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 MelonS/MelonS-Agents --skill news-shortgit clone --depth 1 https://github.com/MelonS/MelonS-AgentsWrote 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/melons/melons-agents/news-short)<a href="https://agentmods.dev/skills/melons/melons-agents/news-short"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/news-short/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/melons/melons-agents/news-short"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/news-short.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 | $0.00122 | $0.00851 |
| Opus 5 | $0.00061 | $0.00426 |
| Sonnet 5 | $0.00024 | $0.00170 |
| Haiku 4.5 | $0.00012 | $0.00085 |
Grade A, and why
news-short 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
news-short (뉴스쇼츠)
Turn a current event into a tight, sourced, recency-gated 60-second news recap — with a stricter legal gate than info-short because news carries defamation, accuracy, and freshness risk.
How to invoke
/news-short "<event / headline>"
/news-short "summarize today's <topic> development"
/news-short "<event>" --id=quake0701 --within-days=2
If no event is given, ask. --within-days=N overrides the recency window
(default 3).
What runs (the four teams)
Same four-team flow as info-short, with news-profile differences:
- 리서치팀 — requires ≥2 independent reputable outlets per claim, stamps
recency.newest_source_date, and setsrecency.ok=falseif the story isn't fresh enough. Ifrecency.okis false, the director stops and tells you — stale news is not shipped. - 제작팀 —
--profile=news: tighter 120–150-word wire-service recap, every claim attributed ("according to ..."), plus an "As of<date>" disclosure. - 법률팀 ⇄ 제작팀 — the strict gate. Adds, on top of info checks:
- defamation — no unsourced allegation about a named living person (BLOCK-tier with no fix; otherwise REVISE to soften/attribute/cut).
- fact-accuracy — every narrated claim must trace to a fact source.
- required-disclaimer — the
As of <date>stamp must be present.
- 출시팀 — packages with the freshness note; news should be uploaded the same day it clears.
What it produces
outputs/short.mp4— 1080×1920, ~60s, attributed recap + "As of ".legal/legal-verdict.json— strict gate result + fix list.release/— upload copy (with the as-of line) + thumbnail + checklist.
What it does NOT do
- Ship stale news (recency gate) or unsourced allegations (defamation gate).
- Auto-upload, or write public URLs into the repo.
- Editorialize — neutral recap only; speculation is a REVISE.
See also
docs/content-shorts-pipeline.md— architecture + data contract.- Sibling profiles:
/info-short(정보쇼츠),/idol-short(아이돌쇼츠).
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 · 65 lines · 122 tokens per session scan A cc15e6c78d7f
news-short is a skill published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 18d ago), licensed MIT. It adds 122 tokens to every session and 851 once invoked, about $0.0006 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
hive.image-generation
Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
music-search
Search cloud drives for downloadable music resources (songs, albums, lossless audio). Use this skill when the user wants to download a specific song or album. Do NOT use for general music information, lyrics, or recommendations.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
presentation-builder
OwnPilot official general skill for creating slide outlines, executive narratives, speaker notes, and presentation critiques. Use when the user asks for slides, a deck, a pitch, or a narrative.
nous-branding
Generate images and content consistent with the Nous Research brand identity. Use when creating visuals in the Nous / Theia / Hermes ecosystem: a "cyber-classical" style blending neo-classical statuary, cyberpunk/industrial grunge, and retro anime illustration. Covers official brand color palette, typography…