日时间分配
- 上午 (2h): {主题}
- 下午 (2h): {主题}
- 晚上 (1h): {主题}

## 学习资源
- {推荐资源}
- {练习平台}
- {参考文档}

## 模拟面试
- /interview/simulate $1 technical
- /interview/simulate $1 system-design
- /interview/simulate $1 behavioral

## 最后提醒
- {重要提示}
- {注意事项}

示例输出片段

Google 技术准备

## 高优先级技术主题

### 1. 分布式系统 (8h)
**重点**:
- CAP定理
- 一致性算法
- 分布式事务
- 数据分片

**推荐练习**:
- 设计URL短链服务
- 设计分布式缓存
- 设计分布式锁

**资源**:
- DDIA - Designing Data-Intensive Applications
- Google系统设计论文

### 2. 算法和数据结构 (6h)
**重点**:
- 图算法
- 动态规划
- 树遍历
- 哈希表

**推荐题目**:
- LRU Cache (Medium)
- Merge K Sorted Lists (Hard)
- Word Ladder (Medium)

### 3. Python深入 (4h)
**重点**:
- GIL
- 内存管理
- 装饰器
- 生成器

## Google已知问题
1. 设计一个URL缩短服务 ⭐⭐⭐
2. 实现LRU缓存 ⭐⭐⭐
3. 设计一个键值存储 ⭐⭐
4. 解释MapReduce ⭐⭐

输出文件

保存到: exports/interview-guides/{company}_prep_guide.md

下一步

  1. 查看准备指南
  2. 制定学习计划
  3. 开始每日练习
  4. 定期模拟面试
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. 2d ago First seen · 178 lines · 7 tokens per session scan A 699b06de6798

Subscribe to this mod's changes

prep is a command published in the GitHub repository huifer/claude-code-interview (23 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 1,093 once invoked, about $0.0000 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.