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 rianvdm/product-ai-public --skill playlist-covergit clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/rianvdm/product-ai-public/playlist-cover)<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/playlist-cover"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/playlist-cover/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/rianvdm/product-ai-public/playlist-cover"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/playlist-cover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 47 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00117 | $0.06888 |
| Opus 5 | $0.00059 | $0.03444 |
| Sonnet 5 | $0.00023 | $0.01378 |
| Haiku 4.5 | $0.00012 | $0.00689 |
Grade A, and why
playlist-cover 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**When Rian names a cover he likes, go and look at it before designing.** `fetch-playlist.mjs` prints the playlist's `current cover` URL — `curl` it and Read the image. Describe what is actually there: subject, ground, p How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playlist covers
Overview
Read what a playlist actually contains, design three covers from it, look at them, and hand over the one that survives.
The core insight: the playlist name is the weakest signal available. Spotify hangs genre tags off every artist, so a playlist resolves to shoegaze ×198, slowcore ×111, dream pop ×89, 1990–2025 median 2021, mean popularity 24 — an era, a scene, and a sense of how underground it is. A playlist called "Guitars" tells you none of that. Fetch the brief before designing anything.
The second insight: image models misspell titles, and nothing in the API flags it — the request succeeds, the file writes, the path prints. The only way to catch it is to open the image. See The verification gate.
The house style
On 2026-08-17 Rian named three of his own covers as the target: Guitars (a burning Stratocaster on flat red), Calm (a hazy amber sunrise over a lake, title in spaced caps inside a thin square rule) and Dark Ambient (a near-black storm sky over a barren plain, title tiny and low-contrast). They look nothing alike and they are built the same way. Four rules, all four in every variant:
| Rule | What it means | The failure it replaces |
|---|---|---|
| One idea, fully committed | A single subject doing a single thing. Nothing added to fill space. | Collages and "and also a…" compositions, which read as clip art no matter how well rendered |
| Photographic realism | Rendered or shot, with real light and real material. | Flat vector and painterly illustration, which read as cheap |
| Near-monochrome | One hue family across a full range from near-white to near-black. Guitars is red/orange/black; Calm runs cream sky to amber water to shadowed ridges; Dark Ambient is grey-blue from pale cloud to black land. | The four-colour palettes this skill kept specifying, which dilute the image |
| Title as a designed lockup | The type is a graphic element with its own treatment — a face borrowed from the genre's visual culture, a considered size, sometimes a rule or frame around it. Small: roughly a third of the frame width, never a headline. | "Put the title in the empty area", which produces a caption rather than a cover |
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.
- 11d ago First seen · 258 lines · 117 tokens per session scan A 5555317085c8
playlist-cover is a skill published in the GitHub repository rianvdm/product-ai-public (16 stars, last pushed 3d ago), licensed MIT. It adds 117 tokens to every session and 6,888 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.