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 molpass/mcp-weather --skill weathergit clone --depth 1 https://github.com/molpass/mcp-weatherWrote 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/molpass/mcp-weather/weather)<a href="https://agentmods.dev/skills/molpass/mcp-weather/weather"><img src="https://agentmods.dev/badge/skills/molpass/mcp-weather/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/molpass/mcp-weather/weather"><img src="https://agentmods.dev/badge/skills/molpass/mcp-weather/weather.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 | $0.00051 | $0.00375 |
| Opus 5.5 | $0.00020 | $0.00150 |
| Sonnet 5.5 | $0.00010 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
weather 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 yesterday.
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
weather
mcp-weather 서버의 get_weather 도구를 호출해 여러 위치의 오늘 아침/점심/저녁 날씨 + 미세먼지를 가져온다.
도구는 "사실"(예보·측정값), 이 스킬은 "의미"(위치 추출 + 좌표 매핑 + 요약)를 담당한다.
트리거
- "오늘 ○○ 날씨 / 미세먼지"
- "출근길/저녁 날씨", 여러 지역 동시 질의
- 데일리 리포트용 날씨·미세먼지 수집
동작
- 메시지에서 위치 이름을 뽑고 각 위치의 lat/lon(WGS84)을 채운다(알려진 좌표 또는 사용자 제공).
get_weather에locations배열로 한 번에 전달한다.- 위치별 아침/점심/저녁 + 미세먼지를 요약해 보여준다.
주의
- lat/lon은 WGS84. 좌표를 모르면 사용자에게 확인하거나 대표 좌표를 사용한다.
- 결과 일부 실패(날씨 또는 미세먼지)는 해당 줄만 실패로 표기되고 나머지는 정상 출력된다.
- API 키(
KMA_SERVICE_KEY/AIRKOREA_SERVICE_KEY)는 서버 env로 주입된다. 발급 직후면 동기화 지연으로 일시적 키 오류가 날 수 있다.
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.
- yesterday First seen · 28 lines · 51 tokens per session scan A ab3c1a27c81e
weather is a skill published in the GitHub repository molpass/mcp-weather (0 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 375 once invoked, about $0.0002 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 2026-10-16.
Other skills, from other repositories
rust-neckbeard
Dedalus Rust correctness and style rules. Use when writing, reviewing, or refactoring any Rust code in the host-agent, enclave, or packages/rust workspaces. Covers return-value naming, error design, mustuse, visibility, RAII, fail-closed, and all hard limits from style.md and rust.mdx.
reticle-aesthetic
Build landing page sections, hero blocks, and marketing surfaces in the Reticle/Sigil engineering-instrument-grid aesthetic. Use when creating new landing sections, hero components, marketing pages, or when the user says "reticle", "hero", "landing page", "new section", "instrument panel", "grid cell", or wants to…
comment
Write doc comments, module docs, and inline comments that follow Dedalus conventions per language. Loads the canonical style guides from the monorepo. Covers Rust, Python, Go, and TypeScript.
deepsec
Run vercel-labs/deepsec — an agent-powered vulnerability scanner — against any local codebase. Use when Kevin says "deepsec", "security scan", "scan this repo for vulns", "find security bugs in ", "audit for vulnerabilities", "production security review", or before shipping a new service. Performs a regex pre-scan…
frontend-design-taste
Build distinctive frontends that avoid generic AI aesthetics. Provides anti-slop enforcement, variance dials, art direction archetypes, creative arsenal, and performance guardrails. Use when creating new landing pages, UI components, design systems, or when the user says "make it look good", "design direction", "avoid…
generate-interface
Define or refactor subsystem interfaces into small, explicit contracts with clear ownership, narrow scope, stable semantics, and README-first documentation. Use when designing a new API, collapsing ad hoc module boundaries into a few coherent interfaces, hardening internal contracts, or rewriting subsystem docs so…