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-storygit 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-story)<a href="https://agentmods.dev/skills/yunyoujun/advjs/adv-story"><img src="https://agentmods.dev/badge/skills/yunyoujun/advjs/adv-story/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-story"><img src="https://agentmods.dev/badge/skills/yunyoujun/advjs/adv-story.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 | $0.00058 | $0.02000 |
| Opus 5 | $0.00029 | $0.01000 |
| Sonnet 5 | $0.00012 | $0.00400 |
| Haiku 4.5 | $0.00006 | $0.00200 |
Grade A, and why
adv-story 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 10d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADV Story Skill
You are an interactive narrator for ADV.JS visual novel stories. You drive the narrative by executing CLI commands and presenting story content to the user in an engaging way.
Overview
ADV.JS is a visual novel / interactive narrative engine. Scripts are written in .adv.md (Markdown) format. This skill enables you to load and play through stories interactively with full context awareness.
Before Starting: Load Context
Before playing any story, understand the project's world and characters:
adv context
This gives you the world setting, character descriptions, story outline, and chapter statuses. Use this information to:
- Present dialog in a way that matches character personalities
- Describe scenes with details from
scenes/*.md - Maintain narrative consistency with the world rules
For a specific chapter's context:
adv context --chapter <n>
Commands
Start a new story
adv play <script.adv.md> --session-id <unique-id> --json
This loads a script and returns the first displayable node.
Advance the story
adv play next --session-id <id> --json
Moves to the next narrative beat. Returns dialog, narration, choices, or end.
Make a choice
adv play choose <number> --session-id <id> --json
When the story presents choices, select one by number (1-based).
Roll back (undo)
adv play back --session-id <id> --json
adv play back --session-id <id> --steps 3 --json
Pop the rollback history stack and jump back to the previous displayable
node. Use this for "undo" UX when a player wants to revisit a moment without
the heavier save / load --slot workflow. The JSON response includes
requestedSteps (what you asked for) and poppedSteps (what actually
happened — capped at history length).
History accumulates as the player advances (one entry per displayable node,
consecutive duplicates collapsed). After rollback, status is forced to
playing so a session that had reached waiting_choice or ended becomes
re-playable.
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.
- 10d ago First seen · 270 lines · 58 tokens per session scan A 9bd9c392c85b
adv-story is a skill published in the GitHub repository YunYouJun/advjs (325 stars, last pushed 21d ago), licensed MPL-2.0. It adds 58 tokens to every session and 2,000 once invoked, about $0.0003 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
anti-cheat-systems
Analyze layered game integrity defenses and select repository resources for process-memory reports, acquired-memory forensics, callback scope, behavioral measurement and driver-policy evidence. Use for DMA versus host-mediated acquisition, input provenance, replay fidelity, collector health, detector rollout/recovery…
game-hacking-techniques
Classify game-cheating threats across client memory, code injection, rendering, input, engines, kernels, DMA and remote transports. Use for repository-backed attack-surface maps, attacker prerequisites, state exposure, legitimate comparison baselines, and observable artifacts. Select engine source, capture or…
windows-kernel-security
Analyze Windows driver trust boundaries and kernel evidence for game-security research. Use for IOCTL authorization, callbacks and IRQL, driver provenance, DSE/PatchGuard, VBS/HVCI, build-specific internals, and crash or memory forensics; select repository resources for symbol comparison, ETW metadata, driver-unit…
graphics-api-hooking
Analyze Direct3D/DXGI, OpenGL, and Vulkan rendering, presentation, composition, and capture evidence. Use to distinguish API samples, PresentMon event metrics, Tracy instrumentation, compatibility translation, frame images, and validation diagnostics; review swap chains, overlays, resource lifetime, and…
reverse-engineering-tools
Investigate supplied game binaries, protection components, drivers, dumps, and traces through reproducible binary analysis. Use for repository resource selection, PE/symbol inspection, disassembly and decompilation, control/data-flow reconstruction, build comparison, obfuscation classification, and interface evidence…
game-engine-resources
Analyze Unreal, Unity, Source, Godot, and custom engine trust boundaries and select matching repository resources. Use for engine/build identification, full source versus C# reference subsets, version-matched demos, editor versus shipped plugins, reflection and object lifecycles, Mono/IL2CPP, asset schemas, and…