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 idol-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/idol-short)<a href="https://agentmods.dev/skills/melons/melons-agents/idol-short"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/idol-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/idol-short"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/idol-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 | $0.00148 | $0.01505 |
| Opus 5.5 | $0.00059 | $0.00602 |
| Sonnet 5.5 | $0.00030 | $0.00301 |
| Haiku 4.5 | $0.00015 | $0.00151 |
Grade A, and why
idol-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 2mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
idol-short — 아이돌/아티스트 콘텐츠 쇼츠
A 60-second 9:16 short about a real idol/artist. The skill is genre-abstract;
the concrete artist is defined in a per-subject file (config/subjects/<id>.yaml)
selected with --subject=<id>. Real subject files are kept local (gitignored);
a tracked config/subjects/example.yaml is a placeholder template.
This is content about REAL PEOPLE. That inverts the legal posture vs a synthetic character: portrait/publicity rights (초상권·퍼블리시티권), music & MV copyright (agency-owned), trademark, and (Korean) defamation all apply. That is exactly why this pipeline has a 법률팀 — a single allowlist grep is not enough here. See the default-safe path below.
How to invoke
/idol-short "<topic>" --subject=<id> # selects config/subjects/<id>.yaml
/idol-short "<topic>" --subject=<id> --base=news # news-shaped (default) | info
Example topics (genre, not a specific artist): "<artist> comeback single release date", "<artist> member's solo channel hits a subscriber milestone".
The default-safe path (what this skill produces)
To stay clearly inside what a fan/news channel may publish, the default render uses only:
- synthetic AI narration (a narrator voice — never a member's voice),
- officially-announced, sourced facts (research-team cites official channels
- reputable outlets),
- license-clean generic B-roll (Pexels) + on-screen text,
- channel branding + mandatory disclaimers burned in.
It deliberately uses NO member photos/video, NO group audio, and NO agency-owned media — those are the high-risk items. If the operator wants to include any of them, the 법률팀 flags it (rights needed) before release.
The subject file
config/subjects/<id>.yaml is the single source of truth for a subject: the
group's official channels (for source verification), branding (channel name +
colors, text-based, no member likeness), the legal posture (incl.
has_minors), and the two mandatory disclaimers. See
config/subjects/README.md for the schema; copy example.yaml and fill in a
real artist locally. Keep real subject files local — they are gitignored.
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.
- 2mo ago First seen · 106 lines · 148 tokens per session scan A bfc1805b23d8
idol-short is a skill published in the GitHub repository MelonS/MelonS-Agents (17 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 1,505 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
refactor-clean
Refactor cleanly instead of layering sediment. Use for rename requests, stale or misleading names, legacy leftovers, changed scope, or when a change reveals duplicated concepts, local adapters, obsolete owners, redundant inputs or guards, compatibility wrappers, parallel abstractions, an over-large module that has…