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 agentmods add instructions/yunyoujun/advjs/claude-mdgit 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/instructions/yunyoujun/advjs/claude-md)<a href="https://agentmods.dev/instructions/yunyoujun/advjs/claude-md"><img src="https://agentmods.dev/badge/instructions/yunyoujun/advjs/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01119 | $0.01119 |
| Opus 5 | $0.00560 | $0.00560 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
advjs CLAUDE.md 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
ADV.JS is a front-end ADV (Adventure/Visual Novel) game engine built with Vue 3, Vite, and TypeScript. It uses a Markdown-based scripting language (.adv.md) parsed into an AST for game dialogue and scenes. Licensed under MPL-2.0.
Common Commands
pnpm install # Install dependencies (pnpm only, enforced via preinstall)
pnpm build # Build all packages (packages/* only)
pnpm dev # Dev mode for all packages + plugins in parallel
pnpm lint # ESLint (uses @antfu/eslint-config with UnoCSS + formatters)
pnpm test # Run unit tests with Vitest (jsdom environment)
pnpm e2e # Run Playwright e2e tests
pnpm e2e:ui # Playwright e2e with interactive UI
pnpm typecheck # vue-tsc type checking
# Run a single unit test file
pnpm vitest run tests/unit/basic.test.ts
# Dev specific packages
pnpm demo # Run demo/starter dev server
pnpm editor # Run editor dev server
pnpm play # Run playground dev server
pnpm docs # Run docs dev server
Build Order
Packages have dependencies that require ordered builds:
@advjs/types → @advjs/parser → @advjs/core → advjs
Use pnpm build:advjs to build the full chain in order.
Monorepo Architecture
Managed with pnpm workspaces. Dependency versions use pnpm catalogs (defined in pnpm-workspace.yaml).
Key Packages (packages/)
@advjs/types— Shared TypeScript type declarations for the entire project@advjs/parser— Markdown-to-AST parser using unified/remark ecosystem. Parses.adv.mdfiles into a structured AST for the game engine@advjs/core— Core engine library: game engine runtime, session management, i18n, VRM model supportadvjs— Main entry package with CLI (advbinary), Vite plugin integration, node/client split architecture, theme resolution@advjs/client— Vue 3 client app: pages, layouts, components, composables, Pixi.js integration@advjs/gui— GUI components (publishable)@advjs/shared— Shared utilities between node and client@advjs/vite-plugin-adv— Vite plugin for ADV.JS@advjs/flow— Visual flow/node editor using Vue Flow
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.
- 4d ago First seen · 101 lines · 1,119 tokens per session scan A 1b5a7cb34f33
advjs CLAUDE.md is an instructions file published in the GitHub repository YunYouJun/advjs (325 stars, last pushed 15d ago), licensed MPL-2.0. It adds 1,119 tokens to every session, about $0.0056 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 instructions, from other repositories
FlingEngine AGENTS.md
Instructions for flingengine/FlingEngine, covering agents.md, what this project is, build, tests and coding style.
FlingEngine CLAUDE.md
Instructions for flingengine/FlingEngine: See @AGENTS.md for project guidance (build, tests, coding style, architecture).
next-engine AGENTS.md
AGENTS.md instructions for Fantety/next-engine, a project described as: Next Engine – Multi-platform 2D and 3D game engine with AI.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
telegramify-markdown AGENTS.md
Instructions for sudoskys/telegramify-markdown, covering telegramify-markdown agent guide, task routing, quick commands, project rules and architecture map.