Borrowing it
Nothing to install: this file belongs to huifer/claude-code-interview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/huifer/claude-code-interview/main/.claude/commands/interview/simulate.mdgit clone --depth 1 https://github.com/huifer/claude-code-interviewWrote 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/huifer/claude-code-interview/simulate)<a href="https://agentmods.dev/commands/huifer/claude-code-interview/simulate"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-interview/simulate/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/huifer/claude-code-interview/simulate"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-interview/simulate.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 | $0.00008 | $0.01502 |
| Opus 5.5 | $0.00003 | $0.00601 |
| Sonnet 5.5 | $0.00002 | $0.00300 |
| Haiku 4.5 | $0.00001 | $0.00150 |
Grade A, and why
simulate 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
模拟面试
启动 $1 的 $2 模拟面试。
参数说明
- company-name: 必需,目标公司名称
- interview-type: 必需,面试类型
technical- 技术面试(编码)system-design- 系统设计behavioral- 行为面试hr- HR面试onsite- 完整onsite模拟
- duration: 可选,面试时长(分钟),默认45
工作流程
步骤 1: 面试准备
读取公司和用户信息:
- 公司和职位信息
- JD分析结果
- 用户简历和技能
- 历史面试记录
步骤 2: 面试设置
- 确认面试类型和时长
- 说明面试规则
- 设置计时器
步骤 3: 开始面试
使用 interview-coach Skill 进行模拟面试:
- 扮演面试官
- 提问并追问
- 记录回答
- 计时提醒
步骤 4: 面试评估
- 分析回答质量
- 识别优势和不足
- 提供改进建议
- 评分(1-5分制)
步骤 5: 保存记录
创建 data/interviews/{date}_{company}_{type}.json
面试类型详解
Technical Interview (技术面试)
形式: 编程题 时长: 45分钟 流程:
- 介绍问题 (2分钟)
- 讨论方案 (5分钟)
- 编写代码 (20分钟)
- 测试优化 (10分钟)
- 追问讨论 (8分钟)
评估维度:
- 问题理解 (5分)
- 方案设计 (5分)
- 代码质量 (5分)
- 优化能力 (5分)
- 沟通表达 (5分)
System Design Interview (系统设计)
形式: 架构设计 时长: 45-60分钟 流程:
- 理解需求 (5分钟)
- 高层设计 (10分钟)
- 详细设计 (20分钟)
- 讨论trade-offs (10分钟)
- 总结 (5分钟)
评估维度:
- 需求理解 (5分)
- 架构设计 (5分)
- 可扩展性 (5分)
- 可靠性 (5分)
- 讨论深度 (5分)
Behavioral Interview (行为面试)
形式: STAR问题 时长: 30-45分钟 流程:
- 提问 (每个问题3-5分钟)
- 倾听回答
- 追问细节
- 评估反馈
评估维度:
- STAR结构 (5分)
- 故事相关性 (5分)
- 成果量化 (5分)
- 沟通清晰 (5分)
- 文化匹配 (5分)
HR Interview (HR面试)
形式: 问答 时长: 30分钟 流程:
- 自我介绍 (2分钟)
- 职业规划 (5分钟)
- 为什么选我们 (5分钟)
- 薪资期望 (5分钟)
- 其他问题 (10分钟)
- 反向提问 (5分钟)
面试记录格式
{
"interview_id": "int_001",
"company_id": "$1",
"position_id": "...",
"interview_date": "2025-01-09T14:00:00Z",
"interview_type": "$2",
"round": 1,
"duration_minutes": $ARGUMENTS,
"questions_asked": [
{
"question_id": "q_001",
"type": "coding|system_design|behavioral",
"question": "问题描述",
"difficulty": "medium",
"time_allocated": 20,
"user_response": {
"approach": "解题思路",
"code_written": true,
"time_taken": 18
},
"interviewer_feedback": "代码结构清晰,但可以进一步优化",
"rating": 4
}
],
"overall_feedback": {
"strengths": ["编码能力强", "沟通好"],
"areas_for_improvement": ["需要加强DP"],
"next_steps": ["练习更多DP题"]
},
"overall_rating": 3.8
}
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.
- 2mo ago First seen · 207 lines · 8 tokens per session scan A 959bc6603061
simulate is a command published in the GitHub repository huifer/claude-code-interview (27 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 1,502 once invoked, about $0.0000 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.
simulate compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| simulatehuifer/claude-code-interview | Command | 27 | 10mo ago | MIT | A | 8 | Claude Code |
| learn-story-flowIntai/story-flow | Command | 16 | 2d ago | MIT | A | 10 | Claude Code |
| start-10-1minicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| start-0-8minicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| setup-m365cli.esminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 8 | Claude Code |
| prep-rolefourleafai/clover-public | Command | 8 | 1mo ago | MIT | A | 0 | Claude Code |
| setup-vercel.esminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | B | 2 | Claude Code |