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 imartinstudio/cover-prompt-skills --skill cover-light-productgit clone --depth 1 https://github.com/imartinstudio/cover-prompt-skillsWrote 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/imartinstudio/cover-prompt-skills/cover-light-product)<a href="https://agentmods.dev/skills/imartinstudio/cover-prompt-skills/cover-light-product"><img src="https://agentmods.dev/badge/skills/imartinstudio/cover-prompt-skills/cover-light-product/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/imartinstudio/cover-prompt-skills/cover-light-product"><img src="https://agentmods.dev/badge/skills/imartinstudio/cover-prompt-skills/cover-light-product.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 | $0.00113 | $0.05044 |
| Opus 5 | $0.00056 | $0.02522 |
| Sonnet 5 | $0.00023 | $0.01009 |
| Haiku 4.5 | $0.00011 | $0.00504 |
Grade A, and why
cover-light-product 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 12d 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 — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Light Product Cover
Use this skill to create a finished image prompt, or call an image generation tool directly when the user asks to generate the final cover. The result must feel like a premium SaaS website hero banner from a $10B AI company—not an ad banner, not a stock illustration, not a tutorial cover.
If generating the image directly, keep all semantic and design analysis internal and output only the generated image result. Do not output analysis, explanations, reference collages, or multiple layout drafts. Generate exactly one complete cover.
If the user sets --out-type prompt, output only the final image prompt. If the user sets --out-type template or omits --out-type, output only the template described in "Template Output" and do not output a generic image prompt.
Output Type
Use the explicit --out-type parameter to decide what to output. Read --out-type only as a control parameter, not as part of the user's topic or subtitle.
--out-type template: output the invocation template only.--out-type prompt: output the final image prompt only.--out-type all: output the template first, then the final image prompt.- Omitted
--out-type: default totemplate.
Backward compatibility:
- Treat
模版,模板,整理成格式,标准格式,调用格式, and使用格式as--out-type template. - Treat explicit output requests such as
输出提示词,生成提示词,完整提示词,生图提示词,直接给 prompt,只要提示词,只要 prompt, andimage promptas--out-type prompt. - Treat
模版和提示词,模板和 prompt,模版+提示词,两个都要,都输出,先给模版再给提示词, and既要标准格式也要完整 promptas--out-type all. - Treat
直接生成,生成海报,出图,生成封面图as direct image generation when an image tool is available.
Do not infer prompt mode from field values. For example, 主题：提示词 means the topic is "提示词"; it does not by itself mean --out-type prompt.
If --out-type has any value other than template, prompt, or all, ask the user to choose one of those three values.
Template Output
For template-only mode, output exactly this structure and fill every field:
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.
- 12d ago First seen · 388 lines · 113 tokens per session scan A 8abd818ac7b3
cover-light-product is a skill published in the GitHub repository imartinstudio/cover-prompt-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 5,044 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 2026-08-31.
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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.