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 agentmods add commands/huifer/claude-code-interview/jd-importgit clone --depth 1 https://github.com/huifer/claude-code-interviewWhat 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 | $0.00040 | $0.03504 |
| Opus 5 | $0.00020 | $0.01752 |
| Sonnet 5 | $0.00008 | $0.00701 |
| Haiku 4.5 | $0.00004 | $0.00350 |
Grade A, and why
jd-import 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.
How it starts
The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能JD导入
智能导入职位描述(JD),支持多种来源和格式。
使用方法
从URL导入单个JD
# 从LinkedIn导入
/jd/import https://www.linkedin.com/jobs/view/123456789/
# 从Indeed导入
/jd/import https://www.indeed.com/viewjob?jk=123456789
# 从公司官网导入
/jd/import https://careers.google.com/jobs/results/123456/
从文件导入JD
# 从文本文件导入
/jd-import ~/Downloads/google-jd.txt
# 从Markdown文件导入
/jd-import ~/Downloads/amazon-jd.md
# 从Word文档导入
/jd-import ~/Downloads/meta-jd.docx
批量导入
# 批量导入多个URL
/jd-import --batch ~/jd-urls.txt
# 批量导入目录中的所有JD文件
/jd-import --batch-dir ~/Downloads/jds/
# 从CSV导入
/jd-import --csv ~/job-applications.csv
交互式导入
# 交互式粘贴JD
/jd-import --interactive
# 然后粘贴JD文本
支持的平台
1. LinkedIn
URL格式:
https://www.linkedin.com/jobs/view/[job-id]/
https://www.linkedin.com/jobs/search/?keywords=...
提取内容:
- ✅ 职位名称和级别
- ✅ 公司和团队信息
- ✅ 职位描述全文
- ✅ 技能要求
- ✅ 职位详情(地点、类型、级别)
- ⚠️ 薪资信息(如果提供)
处理方式:
- 读取LinkedIn页面
- 提取职位详情区域
- 清理HTML标签
- 结构化存储
2. Indeed
URL格式:
https://www.indeed.com/viewjob?jk=[job-id]
https://www.indeed.com/company/[company-name]/jobs
提取内容:
- ✅ 完整职位描述
- ✅ 公司信息
- ✅ 职位类型和地点
- ✅ 薪资范围(常见)
3. Glassdoor
URL格式:
https://www.glassdoor.com/job-listing/[job-title]-[company]-JI.htm
提取内容:
- ✅ 职位描述
- ✅ 薪资估算
- ✅ 公司评价和评分
4. 公司官网
URL格式:
https://careers.company.com/jobs/123456
https://jobs.company.com/position/123456
https://www.company.com/careers/openings/...
处理方式:
- 自动检测常见ATS系统(Workday, Greenhouse, Lever)
- 针对性提取内容
- 保存原始链接
5. 招聘网站
支持:
- Boss直聘 (bosszhipin.com)
- 拉勾网 (lagou.com)
- 猎聘 (liepin.com)
- 其他本地招聘平台
导入流程
步骤 1: 检测来源类型
# 分析输入类型
URL? → 自动检测平台
File? → 读取文件内容
Text? → 直接处理
步骤 2: 获取JD内容
# URL方式
使用 webReader MCP 工具:
- 读取网页内容
- 转换为Markdown
- 提取职位信息
# 文件方式
- 读取文件内容
- 检测格式(.txt, .md, .html, .docx)
- 解析文本
步骤 3: 提取关键信息
{
"extraction": {
"company_name": "自动检测或手动确认",
"position_title": "从JD提取",
"position_level": "从JD推断 (Junior/Mid/Senior/Staff)",
"location": "提取工作地点",
"description": "清理后的完整JD文本",
"salary": "提取薪资信息(如果存在)",
"skills": "技能列表"
}
}
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.
- 2d ago First seen · 560 lines · 40 tokens per session scan A 5bf002167f58
jd-import is a command published in the GitHub repository huifer/claude-code-interview (23 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 3,504 once invoked, about $0.0002 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.