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 skills add DJH-001/multi-agent-job-search --skill docsgit clone --depth 1 https://github.com/DJH-001/multi-agent-job-searchWrote 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/skills/djh-001/multi-agent-job-search/docs)<a href="https://agentmods.dev/skills/djh-001/multi-agent-job-search/docs"><img src="https://agentmods.dev/badge/skills/djh-001/multi-agent-job-search/docs/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/skills/djh-001/multi-agent-job-search/docs"><img src="https://agentmods.dev/badge/skills/djh-001/multi-agent-job-search/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.09073 |
| Opus 5 | $0.00000 | $0.04536 |
| Sonnet 5 | $0.00000 | $0.01815 |
| Haiku 4.5 | $0.00000 | $0.00907 |
Grade A, and why
docs 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 9d 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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill was originally deployed on the OpenCode agent platform as a domain behavior specification. It defines the complete rule system that the Python implementation in
src/follows. The rules were validated across 16+ real job application workflows.
name: job-search description: "Use this skill for ANY job-search / 求职 task for candidate [anonymized]: preparing for an interview, tailoring a resume for a specific company/role, recording application progress, updating job status, researching a target company/JD, writing interview Q&A or PPT, or managing the overall job hunt. Triggers include mentions of: 求职, 找工作, 投简历, 面试准备, 简历优化, 某公司岗位准备 (e.g. 某半导体公司/某相机公司/etc), 内推, offer, 岗位分析, or any request to create/update materials under the job-search archive. This skill enforces using the candidate's verified personal data as the single source of truth, isolates per-company preparation, and maintains progress tracking. Do NOT use for unrelated coding/document tasks that are not about this candidate's job search."
求职管理系统（job-search）
这个 skill 是什么
把 AI 变成[anonymized]的"求职指挥中心"。所有求职工作（简历、面试准备、进度管理）都在统一规则下进行：基于真实个人信息、岗位之间隔离、状态持续记录。
文件库根目录
D:\JobSearch\ —— 所有求职文件的归档总目录。结构：
D:\JobSearch\
├── README.md # 总索引 + 求职状态看板 + 个人核心档案速查
├── 00_个人素材库\ # ⭐ 真相源（Single Source of Truth）
│ ├── 原始资料\ # 个人信息MyInfor、入职版简历PDF、工作概述
│ ├── STAR弹药库.md # 提炼好的可复用案例
│ ├── 母版CV\ # Master-CV.md、摘要库.md、派生记录.md
│ ├── 成长时间线\ # 学习日志、晋级登记、新项目/练习项目证据
│ ├── _模板\ # 岗位分析、面经、面试准备/复盘模板
│ └── 通用话术\ # 被裁话术/薪资谈判/技术面试题库（跨公司复用）
├── 01_公司岗位\ # 每个岗位一个文件夹，独立管理
│ └── {公司}-{岗位}\
│ ├── 面经情报.md # 该岗位面试情报收集
│ ├── JD-岗位要求.pdf
│ ├── 岗位分析与匹配度.md
│ ├── 简历-终版\ # 对外发送的定稿
│ ├── 面试准备\ # 第N轮-准备.md / 第N轮-复盘.md
│ ├── 面试问答准备.md / 面试PPT.pptx
│ ├── 进度跟踪.md # 该岗位的投递/面试/状态/待办
│ └── _历史版本\ # 简历中间版本归档
└── 02_市场调研\ # 跨公司的市场情报
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 431 lines · 0 tokens per session scan A a9510d4ea0ef
docs is a skill published in the GitHub repository DJH-001/multi-agent-job-search (19 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 9,073 tokens. 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 skills, from other repositories
new-job
This skill should be used when the user wants to add a new company or job to their Excel tracker (List.xlsx). Triggers on phrases like "add [company] to tracker", "I applied to [company]", "track [company]", "save [company] for later", "add [company] [role]", "new application at [company]".
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.