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 product-cfgit 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/product-cf)<a href="https://agentmods.dev/skills/melons/melons-agents/product-cf"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/product-cf/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/product-cf"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/product-cf.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 | $0.00000 | $0.01113 |
| Opus 5.5 | $0.00000 | $0.00445 |
| Sonnet 5.5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
product-cf 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(bash:*) Bash(ffmpeg:*) Bash(ffprobe:*) Bash(curl:*) Bash(jq:*) Read Write How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
product-cf
Make a commercial-film-feel (CF) vertical short from one product photo. The defining constraint: never regenerate the product. Generative video distorts labels and mangles hands — exactly the two things a product ad cannot afford. So the product stays a real, pixel-perfect cutout and the world moves around it.
Why a separate skill (not a music-video mode)
music-video is music-as-primary-audio + free-to-morph mood B-roll.
product-cf differs on all three split criteria:
| criterion | music-video | product-cf |
|---|---|---|
| primary input | a music file | a product photo |
| trigger intent | "make a music vid" | "make an ad for this product" |
| hard invariant | none | product label integrity (never morphs) |
So product-cf is its own skill, but it reuses music-video as a
black box for the parts that overlap (beat detection, Pexels B-roll,
9:16 render, shaders). music-video's run.sh is never edited.
The technique (compositing + 2.5D, no I2V on the product)
- Cutout —
rembgremoves the background → product PNG with alpha. - 2.5D camera move — product gets a slow push-in / drift; the background scene moves at a different rate → parallax depth. Product pixels never change, only the virtual camera.
- Label light-sweep — a specular highlight travels across the label, masked to the product alpha. The "premium product shot" tell.
- Motion lives around the product, not on it — splashes, ice, condensation, bokeh come from liquid B-roll (music-video's Pexels layer) intercut with the hero shot, or composited as foreground particles. "Shaking / pouring / drinking" is implied via these cuts — the real product is never touched by a hand or liquid.
- Beat-synced assembly — music-video supplies beat-aligned cut points; hero shots land on the strong beats, B-roll fills between.
What ships with it
6 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.
- 2mo ago First seen · 85 lines · 0 tokens per session scan A 6a50c9cf6034
product-cf is a skill published in the GitHub repository MelonS/MelonS-Agents (17 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,113 tokens. 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
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…