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 itssosunny/job-searcher --skill jobkorea-collectgit clone --depth 1 https://github.com/itssosunny/job-searcherWrote 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/itssosunny/job-searcher/jobkorea-collect)<a href="https://agentmods.dev/skills/itssosunny/job-searcher/jobkorea-collect"><img src="https://agentmods.dev/badge/skills/itssosunny/job-searcher/jobkorea-collect/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/itssosunny/job-searcher/jobkorea-collect"><img src="https://agentmods.dev/badge/skills/itssosunny/job-searcher/jobkorea-collect.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 | $0.00067 | $0.00556 |
| Opus 5 | $0.00034 | $0.00278 |
| Sonnet 5 | $0.00013 | $0.00111 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
jobkorea-collect 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 12d 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.
What it actually says
JobKorea Collect
Collect recent public postings from JobKorea's keyword search and return
normalized JSON (docs/SCHEMA.md). Self-contained: this skill's collect.py
carries its own fetch + parse and depends only on curl_cffi, beautifulsoup4,
lxml.
Boundaries
- Read-only. GET of the public search page only. Never log in, save a job, message, or apply. Do not submit any form.
- No fabrication. Fields the source does not expose are
null; titles, companies, salaries, and locations are copied verbatim. - A collected posting reflects the public page at run time; it is not proof the role is still open.
Run
If collect.py fails with ModuleNotFoundError, install the deps yourself
(pip install curl_cffi beautifulsoup4 lxml) and retry — do not ask the user
to install anything.
# one-time deps (or: pip install -r requirements.txt)
pip install curl_cffi beautifulsoup4 lxml
python3 skills/jobkorea-collect/collect.py --query "데이터 엔지니어" --limit 20
--query, -q— search keyword (default개발자).--limit, -n— max postings (default 20).--pretty— indent the JSON.
Output: a JSON array on stdout; a one-line count on stderr. Each item has
source, external_id, url, title, company, location, employment_type, posted_at, deadline, salary, snippet, collected_at.
Notes
- Source:
SRC-JOB-JOBKOREA— https://www.jobkorea.co.kr/ (collectible_open, re-verified 2026-07-07). - Posting detail URLs use the
Recruit/GI_Read/<id>pattern;external_idis that numeric id (stable for dedup). - JobKorea's search markup is a Tailwind card layout (
div.shadow-list); if the layout changes and 0 postings return, re-derive the card/anchor selectors against a live fetch (do not hardcode a specific company).
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.
- 12d ago First seen · 52 lines · 67 tokens per session scan A 9e346b3b3a08
jobkorea-collect is a skill published in the GitHub repository itssosunny/job-searcher (14 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 556 once invoked, about $0.0003 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 skills, from other repositories
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
open-hot-jobs
This skill should be used when the user wants to open hot job listings in Chrome. Triggers on phrases like "open hot jobs", "open [category] hot jobs in chrome", "open all backend jobs", "open jobs in browser", "open [category] jobs chrome".
safari-extension-control-workflow
Guide macOS Safari integration decisions across Safari Web Extensions, Safari Web Inspector Extensions, Safari App Extensions, SafariServices APIs, content blockers, extension messaging, and app-to-Safari control surfaces. Use when the user wants a Mac app to extend, message, open, inspect, debug, or coordinate with…
safari-mcp-workflow
Inspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.
roast-cold-email
A Chinese-language writing guide for composing deliberately restrained cold emails that point out a company’s documented gap. A cold email is an unsolicited message to someone you do not already know.
indeed-full
Complete Indeed job postings toolkit via RolesAPI.com. Search Indeed job postings by keyword and location, fetch full role details, look up salary for a job posting, and get descriptions, company info, and benefits across 60+ country editions.