Borrowing it
Nothing to install: this file belongs to alecs5am/ralphy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alecs5am/ralphy/main/.agents/skills/vox-collage/SKILL.mdgit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/vox-collage)<a href="https://agentmods.dev/skills/alecs5am/ralphy/vox-collage"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/vox-collage/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/alecs5am/ralphy/vox-collage"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/vox-collage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Agent Snooping · line 188 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 189 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00358 | $0.05169 |
| Opus 5 | $0.00179 | $0.02584 |
| Sonnet 5 | $0.00072 | $0.01034 |
| Haiku 4.5 | $0.00036 | $0.00517 |
Grade A, and why
vox-collage 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 9d 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.
A generalized craft overlay that adapts the vox-director METHOD to OUR stack. It does not name a topic, a person, or an aesthetic — it tells the art-director + editor HOW a paper-collage motion video is built so a strong How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on a generic paper-collage motion-video brief: "make a vox-style video about X", "turn this topic into a collage explainer", "motion collage ad for our product", "sticker-collage explainer", "torn-paper animated short", "scrapbook tribute to ". Any subject — the skill is subject-agnostic.
DO NOT FIRE when:
- The brief is for static multi-slide stills (a swipe-through deck) → use
/carousel. - The brief is for ONE still (poster / key art) → use
/poster. - The brief is a creepy PSA / VHS warning → use
/analog-horror-psa. - The user points at one specific collage video to reproduce → that is the remix path. See
docs/skills-vs-templates.md.
What this skill is
A generalized craft overlay that adapts the vox-director METHOD to OUR stack. It does not name a topic, a person, or an aesthetic — it tells the art-director + editor HOW a paper-collage motion video is built so a strong one comes out for whatever the user is pushing. Every model call routes through ralphy generate / ralphy render (AGENTS.md invariants #1, #2) — no provider API, no Atlas Cloud plumbing, no ad-hoc curl/ffmpeg for the paid steps.
The one idea to internalize: the collage LOOK and the collage MOTION are two different steps.
- The look is born in the IMAGE step. Each beat is a finished collage poster made by a text-to-image model. All the collage DNA (torn paper, cut-outs, halftone, bold flat color, baked headline) lives in that poster. If the image is not a rich, dense collage, nothing downstream saves it.
- The motion is added after. A flat-safe i2v pass animates the whole poster ("living poster"). The constraint set is what makes a video model animate flat art without warping it.
Before writing ANY image or motion prompt, read the two references — they are the whole craft:
references/prompt-guide.md— the LOOK layer (image + motion prompt structures, the vocabulary banks, the era-matched theme presets).references/beat-layer.md— the STORY layer (narrative arcs, hook patterns, beat counts, the hard-constrained flat-safe camera-move vocab).
What ships with it
2 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.
- 9d ago First seen · 193 lines · 358 tokens per session scan A 3fc4f45e5dd8
vox-collage is a skill published in the GitHub repository alecs5am/ralphy (132 stars, last pushed 14d ago), licensed Apache-2.0. It adds 358 tokens to every session and 5,169 once invoked, about $0.0018 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
molecule-visualization
Publication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
ai-image-to-pptx
A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.