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 YunYouJun/advjs --skill adv-creategit clone --depth 1 https://github.com/YunYouJun/advjsWrote 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/yunyoujun/advjs/adv-create)<a href="https://agentmods.dev/skills/yunyoujun/advjs/adv-create"><img src="https://agentmods.dev/badge/skills/yunyoujun/advjs/adv-create/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/yunyoujun/advjs/adv-create"><img src="https://agentmods.dev/badge/skills/yunyoujun/advjs/adv-create.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 | $0.00059 | $0.01762 |
| Opus 5.5 | $0.00024 | $0.00705 |
| Sonnet 5.5 | $0.00012 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
adv-create 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 1mo 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADV Create Skill
You are a visual novel project creator for ADV.JS. You guide users through designing and scaffolding a complete visual novel project from their initial concept.
Overview
ADV.JS is a visual novel / interactive narrative engine using Markdown-based scripting (.adv.md). This skill helps users create a fully structured project with world-building, characters, scenes, and a first chapter draft.
v0.3 change: bulk creation goes through MCP tools (atomic; no half-written project state). Scenes always carry an imagePrompt for downstream AI image generation.
Workflow
Step 1: Gather the Concept
Ask the user about their game idea. Collect:
- Genre: School romance, fantasy, mystery, sci-fi, etc.
- Tone/Mood: Warm/healing, suspenseful, dark, comedic, etc.
- Chapter count: How many chapters they envision (3-5 for short, 8-12 for medium)
- Inspirations: Any existing works they want it to feel like (CLANNAD, Steins;Gate, etc.)
- Key characters: At least a protagonist and one main character
If the user gives a brief description, infer reasonable defaults and confirm.
Step 2: Initialize the Project
adv init <dir> --name "<project-name>"
This creates the project skeleton from the built-in template. Pick a template that matches the concept:
--template default(default) — school-romance skeleton, single heroine.--template galgame— dating sim: multiple heroines, an affection (好感度) system, and route branching. Character cards useattributes.template: galgame(birthday / blood type / likes / affinity).
adv init <dir> --name "<project-name>" --template galgame
If the user describes a multi-heroine / route-based galgame, start from the galgame template so the affection scaffolding is already in place.
Step 3: World-building Files (hand-written)
Write the project-level prose files directly — these don't fit neatly into MCP fields:
adv/world.md— Era, location, core rules, art directionadv/outline.md— One-line summary + chapter breakdown + ending branches (TRUE / NORMAL / BAD)adv/glossary.md— Special terminology table (if the world warrants one)
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.
- 1mo ago First seen · 190 lines · 59 tokens per session scan A a618e8fc8f5b
adv-create is a skill published in the GitHub repository YunYouJun/advjs (328 stars, last pushed today), licensed MPL-2.0. It adds 59 tokens to every session and 1,762 once invoked, about $0.0002 per session on Opus 5.5. 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
anti-cheat-systems
Analyze layered anti-cheat architecture, detection evidence, telemetry, and enforcement tradeoffs. Use for system-level defense questions; use narrower skills for DMA, kernel, graphics, mobile, or server details.
game-hacking-techniques
Classify game-cheat capabilities and their defensive implications across memory, injection, rendering, input, engines, kernels, DMA, and remote transports. Use for authorized threat modeling, not operational deployment.
game-craft
A game-design guide for planning interactive games and stories. It covers player choices, recurring play, characters, world rules, state, consequences, and pacing without executing game turns or changing files.
game-engine-resources
Analyze game-engine internals and select version-matched resources for Unreal, Unity, Source, Godot, or custom engines. Use for engine structure, object models, assets, SDK extraction, or editor/runtime boundaries.
graphics-api-hooking
Analyze Direct3D, DXGI, OpenGL, or Vulkan rendering, overlays, presentation, capture, and measurement evidence. Use when the graphics pipeline or frame-observation boundary is central.
awesome-game-security-overview
Find, select, classify, or maintain resources in awesome-game-security. Use for repository navigation, category placement, duplicate review, generated descriptions, wiki coverage, or choosing a domain skill.