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 yub369302-cyber/gathered-scenes-zine-skill --skill scene-distillation-zine-v1-3git clone --depth 1 https://github.com/yub369302-cyber/gathered-scenes-zine-skillWrote 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/yub369302-cyber/gathered-scenes-zine-skill/scene-distillation-zine-v1-3)<a href="https://agentmods.dev/skills/yub369302-cyber/gathered-scenes-zine-skill/scene-distillation-zine-v1-3"><img src="https://agentmods.dev/badge/skills/yub369302-cyber/gathered-scenes-zine-skill/scene-distillation-zine-v1-3/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/yub369302-cyber/gathered-scenes-zine-skill/scene-distillation-zine-v1-3"><img src="https://agentmods.dev/badge/skills/yub369302-cyber/gathered-scenes-zine-skill/scene-distillation-zine-v1-3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 254 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00187 | $0.05580 |
| Opus 5 | $0.00093 | $0.02790 |
| Sonnet 5 | $0.00037 | $0.01116 |
| Haiku 4.5 | $0.00019 | $0.00558 |
Grade A, and why
scene-distillation-zine-v1-3 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scene Distillation Zine v1.3
Turn a supplied photo into an independently compelling paper-poster artwork. Treat the photo as semantic evidence and creative stimulus, never as a visual layer in the final image.
Return:
- the generated raster image;
- a concise Chinese explanation of the creative idea;
- concise art-direction notes.
Do not display the generation prompt. After generating, deliver directly without visual inspection, quality-gate review, or automatic regeneration, unless the user explicitly asks for a check or a revision.
Decision Priority
Resolve conflicts in this order:
- Establish one specific artistic proposition and embody it visibly.
- Build one central emotional or conceptual tension from the source.
- Create a complete artwork with an independent aesthetic voice.
- Preserve the source's semantic nucleus and emotional provenance.
- Recompose, simplify, exaggerate, and invent with purpose.
- Establish figure–ground clarity, hierarchy, balance, and a deliberate eye path.
- Make edge, material, color, space, and typography serve the proposition.
- Preserve substantial quiet space and one interpretive opening.
- Apply the requested color mode faithfully and use high chroma with purpose.
- Keep the result tactile, flat, poetic, and non-commercial.
Do not treat this as photo filtering, style transfer, rotoscoping, or a literal illustrated copy.
Consent and Source Handling
- Treat a supplied photo plus a request to transform or generate as consent to use image generation; do not ask again.
- Use the photo as a reference image for semantic and visual analysis only.
- Send only the final prompt and required reference image to the image-generation service.
- Do not browse, search, share, or upload the source elsewhere.
- Do not save the source into project files unless the user asks.
- State briefly after generation that the prompt and reference image were used by the generation service.
Build the Distillation Card
Inspect the photo before composing. Resolve:
What ships with it
1 file 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.
- 12d ago First seen · 427 lines · 187 tokens per session scan A 088116c2bbf7
scene-distillation-zine-v1-3 is a skill published in the GitHub repository yub369302-cyber/gathered-scenes-zine-skill (47 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 5,580 once invoked, about $0.0009 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
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.