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/ugc-rockstar/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/ugc-rockstar)<a href="https://agentmods.dev/skills/alecs5am/ralphy/ugc-rockstar"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/ugc-rockstar/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/ugc-rockstar"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/ugc-rockstar.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 | $0.00217 | $0.01770 |
| Opus 5 | $0.00109 | $0.00885 |
| Sonnet 5 | $0.00043 | $0.00354 |
| Haiku 4.5 | $0.00022 | $0.00177 |
Grade A, and why
ugc-rockstar 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 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.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on: "GTA-style video", "make it feel like GTA V / Los Santos", "Rockstar aesthetic", "Vinewood crime short", "satirical fake-brand ad like the GTA radio", "heist-cinema look".
DO NOT FIRE when:
- The user points at one specific GTA-style video to reproduce → remix path (
ralphy template use <slug>). - The brief is a different aesthetic (analog horror, cinematic-narrative, clean UGC) → match that niche.
What this skill is
A generalized style overlay, not a finished video. It tells the scenarist and art-director HOW the Rockstar register reads so they produce a strong one for whatever premise the user brings. Runs through the normal pipeline and all gates.
Hard invariants
- Provider invariants stand. All generation via
ralphy generate; renders viaralphy render <id>. No Higgsfield / Runway / raw API — those appear in the source draft and are NOT our stack. ReadMODELS.mdfor the current i2v / image ids. - Original homage, not impersonation. Build the aesthetic and satirical world — do not impersonate a real living person, and do not reproduce a specific copyrighted GTA mission/scene shot-for-shot. Fake brands and invented characters are the point.
- Music is a separate ElevenLabs pass with no artist/producer names (
MEMORY.md) — describe the register (West-Coast hip-hop bed, cinematic tension score) by genre + instrumentation only. Ban music in the Kling prompt; overlay in the editor.
The GTA-V visual DNA (internalize before any output)
- Cinematic identity: late-2000s LA crime cinema (Mann / Scott / Fincher) filtered through satire. Hyperreal, slightly oversaturated, always slightly dangerous.
- Light: golden hour by default; even night is hot, neon-soaked.
- Camera: low angles for power, eye-level for vulnerability; slow-push establishing (wide, then creep in); rack focus on dialogue (bokeh'd luxury or grim urban texture behind a sharp face); the helicopter aerial pull-back (city as context for chaos).
- Grade: teal-and-orange pushed further — teal/cyan shadows, amber/gold highlights, skin popping orange.
- Tone — the double register: simultaneously funny AND real AND slightly dangerous. Never just funny, never just violent. A billboard, a radio line, or a fake brand in the background that comments on the world.
- Specificity: not "a luxury car" but "a Benefactor-style sedan in the hills, 7pm warm light"; not "a criminal" but "a man in a tracksuit outside an ammo store". The environment talks.
- Scene logic (the four levels): location → establishes character → creates conflict → reveals something about power/money, and through that, something universal. A chase isn't about the chase; it's about who owns the street.
What ships with it
7 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.
- 11d ago First seen · 86 lines · 217 tokens per session scan A 31acf918835b
ugc-rockstar is a skill published in the GitHub repository alecs5am/ralphy (133 stars, last pushed yesterday), licensed Apache-2.0. It adds 217 tokens to every session and 1,770 once invoked, about $0.0011 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
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
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.
lanshu-create-ai-presenter-video
Turn a topic or finished script plus an authorized adult presenter image into a complete, publish-ready AI presenter video. Use for new presenter videos and for continuing, revising, captioning, lip-sync repairing, or re-exporting an existing presenter-video job. Keep model and provider selection capability-based and…
open-video
Generate, edit, or direct videos via open-source models (MiniMax H3 baseline; Wan2.2 / LTX future). Use when the user wants to turn a concept, script, or reference image into a finished video or multi-shot film — single shots, image-to-video, first-last-frame interpolation, reference-video/audio styling, or stitched…
image-generation-gateways
Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts, data-governance review, and billing observability. Use for comparing or building against fal.ai, Replicate, or Together AI…
runway-video
Build and operate production-safe Runway API video generation, video editing, and character-performance workflows with native Runway models, explicit paid-call approval, duplicate-create protection, asynchronous task handling, secure media transfer, and evidence-aware governance.