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 kyopark2014/agent-manus --skill korea-weathergit clone --depth 1 https://github.com/kyopark2014/agent-manusWrote 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/kyopark2014/agent-manus/korea-weather)<a href="https://agentmods.dev/skills/kyopark2014/agent-manus/korea-weather"><img src="https://agentmods.dev/badge/skills/kyopark2014/agent-manus/korea-weather/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/kyopark2014/agent-manus/korea-weather"><img src="https://agentmods.dev/badge/skills/kyopark2014/agent-manus/korea-weather.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 | $0.00099 | $0.01465 |
| Opus 5 | $0.00049 | $0.00732 |
| Sonnet 5 | $0.00020 | $0.00293 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
korea-weather scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
mem = subprocess.run(["python", RECALL], capture_output=True, text=True) How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Korea Weather
기상청 날씨누리(weather.go.kr) 행정동 단위 동네예보·현재날씨와 에어코리아 대기질을 조회합니다.
When to Use
- 한국 날씨 / 기온 / 강수 / 습도 / 바람 문의
- 미세먼지·초미세먼지 등 대기질 문의
- 지역명을 주지 않은 "날씨 알려줘", "우산 필요해?" 류 요청
- 특정 동·구·시 날씨 (예: 반포3동, 서초구, 부산 해운대)
Script Location
application working directory 기준 전체 경로를 사용하세요.
| 스크립트 | 용도 |
|---|---|
skills/korea-weather/scripts/recall_home_location.py |
지역명 미지정 시 memory에서 집/거주 주소 조회 |
skills/korea-weather/scripts/get_weather.py |
기상청 동네예보·현재날씨·대기질 조회 |
IMPORTANT: scripts/...로 줄이지 말고 위 전체 경로를 사용하세요.
Critical Rules
- 지역명이 없으면 먼저 memory로 집/거주 주소를 조회하세요.
python skills/korea-weather/scripts/recall_home_location.py- 주소가 나오면 그 값으로
get_weather.py를 실행하세요. LOCATION_NOT_FOUND이면get_weather.py를 location 없이 실행해 IP 대략 위치를 시도하세요.- 먼저 사용자에게 지역을 묻지 마세요.
- 주소가 나오면 그 값으로
- 위치 해석 순서: memory(집 주소) → 공인 IP 대략 위치 →
LOCATION_NEEDED - 결과가
LOCATION_NEEDED로 시작하면 그때만 지역명을 물어보세요. 도시를 임의로 지어내지 마세요. - 사용자 답변에서 기온·강수확률·습도 등에
**/*마크다운 강조를 쓰지 마세요. 예:최고 30℃,강수확률 60%. - 그래프·이미지를 만들지 마세요. 텍스트 요약 + 표 + 링크만 전달하세요.
Quick Start
지역명 없음 → memory 먼저
# 1) memory에서 집/거주 주소
loc=$(python skills/korea-weather/scripts/recall_home_location.py)
# 2) 주소가 있으면 그 지역으로 날씨 조회
if [ "$loc" != "LOCATION_NOT_FOUND" ]; then
python skills/korea-weather/scripts/get_weather.py "$loc"
else
# memory 실패 시 IP 폴백(스크립트 내부)
python skills/korea-weather/scripts/get_weather.py
fi
JSON 상세 결과:
python skills/korea-weather/scripts/recall_home_location.py --json
현재 위치 별칭(스크립트 내부 memory→IP)
python skills/korea-weather/scripts/get_weather.py "현재위치"
지역명 지정
python skills/korea-weather/scripts/get_weather.py "서울 서초구 반포3동"
python skills/korea-weather/scripts/get_weather.py "부산 해운대"
python skills/korea-weather/scripts/get_weather.py "제주"
예보구역 stnId
python skills/korea-weather/scripts/get_weather.py --stnid 109
| stnId | 대표 지역 |
|---|---|
| 108 / 109 | 서울·인천·경기 |
| 105 | 강원 |
| 131 | 충북 |
| 133 | 대전·세종·충남 |
| 146 | 전북 |
| 156 | 광주·전남 |
| 143 | 대구·경북 |
| 159 | 부산·울산·경남 |
| 184 | 제주 |
What ships with it
2 files 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 · 161 lines · 99 tokens per session scan A 1fb1304b41d5
korea-weather is a skill published in the GitHub repository kyopark2014/agent-manus (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,465 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
minimax-multimodal-toolkit
MiniMax multimodal model skill — use MiniMax Multi-Modal models for speech, music, video, and image. Create voice, music, video, and images with MiniMax AI: TTS (text-to-speech, voice cloning, voice design, multi-segment), music (songs, instrumentals), video (text-to-video, image-to-video, start-end frame, subject…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
minimax-docx
Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or…
minimax-pdf
Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the…
minimax-xlsx
Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new xlsx from scratch, reading and analyzing…
pptx-generator
Generate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. Triggers: PPT, PPTX, PowerPoint, presentation, slide, deck, slides.